Speech Analytics

Speech Recognition Leaps Forward - Is it a revolution?

2011-08-31T07:47:00.000-04:00

Great news from Microsoft about substantial progress in LVCSR.

Please comment if you experience this technology and if you indeed view it as a revolution.

Thx, Ofer

See details in: http://research.microsoft.com/en-us/news/features/speechrecognition-082911.aspx

Speech Recognition Leaps Forward

By Janie Chang

August 29, 2011 12:01 AM PT

During Interspeech 2011, the 12th annual Conference of the International Speech Communication Association being held in Florence, Italy, from Aug. 28 to 31, researchers from Microsoft Research will present work that dramatically improves the potential of real-time, speaker-independent, automatic speech recognition.
Dong Yu, researcher at Microsoft Research Redmond, and Frank Seide, senior researcher and research manager with Microsoft Research Asia, have been spearheading this work, and their teams have collaborated on what has developed into a research breakthrough in the use of artificial neural networks for large-vocabulary speech recognition.

The Holy Grail of Speech Recognition

Commercially available speech-recognition technology is behind applications such as voice-to-text software and automated phone services. Accuracy is paramount, and voice-to-text typically achieves this by having the user “train” the software during setup and by adapting more closely to the user’s speech patterns over time. Automated voice services that interact with multiple speakers do not allow for speaker training because they must be usable instantly by any user. To cope with the lower accuracy, they either handle only a small vocabulary or strongly restrict the words or patterns that users can say.
The ultimate goal of automatic speech recognition is to deliver out-of-the-box, speaker-independent speech-recognition services—a system that does not require user training to perform well for all users under all conditions.

“This goal has increased importance in a mobile world,” Yu says, “where voice is an essential interface mode for smartphones and other mobile devices. Although personal mobile devices would be ideal for learning their user’s voices, users will continue to use speech only if the initial experience, which is before the user-specific models can even be built, is good.”
Speaker-independent speech recognition also addresses other scenarios where it’s not possible to adapt a speech-recognition system to individual speakers—call centers, for example, where callers are unknown and speak only for a few seconds, or web services for speech-to-speech translation, where users would have privacy concerns over stored speech samples.

Renewed Interest in Neural Networks

Artificial neural networks (ANNs), mathematical models of the low-level circuits in the human brain, have been a familiar concept since the 1950s. The notion of using ANNs to improve speech-recognition performance has been around since the 1980s, and a model known as the ANN-Hidden Markov Model (ANN-HMM) showed promise for large-vocabulary speech recognition. Why then, are commercial speech-recognition solutions not using ANNs?
“It all came down to performance,” Yu explains. “After the invention of discriminative training, which refines the model and improves accuracy, the conventional, context-dependent Gaussian mixture model HMMs (CD-GMM-HMMs) outperformed ANN models when it came to large-vocabulary speech recognition.”
Yu and members of the Speech group at Microsoft Research Redmond became interested in ANNs when recent progress in building more complex “deep” neural networks (DNNs) began to show promise at achieving state-of-the-art performance for automatic speech-recognition tasks. In June 2010, intern George Dahl, from the University of Toronto, joined the team, and researchers began investigating how DNNs could be used to improve large-vocabulary speech recognition.
“George brought a lot of insight on how DNNs work,” Yu says, “as well as strong experience in training DNNs, which is one of the key components in this system.”
A speech recognizer is essentially a model of fragments of sounds of speech. An example of such sounds are “phonemes,” the roughly 30 or so pronunciation symbols used in a dictionary. State-of-the-art speech recognizers use shorter fragments, numbering in the thousands, called “senones.”
Earlier work on DNNs had used phonemes. The research took a leap forward when Yu, after discussions with principal researcher Li Deng and Alex Acero, principal researcher and manager of the Speech group, proposed modeling the thousands of senones, much smaller acoustic-model building blocks, directly with DNNs. The resulting paper, Context-Dependent Pre-trained Deep Neural Networks for Large Vocabulary Speech Recognition by Dahl, Yu, Deng, and Acero, describes the first hybrid context-dependent DNN-HMM (CD-DNN-HMM) model applied successfully to large-vocabulary speech-recognition problems.
“Others have tried context-dependent ANN models,” Yu observes, “using different architectural approaches that did not perform as well. It was an amazing moment when we suddenly saw a big jump in accuracy when working on voice-based Internet search. We realized that by modeling senones directly using DNNs, we had managed to outperform state-of-the-art conventional CD-GMM-HMM large-vocabulary speech-recognition systems by a relative error reduction of more than 16 percent. This is extremely significant when you consider that speech recognition has been an active research area for more than five decades.”
The team also accelerated the experiments by using general-purpose graphics-processing units to train and decode speech. The computation for neural networks is similar in structure to 3-D graphics as used in popular computer games, and modern graphics cards can process almost 500 such computations simultaneously. Harnessing this computational power for neural networks contributed to the feasibility of the architectural model.
In October 2010, when Yu presented the paper to an internal Microsoft Research Asia audience, he spoke about the challenges of scalability and finding ways to parallelize training as the next steps toward developing a more powerful acoustic model for large-vocabulary speech recognition. Seide was excited by the research and joined the project, bringing with him experience in large-vocabulary speech recognition, system development, and benchmark setups.

Benchmarking on a Neural Network

“It has been commonly assumed that hundreds or thousands of senones were just too many to be accurately modeled or trained in a neural network,” Seide says. “Yet Yu and his colleagues proved that doing so is not only feasible, but works very well with notably improved accuracy. Now, it was time to show that the exact same CD-DNN-HMM could be scaled up effectively in terms of training-data size.”
The new project applied CD-DNN-HMM models to speech-to-text transcription and was tested against Switchboard, a highly challenging phone-call transcription benchmark recognized by the speech-recognition research community.
First, the team had to migrate the DNN training tool to support a larger training data set. Then, with help from Gang Li, research software-development engineer at Microsoft Research Asia, they applied the new model and tool to the Switchboard benchmark with more than 300 hours of speech-training data. To support that much data, the researchers built giant ANNs, one of which contains more than 66 million inter-neural connections, the largest ever created for speech recognition.
The subsequent benchmarks achieved an astonishing word-error rate of 18.5 percent, a 33-percent relative improvement compared with results obtained by a state-of-the-art conventional system.

“When we began running the Switchboard benchmark,” Seide recalls, “we were hoping to achieve results similar to those observed in the voice-search task, between 16- and 20-percent relative gains. The training process, which takes about 20 days of computation, emits a new, slightly more refined model every few hours. I impatiently tested the latest model every few hours. You can’t imagine the excitement when it went way beyond the expected 20 percent, kept getting better and better, and finally settled at a gain of more than 30 percent. Historically, there have been very few individual technologies in speech recognition that have led to improvements of this magnitude.”
The resulting paper, titled Conversational Speech Transcription Using Context-Dependent Deep Neural Networks by Seide, Li, and Yu, is scheduled for presentation on Aug. 29. The work already has attracted considerable attention from the research community, and the team hopes that taking the paper to the conference will ignite a new line of research that will help advance the state of the art for DNNs in large-vocabulary speech recognition.

Bringing the Future Closer

With a novel way of using artificial neural networks for speaker-independent speech recognition, and with results a third more accurate than what conventional systems can deliver, Yu, Seide, and their teams have brought fluent speech-to-speech applications much closer to reality. This innovation simplifies speech processing and delivers high accuracy in real time for large-vocabulary speech-recognition tasks.
“This work is still in the research stages, with more challenges ahead, most notably scalability when dealing with tens of thousands of hours of training data. Our results represent just a beginning to exciting future developments in this field,” Seide says. “Our goal is to open possibilities for new and fluent voice-based services that were impossible before. We believe this research will be used for services that change how we work and live. Imagine applications such as live speech-to-speech translation of natural, fluent conversations, audio indexing, or conversational, natural language interactions with computers.”

iOS Speech Recognition Settings Confirm Nuance-Apple Partnership

2011-06-13T02:32:00.000-04:00

Interesting post @ http://www.macrumors.com/2011/06/11/ios-speech-recognition-settings-confirm-nuance-apple-partnership/

A couple of screenshots posted on Twitter by @ChronicWire reveals hidden Nuance preferences found in the latest internal iOS builds that confirms that Apple has been actively working on building in speech recognition into iOS.

Rumors of a Nuance-Apple partnership had been heavy in the weeks prior to WWDC, though no announcements were made during the keynote. Later, comments by Robert Scoble indicated that the deals were simply not completed in time for WWDC but were still in the works:

I was told weeks ago by my source (same one who told me Twitter would be integrated deeply into the OS) that Siri wouldn't be done in time. Maybe for this fall's release of iPhone 5? After all, they need to have some fun things to demo for us in August, no?

The source of the screenshots (@Chronic / @SonnyDickson) has been known to have legitimate sources in the past. So, it seems certain that Apple is actively working on bringing Nuance speech recognition into iOS, perhaps as early as iOS 5 this fall.

Again: Nuance Slaps Vlingo With Another Patent Lawsuit Over Voice Recognition Technology

2011-06-11T10:46:00.000-04:00

I guess Nuance is trying again to acquire Vlingo (given its standard sue before acquire strategy).

