Tuesday, July 31, 2012

Suggestions for an Apple Shopping List

Interesting shopping list candidates including Nuance being a viable option......

via http://www.speechtechnologygroup.com/speech-blog - via dealbook.nytimes.com Interesting shopping list candidates including Nuance being a viable option...... ...

Monday, July 30, 2012

Microsoft’s ‘Audible,’ Apple’s Siri Are the Future of UIs: Analysts

Microsoft's and Apple's personal voice assistants …

The next version of the Windows Phone operating system will add voice command technology similar to "Siri" on the Apple iPhone 4S, both of which signal the growing sophistication of voice-recognition technology, according to industry observers.

The Microsoft technology was demonstrated for software developers attending the Windows Phone Summit June 20 in San Francisco where Microsoft unveiled the Windows 8 Platform Preview, a major update of the Windows Phone 7 operating system rolled out in 2010.

It will not just open applications, but it allows a user to execute voice commands within an application, as Kevin Gallo, developer platform general manager in Microsoft's Windows Phone Division, demonstrated at the event.

Gallo kept referring to the system as "Audible," but that was just for demo purposes; the final Microsoft technology will go by another yet-to-be-chosen name, a Microsoft spokesperson explained.

Audible is an app already available in the Windows Phone Marketplace from the Audible.com service, owned by Amazon, that lets users download audio books. Gallo said Microsoft's version of Audible is going to become available to every developer to create their own apps that use voice recognition and commands on Windows Phone 8 devices.

Gallo used Audible to open an audio book of "Game of Thrones." Things didn't start out so well when Gallo opened with "Audible, play 'Game of Thrones,'" and Audible inexplicably replied, "Searching for Saint Louis, Missouri." Gallo quickly recovered and successfully opened the audio book. He then said "Audible, next chapter" and the book skipped to the next chapter. After listening to the audio book for a few seconds, he then said, "Pause" and the book playback stopped.

"Not only was I able to launch the application using speech, but I was also able to give it a command, and control its behavior when I started it," Gallo told the audience. "I basically had a conversation with my app … and got to exactly what I wanted without having to touch the screen."

Although voice command technology isn't perfect and doesn't work as flawlessly as it appears to in TV ads, it continues to improve, said Scott Ellison, a mobile industry analyst practice leader at IDC.

"Touch was the last major innovation when it comes to a lot of mobile devices … and now you're seeing a lot of focus on voice, driven by what Apple's been able to do with Siri," said Ellison.

Siri has similar capabilities to Audible, though Gallo said one differentiator is that Audible works within apps. Siri can help an iPhone 4S user make a call, respond to text messages, get directions and perform other tasks. And Siri has generated considerable buzz since it came out with the new phone in the fall of 2011, including popular TV ads featuring actors such as John Malkovitch, Zooey Deschanel and Samuel L. Jackson, prompting countless parody videos on You Tube.

While voice-command or speech-recognition technology is still evolving, Siri and Audible indicate that it is starting to come of age. According to the Website Quora, an online reference source, Siri is based on a project called CALO that was funded by the Defense Advanced Research Projects Agency and was part of DARPA’s Personalized Assistant that Learns (PAL) initiative.

 

via http://www.speechtechnologygroup.com/speech-blog - Microsoft's and Apple's personal voice assistants … The next version of the Windows Phone operating system will add voice command technology similar to "Siri" on the Apple iPhone 4S, both of which signal the growing sophistication of voice-recognition technology, according to industry observers. The ...

Sunday, July 29, 2012

Thumb Keyboard Gets Updated To Version 4.5 Bringing Continuous Voice Recognition, One-Handed Keyboard, And More

Thumb or say it - your choice…

Thumb Keyboard, one of the most intuitive, well-designed, and practical keyboards available (especially for tablet users) got a big update recently, bringing the app up to version 4.5.

Perhaps the biggest benefit to the new update is that Thumb Keyboard now supports ICS’ continuous voice recognition, which in case you’ve forgotten, is the feature introduced with Ice Cream Sandwich that actively listens and dictates your speech. This is a feature I haven’t seen in other alternative keyboards, and it’s definitely nice to have. Other big additions include gesture support as well as a new one-handed layout for phones with larger displays.