See below from Techcrunch: http://techcrunch.com/2011/06/09/nuance-sues-vlingo-again-over-voice-recognition-patents/#comments

Well, this is interesting. Nuance, a company that develops imaging and voice recognition technologies, is once again suing competitor Vlingo, which also develops a voice search technology and is backed by Yahoo, AT&T and Charles River Ventures.
According to the suit, which we’ve embedded below, Nuance claims Vlingo is infringing on number of Nuance’s patents including U.S. patent no. 6,487,534 B1, which relates to a “Distributed Client-Server Speech Recognition System.” By making, using, selling, offering to sell, and or importing its products and services related to speech recognition, Nuance says Vlingo is infringing on its patent.
Nuance is also claiming that Vlingo is infringing on that U.S. patent no. 6,785,653 B1, which is titled “Distributed Voice Web Architecture and Associated Components and Methods,” U.S. patent no. 6,839,669 B1, titled “Performing Actions Identified in Recognized Speech;” U.S. patent number No. 7,058,573 B1, titled “Speech Recognition System to Selectively Utilize Different Speech Recognition Techniques Over Multiple Speech Recognition Passes;” and U.S. patent no. 7,127,393 B2, titled “Dynamic Semantic Control of a Speech Recognition System.”
Nuance is requesting that Vlingo pay damages for infringing and profiting off the patents, but it’s unclear what the dollar amount of these damages are.
The two companies have a bit of a storied past. Nuance slapped Vlingo with a patent lawsuit back in 2008. Vlingo then bought a number of patents last year relating to voice and speech recognition, that aimed to force Nuance to drop its suit.
Dave Grannan, CEO of Vlingo, recently compared the act of competing with Nuance to
“having a venereal disease that’s in remission.” He tells Bloomberg BusinessWeek, “We crush them whenever we go head-to-head with them. But just when you’re thinking life is great – boom, there’s a sore on your lip.” Gross.
Nuance is a massive company with a $6 billion market cap and is a formidable competitor. In fact, Apple appears to be licensing Nuance’s technology in OS X Lion. And we heard that Nuance was in negotiations with Apple for a partnership to license and use the company’s voice recognition technology, though Nuance was missing from the lineup of products revealed this week’s WWDC conference. And we’ve learned that Apple may already be using Nuance technology in their new massive data center in North Carolina.
Photo Credit/Flickr/KWDesigns

View this document on Scribd

The Search for a Clearer Voice - How Google's Voice Search is getting so good.

2011-01-11T02:41:00.000-05:00

An interesting post by Paul Boutin: http://www.technologyreview.com/blog/guest/26242/?p1=A2

It raises again the issue of talking with the right (= US) accent to your phone.

The Search for a Clearer Voice

How Google's Voice Search is getting so good.

Paul Boutin 01/10/2011

Smart phones are great at a lot of things, with one exception: Typing on a touch screen or a downsized keyboard is still frustrating compared to a full-size computer keyboard. That's probably why Google says that, even before the release of its new personalized Voice Search app for Android in mid-December, one in four mobile searches were already input by voice rather than from a keyboard.
The improved Voice Search takes speech recognition to its next level: Google's servers will now log up to two years of your voice commands in order to more precisely parse exactly what you're saying.
In tests on the new app, which appeared in Google's Android Market a week before Christmas, the app originally got about three out of five searches correct. After a few days, the ratio crept up to four out of five. It's surprisingly good at searches that involve common nouns ("heathen child lyrics") and what search experts call vertical searches for popular topics like airline flights and movie listings. Voice Search knows "United Flight 714" and "True Grit show times 90066" when it hears them. Less successful are searches involving people's names. In repeated attempts to Google up WikiLeaks founder Julian Assange, Voice Search got no closer than "wikileaks founder julian of songs."
How does it work? Rather than try to use the phone itself to do speech recognition, Voice Search digitizes the user's input commands and sends them off to Google's gargantuan server farms. There, the spoken words are broken down and compared both to statistical models of what words other people mean when they utter those syllables, plus a history of the user's own voice commands, through which Google refines its matching algorithm for that particular voice. The app recognizes five different flavors of English—American, British, Australian, Indian and South African—plus Afrikaans, Cantonese, Czech, Dutch, French, German, Italian, Japanese, Korean, Mandarin, Polish, Portugese, Russian, Spanish, Turkish, and Zulu.
The tricky part—and the motive for a personalized search app—is that human voices vary wildly between men and women, between young people and old people, and among those with various accents and dialects. By storing hundreds, perhaps thousands of what speech recognition experts call "utterances" by the same person over months of use, Voice Search can better guess at what that particular person is saying.
That mathematical model used to recognize phrases was refined over three years using voice samples from Google's now-defunct GOOG-411 automated directory assistance service, which the company operated from 2007 through late last year specifically to capture a wide-ranging set of voice samples for analysis. The company's first Voice Search app, for iPhone only, was launched a year after GOOG-411 in November 2008.
Voice Search doubles as a spoken-command system for the phone. As shown in this video, it understands commands such as, "Send mail to Mike LeBeau. How's life in New York treating you? The weather's beautiful here." The app will find LeBeau in your contacts—it's better at matching names here than in a Web search, because it's working with a limited set—and will fill in the subject line with your first sentence. You can speak additional text into the message, or edit it with the phone's keyboard, before sending it.
Google has clearly put a lot of effort into its speech recognition technology. But the impact on it bottom line is obvious: By removing the aggravation of typing on tiny keys, the company hopes to get customers to reach for its search and e-mail services much more often.

New speech analysics whitepaper

2010-09-25T03:52:00.000-04:00

Nice whitepaper from io speech analysics.

http://images.tmcnet.com/tmc/whitepapers/documents/whitepapers/2010/3013-speech-analytics-simple-definition.pdf

Nuance Launches Dragon Dictate for Mac -- Simply Smarter Speech Recognition

2010-09-23T14:38:00.001-04:00

Dragon Speech Application for Mac OS X Taps New Dragon 11 Engine, Allows Mac Users to Create Content and Interact with Their Favorite Applications by Voice

BURLINGTON, Mass., Sep 20, 2010 (BUSINESS WIRE) -- Nuance Communications, Inc. (NUAN 14.88, -0.31, -2.04%) , a leading provider of speech solutions, today unveiled Dragon Dictate for Mac version 2.0, the newest addition to the Dragon family of speech recognition products which includes Dragon NaturallySpeaking for the PC and Dragon Mobile Apps. Dragon Dictate for Mac -- the first major desktop product for Mac OS X from the Dragon family following Nuance's acquisition of MacSpeech earlier this year -- makes it easier than ever to create documents and emails, search the web, navigate the Mac desktop, and interact with popular Mac applications -- all by voice.

Dragon Dictate for Mac, version 2.0, improves on the accuracy and performance of MacSpeech Dictate 1.5, leveraging the new Dragon 11 engine, which also powers the recently-announced Dragon NaturallySpeaking 11 for the PC. Dictate 2.0 offers a more streamlined set-up, revamped Mac user interface, and dynamic new voice commands for dictation, editing, navigation and proofreading. Dragon Dictate for Mac also "learns" better than any previous version of Dictate, responds faster to spoken commands and supports Dragon Voice Shortcuts(TM) for searching the web, email and Mac desktop by voice.

"Recognizing the important opportunity within the Mac community, we set out earlier this year to bring Dragon to the Mac, working closely with our experts from the MacSpeech team, and drawing on our history and proven success with Dragon," said Peter Mahoney, senior vice president and general manager for Dragon at Nuance. "We've maintained the elements of Dictate that are most important to our Mac customers, such as the native Mac interface, and integrated many features of Dragon NaturallySpeaking 11 to bring improved accuracy as well as smarter command and control capabilities to this discerning audience of new Dragon customers."

Dragon for PC, Mobile, and now the Mac

For years, people from all walks of life have used Dragon NaturallySpeaking on the PC to be more productive, save time and capture their ideas at the speed of thought -- at home, in the office, the courtroom, the classroom, the exam room, or even on the road. Most recently, with Nuance's Dragon Mobile Apps on the BlackBerry, Apple iPad, iPhone and iPod touch, millions of people now communicate quickly and easily on their mobile devices, simply using speech recognition. Dragon Dictate for Mac is the first Mac member of the Dragon desktop family, allowing Mac users to speak their minds to:

- Turn talk into text -- Dragon Dictate for Mac lets users simply speak to produce text. Speak thoughts and watch the words appear on screen, inside almost any Mac application -- up to three times faster than typing -- with an astounding recognition accuracy rate of up to 99 percent, right out of the box.

- Unlock creativity -- Transform ideas into text at the speed of thought with Dragon Dictate for Mac. Users can let their creativity flow from brain to voice to produce emails, blog posts, essays, and more.

- Work comfortably -- With Dragon Dictate for Mac, control the Mac in a relaxed, hands-free manner without being tethered to the keyboard. Instead of using a mouse, just speak commands to launch and control applications. Move the cursor or click anywhere on screen, simply by voice.

- Multi-task -- Dragon Dictate for Mac allows users to tell the Mac what to do, with commands like "Reply To This Message" or "Open Microsoft Word" or "Search Google for Italian restaurants" to work faster and smarter. In addition, it's easy to create custom voice commands that automate complex workflows on the Mac.

- Work your way -- Dragon Dictate for Mac can be customized with a personal vocabulary and voice commands that reflect an individual's work style.

In addition to the powerful voice commands that MacSpeech Dictate 1.5 already offers for controlling popular Mac applications such as Safari, Mail, iCal and iChat, the new Dragon Dictate for Mac 2.0 adds more ways to interact with the Mac by voice:

- Dragon Voice Shortcuts(TM) for Search -- Offers an easy way to search for information, files and content anywhere on your Mac or on the Web by using single voice commands. For example:

- "Search Google for hula dancing lessons"

- "Search Bing for wedding dress repair"

- "Search Yahoo for gondola rentals"

- "Search Mail for RSVP"

- "Search Mac for history term paper"

- New Editing Commands -- A new suite of commands in Dragon Dictate for Mac makes it easy to edit documents. With commands that are designed to simplify editing, users can select and delete text, insert new text, capitalize text, and more.

- Proofreading -- The new Proofreading commands in Dragon Dictate for Mac take advantage of the powerful Text-to-Speech capabilities built into Mac OS X. Simply dictate text, and ask Dragon Dictate for Mac to read it back.

- Surrounding Punctuation -- New commands in Dragon Dictate for Mac enable users to put punctuation around certain words or groups of words, using a simple command, such as:

- "Put Quotes Around "

- "Put Parentheses Around "

- "Put Brackets Around "

- Voice Navigation -- Dragon Dictate for Mac lets users control the Mac's cursor and mouse actions by voice, giving new options for interacting with their desktop and precise handling of mouse pointer-based tasks. New features include:

- MouseGrid: Placement of the cursor can be accomplished with MouseGrid commands

- Mouse Click: Speak a command, with optional that designate one or more keys such as Command, Option, Shift or Caps Lock

- Mouse Movement: New commands move the mouse pointer by voice

- Flexible Microphones -- Dragon Dictate for Mac users who have multiple microphones, such as a wired and wireless headset, can easily switch between microphones within the same voice profile.

Pricing, Availability & System Requirements

Dragon Dictate for Mac is available immediately starting at $199.99 through Nuance's Web site as well as its global network of reseller partners, software retailers and professional sales organizations. Existing MacSpeech Dictate customers and Dragon NaturallySpeaking customers can purchase Dragon Dictate for Mac starting at $49.99 and $99.99 respectively for a limited time. For additional information on features, editions, pricing and volume licensing programs, please visit www.nuance.com/dragon/mac.

Dragon Dictate for Mac requires an Intel-based Mac, Mac OS X 10.6 Snow Leopard or greater, 3GB of available hard drive space, 2GB of RAM recommended and an Internet connection for product registration. Dragon Dictate for Mac comes complete with a Nuance-approved USB microphone headset.

Trademark reference: Nuance, Dragon, Dragon Voice Shortcuts, Dragon Dictate, Dragon NaturallySpeaking, and the Nuance logo are registered trademarks or trademarks of Nuance Communications, Inc. or its affiliates in the United States and/or other countries. All other company names or product names referenced herein may be the property of their respective owners.

About Nuance Communications, Inc.

Nuance is a leading provider of speech, imaging and customer interaction solutions for businesses and consumers around the world. Its technologies, applications and services make the user experience more compelling by transforming the way people interact with information and how they create, share and use documents. Every day, millions of users and thousands of businesses experience Nuance's proven applications and professional services. For more information, please visit: www.nuance.com.

SOURCE: Nuance Communications, Inc.

Nuance Communications, Inc.  Erica Hill, 781-565-5218  erica.hill@nuance.com  Twitter : @DragonTweets, @macspeech  http://www.facebook.com/dragonnaturallyspeakingor  InkHouse for Nuance Communications, Inc.  Lisa Mokaba, 781-791-4570  nuance@inkhouse.net

UTOPY Recommended by Ovum’s 2010 Contact Center Speech Analytics Market Report

2010-09-23T14:36:00.000-04:00

- September 20, 2010

UTOPY, the leading provider of Voice of the Customer and Performance Optimization solutions powered by Speech Analytics, announced that it has been recognized for its leadership in recording-system-independent Speech Analytics by Ovum’s 2010 contact center Speech Analytics market report.

Titled “Decision Matrix: Selecting a Speech Analytics Vendor,” the report examines the competitive dynamics within the Speech Analytics market in order to help businesses select a vendor based on its technology strength, reputation among customers and impact on the market.

In the report, an independent technology analyst provides a comprehensive view of vendor capabilities and advises on those that businesses should explore, consider and most importantly, shortlist. The report cited the advantages provided by UTOPY’s ability to integrate with virtually any call recording system. UTOPY also gained high marks for its core technology, interface and packaged applications, and earned additional praise for its support of a wide range of languages, dialects, and accents.

“We are pleased to receive this recommendation from Ovum,” said Roy Twersky, President and CEO at UTOPY. “We believe this further underscores UTOPY’s unwavering commitment to developing innovative, analytics-driven solutions that provide contact centers with unsurpassed insight into customer-agent conversations, which can be leveraged to maximize performance and profitability.”

Find more on Utopy at www.speechanalytics.com.

Microsoft translating telephone

2010-05-08T06:59:00.001-04:00

Yet another speech translation story - now from Google

2010-02-07T15:00:00.003-05:00

Not only speech to text from cellulars but also translation. Google is aiming high but does their existing voice to text really works?

http://technology.timesonline.co.uk/tol/news/tech_and_web/personal_tech/article7017831.ece

Google leaps language barrier with translator phone

Chris Gourlay

GOOGLE is developing software for the first phone capable of translating foreign languages almost instantly — like the Babel Fish in The Hitchhiker’s Guide to the Galaxy.

By building on existing technologies in voice recognition and automatic translation, Google hopes to have a basic system ready within a couple of years. If it works, it could eventually transform communication among speakers of the world’s 6,000-plus languages.

The company has already created an automatic system for translating text on computers, which is being honed by scanning millions of multi-lingual websites and documents. So far it covers 52 languages, adding Haitian Creole last week.

Google also has a voice recognition system that enables phone users to conduct web searches by speaking commands into their phones rather than typing them in.

Now it is working on combining the two technologies to produce software capable of understanding a caller’s voice and translating it into a synthetic equivalent in a foreign language. Like a professional human interpreter, the phone would analyse “packages” of speech, listening to the speaker until it understands the full meaning of words and phrases, before attempting translation.

“We think speech-to-speech translation should be possible and work reasonably well in a few years’ time,” said Franz Och, Google’s head of translation services.

“Clearly, for it to work smoothly, you need a combination of high-accuracy machine translation and high-accuracy voice recognition, and that’s what we’re working on.

“If you look at the progress in machine translation and corresponding advances in voice recognition, there has been huge progress recently.”

Although automatic text translators are now reasonably effective, voice recognition has proved more challenging.

“Everyone has a different voice, accent and pitch,” said Och. “But recognition should be effective with mobile phones because by nature they are personal to you. The phone should get a feel for your voice from past voice search queries, for example.”

The translation software is likely to become more accurate the more it is used. And while some translation systems use crude rules based on the grammar of languages, Google is exploiting its vast database of websites and translated documents to improve the accuracy of its system.

“The more data we input, the better the quality,” said Och. There is no shortage of help. “There are a lot of language enthusiasts out there,” he said.

However, some experts believe the hurdles to live translation remain high. David Crystal, honorary professor of linguistics at Bangor University, said: “The problem with speech recognition is the variability in accents. No system at the moment can handle that properly.

“Maybe Google will be able to get there faster than everyone else, but I think it’s unlikely we’ll have a speech device in the next few years that could handle high-speed Glaswegian slang.

“The future, though, looks very interesting. If you have a Babel Fish, the need to learn foreign languages is removed.”

In the Hitchhiker’s Guide to the Galaxy, the small, yellow Babel Fish was capable of translating any language when placed in the ear. It sparked a bloody war because everyone became able to understand what other people were saying.

Nuance and Lawsuits - again

2009-09-20T02:44:00.002-04:00

In addition the the IBM engine which has strong patent behind it, Vlingo is leveraging new relations with AT&T as an investor and as a speech engine (Watson) provider in prep for the Nuance lawsuit. So now the IBM engine is licensed to Vlingo via Nuance (and this is why theuy are suing them). Moreover, Vlingo is not using this engine anymore. It seems like lawyers tricks rather than technology.

AT&T Backs Vlingo as Nuance Lawsuit Looms

AT&T has taken a minority stake in Vlingo in a move that could have major repercussions for Nuance’s patent infringement suit against the voice navigation startup. As part of the deal, Vlingo will integrate its offerings with AT&T’s Watson, a core speech recognition technology that serves as a foundation for voice-activated products. Vlingo will all but abandon the IBM-developed technology that it had been using — and which is at the heart of Nuance’s lawsuit.

“Our goal is to move everything to AT&T,” Vlingo CEO Dave Grannan told me this morning. “If Nuance decides to proceed, they’ll essentially be suing us for violating patents — and this is the crazy thing — and the alleged violation occurs in the IBM engine Nuance licensed to us and, by the way, we don’t use anymore.”

Nuance executives were not immediately available for comment.

Grannan said the Watson engine is “superior” to the IBM-developed technology and will help Vlingo build better voice navigation offerings. AT&T and Vlingo will begin rolling out new products later this year for AT&T customers and plan to market the joint solution to other industry players, including device manufacturers and other carriers.

The cutthroat nature of the speech recognition space underscores the increasing attention it’s attracting from investors, as voice is positioned as a superior navigation tool to device keypads and touchscreens -– especially for users behind the wheel. A Boston-area outfit, Vlingo began to gain traction in early 2008 when Yahoo tapped it to add a speech recognition component to its oneSearch offering. The agreement –- which followed Vlingo’s $6.5 million Series A round in 2007 -– saw Yahoo lead a second round of funding that brought in $20 million.