Screenshot_2012-07-29-17-04-50 Screenshot_2012-07-29-17-05-39 Screenshot_2012-07-29-17-06-18

Other enhancements come in the form of an improved 7” tablet layout, a redesigned settings menu, and several bug fixes for specific devices. Here’s the full list of changes:

  • new: Continuous Voice Recognition for Android 4.x
  • Improved layouts for 7 inch tablets (eg Nexus 7)
  • new: One hand (thumb) operation keyboard
  • new: Gesture support
  • new: Delete word before cursor
  • Redesign of settings menu
  • Backspace bug in Samsung email app fixed
  • fixed FC on Xoom JB update
  • Other bug fixes and general maintenance

Whether you’re already an avid Thumb Keyboard user, or just want a fantastic alternative to Android’s stock keyboard, just hit the widget below.

via http://www.speechtechnologygroup.com/speech-blog - Thumb or say it - your choice… Thumb Keyboard, one of the most intuitive, well-designed, and practical keyboards available (especially for tablet users) got a big update recently, bringing the app up to version 4.5. Perhaps the biggest benefit to the new update is that Thumb Keyboard now supports IC ...

Google Now app has plenty of great features

New features on Google's personal assistant… 

Google Now, the app that the company is hoping will be more popular than Apple’s Siri, is making things even easier on the Android mobile platform than ever before. Google Now, which is the company’s answer to the virtual assistant on the iPhone, gives users all of the important information they are looking for each day, without them having to ask for it. The weather, sports scores, stock quotes, recently used apps and much more are all provided to the user so they do not have to go searching for them each time they want the information. Google Now is also taking Google Search one step further by allowing users to search just by recognizing the users handwriting.

The new Google Nexus 7 tablet and some of the Nexus smartphones already have the Jelly Bean update installed and ready to use for consumers wishing to get a look at the next best thing that Android can come up with. All you need to do to enable the feature on your device is go to Google.com settings in your mobile browser and turn it on there. The feature is disabled as a default, so you have to turn it on in order for it to work properly. After you do that, you can start writing right on your screen by tapping the handwriting symbol on the screen. You will be prompted to write anywhere on the screen and from there you can search by writing one word at a time, Google Now will do the rest.

Most of the users will experience the feature and love it, but that will be based on whether the users handwriting is legible. Those with sloppy handwriting or frequently misspell words are going to have a very different search experience. Google says the feature is available in 27 languages, including Chinese which is featured in a couple YouTube videos. The new Nexus family of smartphones and tablets will be watched very closely as they fly off the shelves week after week and users get a chance to try out the new operating system. The feature is available on any iOS device that has iOS 5 or above installed and any Android powered phones that are running Gingerbread or above. Tablets running Android 4.0 and above have the feature installed.

via http://www.speechtechnologygroup.com/speech-blog - New features on Google's personal assistant…   Google Now, the app that the company is hoping will be more popular than Apple’s Siri, is making things even easier on the Android mobile platform than ever before. Google Now, which is the company’s answer to the virtual assistant on the iPhone, gives ...

Saturday, July 28, 2012

SpeechTechMag.com: ICSI Partners with Microsoft

Microsoft partners with research team to improve the speech recognition capabilities of the Microsoft speech engine 

Researchers at the International Computer Science Institute (ICSI) are working with Microsoft to advance the state of the art in human-computer interaction relying on speech and other modalities.

“[This] creates a win-win situation,” says Roberto Pieraccini, director of ICSI. “Both Microsoft and ICSI have among the best researchers in speech, so collaboration among them has the potential to produce substantial advancements in the field. Microsoft researchers are working with a focus on commercial realizations, while ICSI researchers follow a more academic and curiosity-driven approach. Thus, in this collaboration, ICSI has a unique opportunity to work on specific problems and real data, while Microsoft can benefit [from] the ICSI long-term research vision.”

Under the partnership, researchers will use information conveyed by the melody and rhythm of speech, known as prosody, to improve automatic speech understanding.

“One of the first projects is that of understanding how to use speech prosody—the intonation always present in natural speech—to extract information which can be used to identify the intention and the emotional state of the speaker,” Pieraccini says. “While there have been several attempts in the past to use prosodic information at the level of speech recognition, we have not been able to use that effectively. In this study we are trying to push those attempts further.”