But Vlingo isn’t the only startup getting funded; the space has attracted hundreds of millions of dollars, and competition is fierce. Microsoft Corp. joined the field two years ago with its $800 million acquisition of Tellme, whose technology it’s using to incorporate speech into its upcoming Windows Mobile 6.5. Google has invested heavily as well, and is deploying voice navigation with its Android platform. As for the voice recognition companies themselves, outside of Vlingo, smaller players such as V-Enable and Promptu are also vying for attention. Meanwhile Nuance, the dominant pure play on the field, has spent $1 billion or so in acquisitions.

- By Colin Gibbs | Gigaom

Nuance acquires Jott (without suing them first :-)

2009-07-14T15:01:00.002-04:00

Aiming to improve at the human based transcription, Nuance just acquired Jott. It is not the technology, so why? Probably minimal price for Jott assets (not disclosed) and some methodology and interfaces for some external applications such as salesforce.com.
If you know more, share with us this info.

Nuance Acquires Jott, Expands Mobile Portfolio

Innovative Jott Service to Deliver Powerful New Voice-to-Text Capabilities to Mobile Operators and En

BURLINGTON, Mass. & SEATTLE--(BUSINESS WIRE)--Nuance Communications, Inc. (NASDAQ: NUAN - News) today announced it has expanded its Mobile Division voice services portfolio with the acquisition of Jott. Jott is the innovator behind the popular Jott Assistant, the simple and easy-to-use service that enables users to create notes, set reminders and appointments, send email and text messages, and post to their favorite web services – all by voice, from any device.

“Jott’s voice-to-text offerings have experienced a groundswell of adoption and positive industry recognition since the company’s inception, and we’re thrilled about the opportunity to expand our market reach and our voice services portfolio,” said Michael Thompson, senior vice president and general manager, Nuance Mobile. “Together we will deliver a range of new services to our mobile operator and enterprise customers.”

The combined Nuance and Jott teams will focus on several key voice-to-text initiatives:

The innovative Jott Assistant service has been adopted by hundreds of thousands of users, providing vast insight into the demands of today’s mobile users. To further extend the power of Jott across the mobile mass market, Nuance plans to package and offer Jott Assistant to mobile operators as part of its voice services portfolio, including Nuance Voicemail-to-Text.
By combining its easy-to-use voice services with email, text messaging and a variety of web services, Jott’s service has advanced mobile productivity in the enterprise market. Nuance, together with its Enterprise Unified Communications partners, will offer a secure, highly scalable and differentiated Enterprise package including Nuance Voicemail-to-Text, Messaging, and Collaboration.
As used in Jott for Salesforce, Jott provides open APIs that allow for voice integration with third party CRM providers and other critical enterprise applications that require mobile access. Nuance will continue to mainstream and expand the CRM partner program through its existing CRM partnerships, enabling enterprise application providers to better meet the needs of the evolving professional mobile market.

“We’ve seen dramatically increased demand for our mobile voice solutions, because they offer real business value, are easy to deploy, and are a delight to use,” said John Pollard, co-founder, Jott. “Nuance has consistently delivered groundbreaking mobile applications to billions of people worldwide. Our combined expertise will bring innovative and differentiated voice services to a variety of markets with tremendous scale.”

All of Jott’s services, including Jott Assistant, Jott Voicemail and Jott for Salesforce, will remain available, and existing customers will experience no interruptions in service. For more information and to access Jott services, visit www.jott.com.

About Nuance Communications, Inc.

Nuance is a leading provider of speech and imaging solutions for businesses and consumers around the world. Its technologies, applications and services make the user experience more compelling by transforming the way people interact with information and how they create, share and use documents. Every day, millions of users and thousands of businesses experience Nuance’s proven applications and professional services. For more information, please visit: Nuance.com.

About Jott

Headquartered in Seattle, WA, Jott Networks is the world leader in mobile voice-to-text applications. Jott allows individuals and businesses to easily capture thoughts, send emails and text messages, set reminders, organize lists, and post to web services and business applications – all with their voice, using any phone. Jott also converts voicemail into email and text messages, making voicemail a more productive tool. Since being founded in 2006 by John Pollard and Shree Madhavapeddi, Jott has made world-class voice transcription accessible to anyone with a cell phone. For more information on the Jott service, visit www.Jott.com.

Google voice mail transcription quality - can you trust it?

2009-07-03T15:19:00.002-04:00

Recently David F. Gallagher wrote in the NY times about Google voice. David asked people to leave him messages and he posted the automatic transcriptions. While performing good in many cases, the results are far from accurate and in many cases one cannot understand the gist of the message.
See information at pushing the limits of googles speech recognition and messing with googles speech recognition part 2.

To some extent everybody knows it is experimental and do not really trust it. Is it useful? Probably just for fun and for people who do not want any human to be involved in their private message transcription like SpinVox, Nuance or other such vendors.

“Mainstream” Speech Analytics

2009-05-23T15:22:00.002-04:00

Recently Verint announced a new offering for the "mainstream" market. Many people do not understand the importance of this announcement.

For years we are pushing speech anlaytics to the market and the adoption cycle is pretty long and thus maybe expensive. It requires experts to learn the system and get th best out of it. Eventually there are many success stories for speech analytics. However for a technology to become widely use there is a need for additional simplicity - make sure it can be operated by laymen, work out of the box and provide benefits without much learning. This is exactly the step that Verint is taking with the new system and I bet it will overachieve any other offering in the market.

If you consider deploying a speech analytics solution, even for a small contact center - this should be your first alternative.

May 13, 2009 08:30 AM Eastern Daylight Time

Verint Witness Actionable Solutions Takes Speech Analytics “Mainstream” with New Impact 360 Speech Analytics Solution

Breakthrough Technology Enables Cost-Effective Deployment of Speech Analytics, Helping Companies React Rapidly to Changes in Customer Behavior, Reduce Expenses and Enhance the Customer Experience

New Speech Analytics “Essentials” Solution Enables Small and Medium-Sized Contact Centers to Attain Speech Analytics Benefits Previously Out of Reach

Driving Innovation 2009

Verint Witness Actionable Solutions’ 13th Annual Global User Conference

Loews Lake Las Vegas Resort, Nevada

LAS VEGAS & MELVILLE, N.Y.--(BUSINESS WIRE)--Verint^® Systems Inc. today announced the availability of its new Impact 360^® Speech Analytics solutions. Simple and cost effective to deploy, the software from Verint^® Witness Actionable Solutions^® is bringing speech analytics technology into mainstream contact center operations without costly setup overhead, lengthy consulting engagements and the need for interpretation by separate analyst staff.

The new Impact 360 Speech Analytics enables businesses to mine recorded customer interactions to surface the intelligence essential for building effective cost containment and customer service strategies. Designed to provide rapid insight into changes in customer behaviors and patterns, the solution can deliver value right out-of-the-box by helping remove guesswork from the customer service equation. Impact 360 Speech Analytics proactively identifies call drivers — along with the related product, process and service issues that often originate in areas outside the contact center, such as back-office functions — emerging trends, opportunities and competitive influences, and can then make that business intelligence available enterprise-wide.

The newly introduced Impact 360 Speech Analytics Essentials solution enables businesses with small to medium-sized contact centers to cost-effectively achieve these speech analytics benefits that were previously out of reach.

“We believe this is a technological breakthrough that has the potential to create a new wave of adoption for speech analytics, breaking down previous barriers to entry, such as set-up and configuration,” explains Nancy Treaster, senior vice president and general manager, Verint Witness Actionable Solutions. “We know that the contact center holds a wealth of valuable business intelligence, and speech analytics is an automated, powerful solution that can help companies not only get to that information, but then determine what actions to take. Impact 360 Speech Analytics Essentials allows organizations with small and medium-sized centers to analyze captured conversations and rapidly benefit from valuable insight.”

Robust, New Functionality Extends Verint Leadership in Analytics

The patent-protected Impact 360 Speech Analytics Essentials, and the Impact 360 Advanced Speech Analytics solution, leverage both phonetics and LVCSR recognition — the best combination of both speed and accuracy — adding meaning and context to every word and phrase identified in every call processed without predefinition of terms.

Key, patent-pending functionality featured in Impact 360 Speech Analytics Essentials, as well as Verint’s Impact 360 Advanced Speech Analytics solution, is driven by the company’s proprietary Complete Semantic Index™ technology that features such functionality as:

Automated Trend Analysis, Surfacing Changes in Customer Behaviors

Using hundreds of thousands of term and phrase combinations, the new Complete Semantic Index automatically identifies significant changes in customer behavior as expressed within recorded customer interactions. Such changes are proactively surfaced by the software’s Automated Trend Analysis, which identifies increases or decreases in terms and phrases used during customer/agent conversations. Delivered daily, trend reports can be tracked for up to 18 months.

Guided Search and Context Visualization

With the Complete Semantic Index, users do not need to know in advance what terms to search. Intuitive search engine-like, guided search capabilities — including contextual suggestions and search visualization functionality — help business users find relevant calls quickly to determine the underlying causes of rising call volumes, costs and customer dissatisfaction.

Analytics-Driven Unification with Workforce Optimization Suite Via Native Integrations

The Impact 360 Speech Analytics solutions, part of Verint’s patent-protected, unified Impact 360 Workforce Optimization suite, can use the content of captured customer interactions to route contacts of interest to users throughout the enterprise, such as quality supervisors, marketing managers and customer retention teams.

“We’re excited to introduce this solution, as Verint is fulfilling a critical market need in enabling businesses with small and medium-sized centers to reap the same type of intelligence that their larger counterparts have used for years — all at an attractive price point, and at a time in our economy in which cost containment, retention and the customer experience are paramount,” adds Treaster.

Specifications and Availability

Optimally sized for centers with 50 to 300 agent seats, Impact 360 Speech Analytics Essentials can operate on a single box. As businesses’ needs change and grow, the solution can be easily upgraded to Verint’s advanced speech offering designed for larger centers, scaling up to 50,000 seats.

In addition to the new Complete Semantic Index, Automated Trend Analysis and Guided Search functionality, the Impact 360 Advanced Speech Analytics solution for larger center operations includes Automated Root Cause Analysis with patent-pending TellMeWhy™ functionality. With this capability, the solution can identify potential underlying drivers of specific call types, such as customer complaints or long calls, prioritize the top five root cause groups and automatically suggest the top instigators for each call set.

The Impact 360 Advanced Speech Analytics solution also features Speech Analytics-driven Scorecards designed to help centers better manage performance by balancing cost drivers with customer satisfaction drivers. Peer-based agent comparisons factor in key performance indicators (KPIs), such as customer complaints and repeat call drivers, that are identified from speech analytics results, along with proactive alerts on defined thresholds. Other functionality includes native business integrations with Impact 360 Quality Monitoring’s Smart Inbox^™— which delivers recorded interactions directly to the desktop based on defined criteria that can include speech analytics categories — and Impact 360 Data Analytics, which analyzes call attributes to help uncover contact scenarios that can positively or negatively impact organization and/or individual KPI achievements.

About Verint Witness Actionable Solutions

Verint^® Witness Actionable Solutions^® is the leader in analytics-driven workforce optimization software and services. Its solutions are designed to help organizations capture customer intelligence, uncover business trends, discover the root cause of employee and customer behavior, and optimize the customer experience. From contact centers to remote office, branch and back-office operations, its award-winning, next-generation Impact 360^® Workforce Optimization suite is the industry’s most unified solution set — featuring quality monitoring and recording, workforce management, speech analytics, data analytics, customer feedback surveys, performance management, eLearning and coaching. Impact 360 helps improve the entire customer service delivery network, powering the right decisions to help ensure service excellence and transform organizations into customer-centric enterprises.

About Verint Systems Inc.

Verint Systems Inc. (VRNT.PK), headquartered in Melville, New York, is a leading provider of Actionable Intelligence^® solutions for an optimized enterprise and a safer world. Today, more than 10,000 organizations in over 150 countries rely on Verint solutions to perform more effectively, build competitive advantage and enhance the security of people, facilities and infrastructure. Visit us at our website www.verint.com.

This press release contains "forward-looking statements" within the meaning of the Private Securities Litigation Reform Act of 1995, including statements regarding expectations, predictions, views, opportunities, plans, strategies, beliefs, and statements of similar effect relating to Verint Systems Inc. These forward-looking statements are not guarantees of future performance and they are based on management's expectations that involve a number of risks and uncertainties, any of which could cause actual results to differ materially from those expressed in or implied by the forward-looking statements. For a detailed discussion of these risk factors, see the Company's Current Report on Form 8-K filed with the Securities and Exchange Commission on September 10, 2007, as supplemented by our Current Reports on Form 8-K filed on November 5, 2007, January 16, 2008, and April 9, 2008 and the Form NT-10Q filed on April 16, 2009. The forward-looking statements contained in this press release are made as of the date of this press release and, except as required by law, the Company assumes no obligation to update or revise them or to provide reasons why actual results may differ.

VERINT, the VERINT logo, ACTIONABLE INTELLIGENCE, POWERING ACTIONABLE INTELLIGENCE, WITNESS ACTIONABLE SOLUTIONS, STAR-GATE, RELIANT, VANTAGE, X-TRACT, NEXTIVA, ULTRA, AUDIOLOG, WITNESS, the WITNESS logo, IMPACT 360, the IMPACT 360 logo, IMPROVE EVERYTHING, EQUALITY, CONTACTSTORE, EYRETEL, BLUE PUMPKIN SOFTWARE, BLUE PUMPKIN, the BLUE PUMPKIN logo, EXAMETRIC and the EXAMETRIC logo, CLICK2STAFF, STAFFSMART, AMAE SOFTWARE and the AMAE logo are trademarks and registered trademarks of Verint Systems Inc. Other trademarks mentioned are the property of their respective owners.

Google's 'Voice Search' comes to India

2009-04-11T16:12:00.002-04:00

Nice post on siliconindia: http://www.siliconindia.com/shownews/Googles_Voice_Search_comes_to_India-nid-55075.html
I specifically liked the example to search for whether :) - must be phonetic.. Anyway given the heavy accents of the south and north and various sub languages, there is a lot of work for google india for just collecting all this data.

Google's 'Voice Search' comes to India

By siliconindia news bureau

Friday,10 April 2009, 15:09 hrs

Bangalore: Now search is just a call. Google has set path for a new era in the speech analytics with 'voice search', which it recently introduced in Hyderabad, Delhi, Mumbai and Bangalore. One just needs to speak a single word into the phone, such as 'whether' or 'hotel' and one can get the top results.

The 'voice search' uses a combination of automated voice recognition engine and operators to provide this facility. To make the service faster and better, Google is also experimenting with voice recognition technology, which will ensure 24-hour support. Currently, the automated system offers results in English, but the operator-driven system offers results in only Hindi and Telegu.

"This is in line with our mission of making information universally useful and accessible, be it at home or on the go," explains Hugo Barra, Group Product Manager, Google Mobile. Not all those who make queries, though, will get accurate results, since the project is still in its pilot stage, reported Business Standard.

Google's logic is a simple one. Mobiles outnumber personal computers (PCs) in India. Besides, just about 5-7 percent of the population has an internet connection, including those who use surf the net via their mobiles. "Voice enables India to reach non-web users in local languages even as our core strength is search," Barra adds.

In the U.S., Western Europe and Japan, the 'voice search' feature is available under the Google Mobile App for the iPhone. It is also available on the Android-based T-Mobile G1, and was introduced on the BlackBerry as a free download last month.

In India, though, Google plans to extend the technology to other cities once it is confident in the quality of its speech recognition technology "in any region of the country", since the number of languages and accents in India are very diverse and distinct from each other.

The company is currently not making any revenue on this service in India though it monetises this in the U.S., Western Europe and Japan through ads which appear when the results show up. It does not charge the user for information received or for connecting them to businesses. The local business information used by Google is the same as that on local search. Data is continuously being added, and Google is collecting feedback from the users, Barra explained.

Talking about the company's mobile strategy, Vinay Goel, Country Head of Products, Google India, said, "There has been a significant increase of mobile search users in 2009. We believe that users graduate from plain voice search to an SMS-based one and finally to internet-based search, which is our goal."

The search giant has also made Orkut (its social networking site) and Google Maps available on mobiles. Besides, it also has the Google Latitude (to help locate one's friends) feature as an opt-in download.

Google Voice should hire Spinvox for message transcription

2009-03-31T09:19:00.003-04:00

I just saw this post at: http://abrilliantblog.com/2009/03/google-voice-should-hire-spinvox-for-message-transcription/

I guess it is the laymen feedback on the google voice service and exactly what I anticipated at:
Google Voice - the new threat to the reputation of speech recognition system.

Google Voice should hire Spinvox for message transcription

March 30th, 2009

I have been using GrandCentral for years and when they announced Google Voice I was elated. I could not wait for the new features including my absolute favorites being SMS and voice mail being transcribed to text and emailed and texted to you.

Well the SMS is great but the voice transcription is dreadful. I didn't call someone back last week mistakenly thinking it was a telemarketer. It was Bena Roberts of GoMoNews fame and a very important mover and shaker in the business. This kind of transcription mistake is not acceptable. I have a suggestion for Google Voice that I really hope they listen to, OUTSOURCE TO SPINVOX. Now I don't work for SpinVox, but I've used it and on dozens of friends very high regard and reference for the SpinVox service I'm willing to give this advice.

Google don't allow Google Voice to tarnish a perfectly fantastic service because you're not willing to spend a few dollars. Go test out SpinVox and if it beats your transcription (I guarantee it will) then please switch over.

TelStrat - TelStrat’s Engage™ Suite Now Understands Speech Analytics

2009-03-31T05:22:00.002-04:00

Engage Analyze expands TelStrat's contact center product portfolio with true phonetic speech analytics intelligence

Orlando, Florida – March 30, 2009 – TelStrat, a global supplier of comprehensive contact center solutions, business call recording products, and leading-edge access network systems, today chose VoiceCon Orlando 2009 as the venue to announce Engage Analyze, the latest addition to its industry-leading contact center solution suite. Engage Analyze provides advanced speech analytics that equip organizations to transform voice calls into knowledge that can help them improve efficiency, increase compliance, and gain the competitive advantage.

Engage Analyze indexes and audio mines words and phrases buried in calls using a patented Phonetic Audio Search and Recognition Engine. Unlike older, less efficient speech-to-text approaches, phonetic speech search is not dependent on finite dictionary and grammar models which require constant maintenance. This makes it easy to accurately search for new competitors, product names, slang, and other dynamically changing terms.

Phonetic search technology also makes Engage Analyze fast – much faster than speech-to-text systems. Pre-processing or indexing of content is typically 60-80 times faster than real time, more than an order of magnitude faster than Large Vocabulary Conversational Speech Recognition (LVCSR) speech-to-text systems. Subsequent searches for words or phrases are incredibly quick, averaging over 30,000 times faster than real time and reaching rates up to 80,000 times faster.

Speech-to-text systems rely on limited, statistical sampling of calls, typically 3-5% of call volume, due to cost and complexity. The technology in Engage Analyze makes it possible to audio mine up to 100% of calls, in real time if desired. The product does all this without the massive computing power necessary for comparable LVCSR systems. With Engage Analyze, contact centers can now accurately analyze and recognize trends over thousands of hours of customer calls.

"With Engage Analyze we're bringing our customers advanced technology that provides them with a powerful tool to enhance business and customer intelligence, "said TelStrat President Kevin Smith. "The search speed and recognition capabilities make this product a market leader, and we've made it affordable for organizations of virtually any size."

Engage Analyze is the newest component of TelStrat's Engage Contact Center Suite. Engage Suite blends full-featured voice and screen recording; intuitive agent performance evaluation, tracking and coaching; powerful agent scripting and call automation; sophisticated workforce forecasting and scheduling; and now, advanced speech analytics. It addresses each major aspect of contact center operations. Designed to benefit any 'center of contact', Engage Suite is ideal whether used by a large telemarketing firm or a small company's support staff.

http://www.telstrat.com/content/view/399/350/

Salesforce.com speech recognition integration by Jott

2009-03-30T14:06:00.002-04:00

Jott recently announced a speech interface to salesforce.com. By leveraging their speech to text services, they came with an offering to enterprise users. It is another example how a speech to text API (human based on automatic) can be easily integrated into other saas applications. See also SpinVox Open API. A key around this service will be what happen when the data is inaccurate due to transcription error (weather human or machine error). What is the feedback that users will recieve from the system and what is the fix process for such error. I guess the Jott people can highlight some of that but so can similar service providers like SpinVox, Nuance, Google etc.

Jott Networks Introduces Jott for Salesforce, Makes Mobile CRM Input Insanely Simple With Voice-to-text

SEATTLE, March 19 /PRNewswire/ -- Jott Networks today announced the addition of Jott for Salesforce to its expanding line of mobile productivity services. The new service uses Jott's high-quality voice-to-text technology, and allows sales professionals to make a simple call on any phone to directly input opportunity updates, take quick notes, and set reminders and appointments - all hands-free. Jott is offering a one-month free trial of Jott for Salesforce and it comes with a free subscription to Jott Assistant Pro, Jott's widely acclaimed mobile productivity tool.

Jott CEO and co-founder John Pollard said, "There are already over a thousand businesses that use Jott's other services to get more done on the go. These same businesses wanted us to provide integration with more critical business applications and Jott for Salesforce is the first in that line." He added, "Sales professionals can now use our best-in-class voice-to-text technology to avoid the hassle of cramped and clumsy mobile interfaces and frustratingly slow connection speeds. Sales teams spend more time selling and less time typing reports, and sales managers see greater adoption of Salesforce and receive better, fresher forecast data." Jott for Salesforce includes the following features:

Features for Sales Professionals

Update opportunities and accounts - Use your voice to quickly update entire opportunities with a simple flow or individual forecast fields with shortcuts. Data ends up in specific accounts with no cutting, pasting or forwarding required.
Take quick notes - While they are still fresh, speak quick notes about accounts and opportunities and add tasks to your Salesforce dashboard.
Schedule appointments and set reminders - Use your voice to book a meeting on your Salesforce.com or Outlook calendar, and set reminders so you never forget.
Get confirmation of everything - Every update you leave comes with a confirmation email/text message so you know for certain that data was entered into your accounts.

Features for Managers

Set up in minutes - Jott for Salesforce is incredibly easy to set up. There are no desktop or phone downloads, and it requires no changes to your existing Salesforce set-up.
Scale easily - Jott for Salesforce was built for scale. With nothing to download or maintain, and no new equipment to buy, it easily accommodates individuals or organization-wide rollouts.
No training necessary - While training is available to help teams get the most out of Jott for Salesforce, only a few simple commands are needed to get started.

Pricing and Availability

Jott for Salesforce is available today from the App Exchange on Salesforce.com and from the Jott.com web site. It takes just a few minutes to set up, and is compatible with all carriers and all mobile phones in the US and Canada. Jott for Salesforce's pricing is straightforward and affordable at $25 per user per month. For that fee, users can send unlimited updates into Salesforce with no need to worry about overage charges.

For more information on Jott Salesforce and other Jott services, please visit www.Jott.com.

Visual Speech Recognition: Lip Segmentation and Mapping

2009-03-29T03:57:00.003-04:00

I just saw this free ebook which maybe of interest for the speech analytics community. See the link below.

Enjoy.

Description: The unique research area of audio-visual speech recognition has attracted much interest in recent years as visual information about lip dynamics has been shown to improve the performance of automatic speech recognition systems, especially in noisy environments.

Visual Speech Recognition: Lip Segmentation and Mapping presents an up-to-date account of research done in the areas of lip segmentation, visual speech recognition, and speaker identification and verification. A useful reference for researchers working in this field, this book contains the latest research results from renowned experts with in-depth discussion on topics such as visual speaker authentication, lip modeling, and systematic evaluation of lip features.

http://www.dbebooks.biz/engine/redirect.php?url=http://paid4share.net/file/13767/9781605661865-1605661864-rar.html

SpinVox Open API

2009-03-20T15:40:00.005-04:00

Congrats to SpinVox for this important move. Opening your system to others can drive speech applications faster leveraging many more developers and creative minds. Whether it is human transcription or machine transcription, this move separates the speech processing part from the application part and push for SaaS speech enabled applications.

March 18, 2009 07:30 AM Eastern Daylight Time

SpinVox to Demonstrate Open API Applications at CTIA Wireless 2009

Pre-Registrations For SpinVox Create Fuel Co-Development Program and Confirm Demand for Voice Conversion Services from Web-Based Technology Developers Wanting to Build Speech 2.0 Applications

CTIA Wireless 2009

LONDON & NEW YORK--(BUSINESS WIRE)--SpinVox, the global leader in voice to content messaging, will showcase three brand new Speech 2.0 applications at CTIA Wireless 2009, to be held April 1-3 in Las Vegas. The applications have been developed in less than a month to demonstrate the power of SpinVox Create, an open API (Application Programming Interface) to the SpinVox Voice Message Conversion System™ (VMCS), the world’s largest commercial speech platform.

SpinVox Create was announced at Mobile World Congress, Barcelona in February 2009 and developers were invited to pre-register their interest in SpinVox Create in advance of its launch via a web registration page - www.spinvox.com/developer

SpinVox Create will be launched as a key part of a two-stage corporate API strategy that will also be announced at CTIA and rolled out by SpinVox in the first half of 2009.

Nearly 100 developers have already registered interest in SpinVox Create and, of these, 20 have been selected by SpinVox to be part of the co-development program. Those selected include business efficiency, personal productivity, games and social networking applications.

SpinVox Create is a simple, straightforward API that leverages SpinVox’s commercial speech platform – which is growing quickly with more than 30 million users - to enable any developer with Web access to quickly build commercial speech applications. It also enables SpinVox to collaborate with third parties to expand the Speech 2.0 market and foster further innovations in voice that complement SpinVox’s existing platform development services for Enterprise application partners and Carrier networks.

“We’ve been impressed by both the quality and quantity of responses to our pre-registration announcement,” says SpinVox co-founder and CEO Christina Domecq. “We are clearly seeing an increased demand for voice conversion services from technology developers who recognize that a speech interface enables the most natural form of communication, and who want to build Speech 2.0 applications with best-in-class open products.”

Demonstration of Voice innovation on Apple, Nokia, and Windows Mobile platforms

Three applications will be demonstrated at CTIA Wireless 2009. These are based on Apple iPhone, Nokia Series 60, and Microsoft Windows Mobile platforms.

`Travel Blog`, a Windows Mobile 6.0 Application developed by Singapore-based Global Idealogy Corporation lets you tag and post your photographs using just your voice . You can select photographs through the application, speak a message, attach the converted text to the photographs, post it on blog, social networking websites or send it as email or MMS.

`Speak-a-Text`, a Nokia Series 60 Application developed by UK-based Symbian Platinum Partner, Savage Minds, incorporates the ability to speak a text which is converted to text and placed into the menu structure of the phone software.

`Memo`, an iPhone Application, developed by UK-based SpinVox allows iPhone users to speak a memo through the iPhone application and after conversion into text by the SpinVox VMCS the memo resides on the iPhone for instant access whenever needed.

Drive the next upturn

SpinVox has already received pre-registrations for SpinVox Create across the globe and looking ahead expects rapid uptake of the API particularly in Silicon Valley where SpinVox Web 2.0 services such as SpinVox Blog and SpinVox Social Networks have been increasingly popular.

Adds Domecq, “SpinVox has created a new category - carrier-grade voice conversion - and now is helping talented developers take advantage of the next growth opportunity in speech. The potential for innovation between carriers and the web is enormous – along with our own innovations we're now delivering a platform for creation of market changing applications and supporting their transformation to carrier-grade services. Speech 2.0 applications will be one of a cluster of innovations that will drive the next upturn as people are increasingly enabled to re-discover the power of their voice.”

About SpinVox

SpinVox® is the world's largest privately-held speech technology company, providing the only voice to text messaging services which are used daily by millions of people and whose user base has grown over twenty-fold in the last 12 months.

Through significant innovations in voice and network technologies which are protected by over 40 patents worldwide, SpinVox has converged the two most natural forms of communication - voice and text - to create the fastest-growing form of messaging: Voice-to-Content™.

SpinVox services are available directly on www.spinvox.com and through leading carriers and through new media, Unified Communications and other service providers globally.

Implemented as a carrier-class cloud service, SpinVox is proven to be able to easily create value from everyday user behavior using voice and deliver rapid and easy implementation of low input, sustained high reward services.

At the heart of SpinVox is its ground-breaking Voice Message Conversion System™ (VMCS), which works by combining state-of-the-art speech technologies with a live-learning language process. Developed by the Cambridge, UK- based SpinVox Advanced Speech Group; VMCS now serves users across five continents in English, French, Spanish, German, Portuguese and Italian.

SpinVox is now live with Alltel, Cincinnati Bell, Sasktel, Rogers Wireless, Telus, Telstra, Vodacom South Africa, Vodafone Spain, Movistar Chile, Skype and Livejournal.

SpinVox response for Google voice - where is the Nuance response?

2009-03-18T07:11:00.004-04:00

As per the recent google voice voicemail transcription announcement, SpinVox is reponding -
In a recent post by Rich Tehrani from TMC, he quote a response from SpinVox about Google voice:

Google is entering a marketplace that continues to be led by SpinVox, the world's largest privately-held speech technology company. We're excited by the launch of Google Voice because it will demonstrate the benefits of speech-to-text conversion and validate its deployment as a network service to an increased audience. We have already launched carrier-grade services with 13 operators - including recently with Skype - on five continents and SpinVox is in use by in excess of 30 million users. SpinVox's 97 percent accuracy in conversion is now the benchmark around the world. - Christina Domecq, co-founder and CEO of SpinVox

And this 97% are human results. I am not sure that Google will post any response but we need to wait for usability feedbacks from users.

I further wonder about Nuance's response to Google Voice..?

Google Voice - the new threat to the reputation of speech recognition system

2009-03-15T13:03:00.004-04:00

Google posted last week the new enhancements for GrandCentral and actually its evolution to Google Voice. It is in general an application to better manage your voice communications.

The new application improves the way you use your phone. You can get transcripts of your voicemail (see the video below) and archive and search all of the SMS text messages you send and receive. You can also use the service to make low-priced international calls and easily access Goog-411 directory assistance. It is an addition to the GrandCentral standard features
including a single number to ring your home, work, and mobile phones, a central voicemail inbox that you could access on the web, and the ability to screen calls by listening in live as callers leave a voicemail. You'll find these features, and more, in the Google Voice preview. Check out the features page for videos and more information on how these features work. It is great to have visual voicemail and this will enahance further the iPhone and simialr smartphones.

Google is taking its voice recognition into prime time and into a very delicate position as it exposes all the voice transcripts load and clear with no option for human correction. I can only guess what will happen to voicemails in foreign language, heavy accent etc. We've all seen the mistakes in the Google speech recognition system used on for mining presidential campaign in the US and trust me, most of us do not speak as clear as Obama.

So as a user, there are several options for getting a transcription to your voice mail. SpinVox, Nuance and all other small players (SimulScribe, Jott etc.) who rely on human review and Google who is claiming that there maybe errors but its the user decision whether to rely on the provided transcripts.

I anticipate that the frustration from the quality of Google Voice transcription is going to be a source for bad attitude towards speech recognition technology (see the Dilbert cartoon I put in this blog in the past). While there were mechanisms to "hide" the embracing mistakes in other systems, here all the transcript will be visible and may relate to mission critical information.

My recommendation to Google is to open an interface for providing a manual transcripts. Either this can be connected to the SpinVox API (announced recently) or alternatively open an interface that allows sending a proposed transcript + Audio and receiving back a corrected transcript. This can open a new market for people who will be willing to send their voice communication to remote secretaries (probably in India) who will transcribe the audio and return it to Google Voice. This can also be a perfect fit to Amazon’s Mechanical Turk service where you can get people to perform simple tasks. If you want further info, contact me directly about the way it should be constructed including adaptive language id etc.

Nuance buys speech recognition business from Philips

2008-10-01T12:34:00.003-04:00

Another step in speech recognition consolidation: Nuance Communications buys Philips speech recognition unit

More than five years after acquiring Philips Speech Processing Business Units, Nuance completes acquiring the Philips speech recognition business. While the older acquisition was for telephony and voice control, the recent acquisition is mainly around the healthcare speech dictation market. It seems more of a business driven acquisition (the EU market) rather than technology. Will the future of Speech Magic be the same as Speech Pearl? Nuance was very aggressive and I assume efficient with its acquisitions making sure that no multiple engines will coexist for the long term.

Nuance Communications buys speech recognition unit

Wednesday October 1, 8:40 am ET
Nuance Communications pays $96.1 million for speech recognition unit in Europe

BURLINGTON, Mass. (AP) -- Nuance Communications Inc., which makes speech recognition software, said Wednesday it bought Royal Philips Electronics' speech recognition unit for about 66 million euros, or US$96.1 million.

Nuance bought the unit in order to expand its presence in the European health care market.

Under the deal, Netherlands-based Royal Philips received a payment of 21.7 million euros on Sept. 26 and will receive 44.3 million euros in a deferred payment on Sept. 21, 2009. Nuance said the deal will add between $36 million and $39 million in revenue in 2009, and now expects revenue to reach $410 million. The buyout will add up to 1-cent per share in profit.

The addition of the speech recognition unit, Nuance said, enhances the company's ability to provide documentation and communication services to health care organizations throughout Europe. It said about $2 billion is spent annually in Europe for health care companies to manually process clinical information.

ScanSoft Completes Acquisition of Philips Speech Processing Business Units

Leading Telephony and Voice Control Technologies and Applications Expand ScanSoft's Presence in Telephony, Automotive and Embedded Markets

PEABODY, Mass., 3rd February, 2003 - ScanSoft, Inc. (Nasdaq: SSFT), a leading provider of imaging, speech and language solutions, today announced that is has closed the acquisition of the Speech Processing Telephony and Voice Control business units and related intellectual property from Royal Philips Electronics (NYSE: PHG, AEX: PHI).

"ScanSoft's acquisition of the Telephony and Voice Control business units from Philips Speech Processing further enhances our market share in key markets and gives the company additional competitive momentum in our target markets," said Paul Ricci, ScanSoft's chairman and CEO. "With a broader set of technologies and an enhanced distribution channel, ScanSoft is well positioned to capitalise on growth opportunities in the telephony, automotive and embedded markets. In addition, we expect the relationship we have forged with Philips to contribute to the development of new speech technologies in the future."

The businesses acquired by ScanSoft include:

Telephony - The Philips Speech Processing Telephony business allows enterprise customers, telephony vendors and carriers to speech-enable a range of services, including directory assistance, interactive voice response and voice portal applications. Philips automatic speech recognition (ASR) engine, SpeechPearl®, supports more than 40 languages and can process a vocabulary of more than one million words, making it the solution of choice for telephony applications that target global and broad regional markets. Philips has also leveraged its expertise in telephony ASR to develop VoiceRequest™, an enterprise auto-attendant solution, and automated directory assistance implementations that have been deployed by Telia in Sweden, the Japan Multimedia Service and Telefónica de Argentina, among others.

Voice Control - The Philips Speech Processing Voice Control business is addressing growing consumer demand for speech-enabled automotive, mobile and consumer electronics products. Philips' SpeechWave™ and VoCon® small-footprint speech recognition engines are ideal for embedded applications including voice-control of climate and entertainment features within cars. These solutions are also used within navigation systems and to enable automated voice dialing within mobile phones, including those from Philips.

The consideration for the transaction comprises a $27.5 million three-year, zero-interest convertible subordinated debenture, convertible at any time into common shares of ScanSoft at $6.00 per share; 4.1 million euros in cash, of which 3.1 million euros were paid at closing and 1 million euros are payable by December 31, 2003; and a 5 million euro 5% interest note due December 31, 2003. The cash payable is subject to adjustment in accordance with the provisions of the agreement as amended.

iPhone speech recognition - status

2008-09-02T15:35:00.001-04:00

The iPhone mania is pushing many vendors to offer speech recognition on this platform. As there are many offerings, I enclose a summary to ensure a simple presentation of the current status. I am not certain it covers all iPhone speech offering and will be glad to receive comments about additional speech recognition solutions for the iPhone.

There are many posts on the net about speech recognition around iPhone, some for command and control and some for perfroming free speech web search. Many people are disappointed that there is no speech recognition for iPhone while other are discussing working or semi-working applications and few names are mentioned:

AT&T
Nuance
VoiceSignal
VoiceDialer
VOICE DIAL
VoiceThis
Fonix

AT&T exposed recently a research project - Watson Speech Mashups Architecture - a new software framework that casts AT&T’s WATSON speech recognition as a web service to economically bring speech processing technologies to the larger web and mobile developer community. This new capability provides network-hosted speech technologies for multimedia devices with broadband access (iPhone, BlackBerry®, IPTV set-top box, SmartPhones, etc.) without the need to install, configure, and manage speech recognition software and equipment. This enables easy and rapid development of new speech and multimodal mobile services as well as new web-based services. The software implementation is based on well-established web programming models, such as SOA, REST, AJAX, JavaScript and JSON.

AT&T provides a video of the YellowPages.com application with speech recognition on an iPhone.

Nuance & VoiceSignal are promoting separate solutions or maybe the same one? VoiceSignal is part of Nuance but still exposed its own iPhone speech recognition solution. I am confused and I bet many others inside Nuance are confused.

I wrote in the past about the Nuance iPhone offering. What I managed to understand from the various announcements is that Nuance named its solution OVS for open voice search (in some cases it is referred to as open vsearch). It is also known as the Mobile Solution Suite. Surprisingly on the VoiceSignal website, there is a demo video of vSearch which is a speech recognition based search application for iPhone. The application logo displayed on the iPhone in this video is the VoiceSignal logo (unlike the logo on the Nuance vsearch demo which is of course the Nuance logo).
If you are still not confused, take a look at the Nuance announcement from June 10th and compare to the VoiceSignal announcement from August 24th:

Nuance Unveils Voice Search Prototype On iPhone

APPLE WWDC, SAN FRANCISCO. June 10, 2008 — Nuance Communications, Inc. (NASDAQ: NUAN), a leading provider of speech solutions, today unveiled a ground-breaking prototype for voice search capabilities shown on the Apple iPhone (NASDAQ: AAPL).

The newly designed application introduces a new, more compelling consumer and search experience. Through Nuance speech recognition servers, mobile consumers — with no training required — can simply speak requests into their phone like “Find the Apple store in Boston, Massachusetts,” “Score of the Boston Celtics game,” or “Play Hannah Montana Best of Both Worlds” to quickly and accurately search the mobile web or in the future dictate an IM, SMS or e-mail message. The prototype, code-named “OVS” for open voice search, will allow mobile operators to offer simple ‘say anything’ search capabilities and is search engine agnostic, able to link to any search engine of an operator’s choosing. A video demonstration of the new application can be found at www.nuance.com/mobilesuite.

VoiceSignal Voice Enables iPhone in Proof of Concept Development

WOBURN, Mass., August 24, 2007– VoiceSignal Technologies, Inc., a leading supplier of speech recognition solutions, today announced that VoiceSignal engineers have ported several of VoiceSignal’s applications to the iPhone. These initial proof-of-concept applications include VSearch (mobile local search by voice) and VTunes (voice enabled music player).

The video demonstrations can be found either on the VoiceSignal website (www.voicesignal.com) or on the following YouTube links:

VTunes: http://www.youtube.com/watch?v=zne4rwCCmAc
VSearch: http://youtube.com/watch?v=ayrCCw5xWug

I am surprised by the Nuance marketing performance on this issue. I hope that someone from Nuance will wake up to clear this issue and maybe add some comments to enable us understand their offering.

SpeechCloud's VoiceDialer (free) was the first iPhone application to try to offer speech dialing on the iPhone. VoiceDialer takes advantage of the iPhone's always-on internet connection to record your voice and send it to SpeechCloud's servers to perform the actual recognition. Similar to the AT&T and Nuance approach. Once recognized, the application pulls up the contact's name and allows you to select which number to dial. Some of the criticism of the application is that it requires too much manual interaction (tapping on buttons) to actually dial a number, and slow response time due to the transferring of data across wireless networks.

VoiceDial ( by Makayama) ($ 14.99 on apple store) avoids actual speech recognition and instead perform audio comparison. VoiceDial requires you to actually record your own voice for each contact which can then later be used to match your voice command. If you are willing to pay the $15 and willing to record yourself saying your contacts, MercuryNews claims the product "works as advertised" and "had no problems recognizing the contact I wanted to call, even when it was similar to other names I'd recorded."

HRL Technologies' VoiceThis Dialer , ( $9.99) is an application that actually tries to perform speech recognition within the iPhone itself. No wireless connection required. Instead, the application runs within the iPhone. VoiceThis Dialer promises to offer completely hands free activity with the ability to dial contacts and even quit the application with your voice.

Fonix Speech is currently developing iSpeak, which includes a run-time engine that sits on the phone allowing users to interact with the personal contents of their Apple iPhone™. Unlike other voice applets that enable voice search of the Internet by sending commands over the airwaves, this client-side application gives users the power of voice interaction with their personal content and eliminates network latency. Fonix iSpeak™ connects the user by just saying the phone number or by saying the name of a person in the contacts database. Additionally, users will be able to navigate their music libraries and launch a song or playlist simply by saying the name of the artist, song, or playlist.

To summarize, we are facing a proliferation of speech recognition applications on the iPhone.
A Key for the evolution of speech recognition on the iPhone is the 3G capability (which provides a fast channel to server side conmputing) and the platform openness - both released recently. As this two criteria are fulfilled, we should expect a quick growth in speech recognition applications availability for iPhone.

IBM is behind Vlingo's technology - will Nuance sue IBM?

2008-08-19T14:09:00.000-04:00

Recently Nuance decided to play aggressively against Vlingo. While filing a lawsuit against Vlingo seems reasonable for Nuance who has a long history for using the lawsuit weapon against small companies (usually pre acquisition attempts). However the recent Business Week article - IBM's Speech Recognition, expose the fact that Vlingo is using the IBM technology as the basis for their solution.

I wonder if Nuance will continue the legal actions given this information. IBM speech recognition patents is one of the broadest in the industry and in general nowone should mess with IBM about patents.

Google Video Search via Speech Recognition

2008-07-16T04:59:00.000-04:00

Finally a hint on the expected Google move to the speech recognition arena.

Google announced at the Official Google Blog, the availability of a new video search capability based on speech recognition.

It was release as a gadget you can embed on your iGoogle homepage and is a good preview of things to come.
The gadget only searches videos uploaded to YouTube's Politicians channels, which include videos from Senator Obama's and Senator McCain's campaigns, as well as those from dozens of other candidates and politicians. It usually takes less than a few hours for a video to appear in the index after it has been published on YouTube.

So apart from congratulations to the google team who are exposed to the public for the first time, how are they compared to other speech recognition engines aimed for broadcast quality? The google team refer to their precision: "While some of the transcript snippets you see may not be 100% accurate, we hope that you'll find the product useful for most purposes." While I do not understand what are the purposes for just searching within the YouTube political channel, people should be aware of much more mature solutions developed in the past years. From the pioneering work of BBN and IBM to the existing online solutions like everyzing, tveyes, blinx, snipp.tv by NSC and more. Based on the perceived quality, the google team has a long way to go in order to get to the first league and to be able to analyze data which is not at broadcast quality. The good news as users is that the YouTube data is easier to process relative to telephony calls speech recognition performed widely today at contact centers by companies like Verint, Nice, Autonomy, Utopy, Nexidia, CallMiner and other players.

Speech Analytics

Speech Recognition Leaps Forward - Is it a revolution?

The Holy Grail of Speech Recognition

Renewed Interest in Neural Networks

Benchmarking on a Neural Network

Bringing the Future Closer

iOS Speech Recognition Settings Confirm Nuance-Apple Partnership

Again: Nuance Slaps Vlingo With Another Patent Lawsuit Over Voice Recognition Technology

The Search for a Clearer Voice - How Google's Voice Search is getting so good.

The Search for a Clearer Voice

New speech analysics whitepaper

Nuance Launches Dragon Dictate for Mac -- Simply Smarter Speech Recognition

Dragon Speech Application for Mac OS X Taps New Dragon 11 Engine, Allows Mac Users to Create Content and Interact with Their Favorite Applications by Voice

UTOPY Recommended by Ovum’s 2010 Contact Center Speech Analytics Market Report

UTOPY, the leading provider of Voice of the Customer and Performance Optimization solutions powered by Speech Analytics, announced that it has been recognized for its leadership in recording-system-independent Speech Analytics by Ovum’s 2010 contact center Speech Analytics market report.

Microsoft translating telephone

Yet another speech translation story - now from Google

http://technology.timesonline.co.uk/tol/news/tech_and_web/personal_tech/article7017831.ece

Google leaps language barrier with translator phone

Related Links

Nuance and Lawsuits - again

AT&T Backs Vlingo as Nuance Lawsuit Looms

Nuance acquires Jott (without suing them first :-)

Nuance Acquires Jott, Expands Mobile Portfolio

Innovative Jott Service to Deliver Powerful New Voice-to-Text Capabilities to Mobile Operators and En

Google voice mail transcription quality - can you trust it?

“Mainstream” Speech Analytics

Verint Witness Actionable Solutions Takes Speech Analytics “Mainstream” with New Impact 360 Speech Analytics Solution

Google's 'Voice Search' comes to India

Google Voice should hire Spinvox for message transcription

Google Voice should hire Spinvox for message transcription

March 30th, 2009

TelStrat - TelStrat’s Engage™ Suite Now Understands Speech Analytics

Salesforce.com speech recognition integration by Jott

Jott Networks Introduces Jott for Salesforce, Makes Mobile CRM Input Insanely Simple With Voice-to-text

Visual Speech Recognition: Lip Segmentation and Mapping

SpinVox Open API

SpinVox to Demonstrate Open API Applications at CTIA Wireless 2009

SpinVox response for Google voice - where is the Nuance response?

Google Voice - the new threat to the reputation of speech recognition system

Nuance buys speech recognition business from Philips

iPhone speech recognition - status

IBM is behind Vlingo's technology - will Nuance sue IBM?

Google Video Search via Speech Recognition