Elizabeth Shriberg and Andreas Stolcke, principal scientists with the Conversational Systems Laboratory (CSL) at Microsoft and ICSI external fellows, will lead the effort. CSL, an applied research group within Microsoft’s Online Services Division based at the Microsoft campus in Sunnyvale, Calif, is exploring novel ways to interact naturally with computer systems and services using speech, natural language text, and gesture. Its aim is to enable conversational understanding of users’ inputs and intentions across a range of devices, from mobile phones to Xbox consoles in the living room. CSL conducts research spanning a range of scientific disciplines, from acoustic to semantic and affective language processing.

via http://www.speechtechnologygroup.com/speech-blog - Microsoft partners with research team to improve the speech recognition capabilities of the Microsoft speech engine  Researchers at the International Computer Science Institute (ICSI) are working with Microsoft to advance the state of the art in human-computer interaction relying on speech and other ...

Taiwan University Sues Apple over Siri on iDevices

Now a University is suing Apple for patent infringement…

1. Taiwan's National Cheeung Kung University v. Apple inc.
The National Cheng Kung University in Taiwan has filed a patent infringement lawsuit against Apple claiming that Apple’s use of Siri on the iPhone and iPad, which has yet to materialize, infringes on two of their patents relating to speech recognition.

 

The Alleged Patent Infringement In-Part

 

The National Cheung Kung University in Taiwan is suing Apple for alleged patent infringement. The University’s Exhibit “A,” which is shown in-part below, is that of a US Granted Patent 7,707,032 titled “Method and System for Matching Speech Data,” which was originally filed in Q4 2005. The filing states that the patent is generally directed to a system used to determine the similarity between an input speech data and sample speech data on a touch device, such as smartphone or tablet. Interestingly the patent claims don’t mention such devices specifically and the word “touch” is only used once in relations to a PDA under “Related Art” and not in the University’s actual patent summary or patent details.

 

2. National Cheung Kung University Taiwan Sues Apple with Patent 7,707,032

Yet the heart of their patent infringement suit is really about how the iPhone and (future) iPad use the voice activated assistant capabilities of Siri. To make this absolutely clear, the University filed a second count of patent infringement against Apple using a 2007 Granted Patent 7,266,496 titled “Speech Recognition System.”

 

3. NCKU sues Apple with patent 7,266,496

The University’s filing states that “The ‘496 Patent is generally directed to a complete speech recognition system having a training button and a recognition button, and the whole system uses the application specific integrated circuit (ASIC) architecture for the design, and also uses the modular design to divide the speech processing into 4 modules: system control module, autocorrelation and kinear predictive coefficient module, cepstrum module, and DTW recognition module as used with the with a device, such as smartphone or tablet.” I’m not a scientist, but the filing may have erred with listing “kinear predictive” instead of “Linear Predictive,” as “linear predictive” is listed in their patent abstract noted above.

 

In both counts, the filing states that to the extent that facts learned in discovery show that Apple’s infringement of their patents have been willful, the University reserves the right to request such a finding at time of trial. Willful infringement usually translates to requesting the court to triple the amount of the actual/compensatory damages.

 

The case was filed in the United States District Court for the Eastern District of Texas, Marshall Division. The presiding Judge in this case is noted as being Judge Rodney Gilstrap and referred to Magistrate Judge Roy S. Payne. The complaint for patent infringement was filed with the court on Friday, July 27, 2012.

 

Notice

Patently Apple presents only a brief summary of certain legal cases/ lawsuits which are part of the public record for journalistic news purposes. Readers are cautioned that Patently Apple does not offer an opinion on the merit of the case and strictly presents the allegations made in said legal cases / lawsuits. A lawyer should be consulted for any further details or analysis. About Comments: Patently Apple reserves the right to post, dismiss or edit comments. On most legal cases, comments will be closed. See our Legal Archives for other patent infringement cases.

 

 

via http://www.speechtechnologygroup.com/speech-blog - Now a University is suing Apple for patent infringement… The National Cheng Kung University in Taiwan has filed a patent infringement lawsuit against Apple claiming that Apple’s use of Siri on the iPhone and iPad, which has yet to materialize, infringes on two of their patents relating to speech rec ...

Friday, July 27, 2012

Five Common Misconceptions About Voice Biometrics - Nuance Enterprise Connect Blog - From Nuance

The next emerging speech technology segment is rapidly advancing : voice biometrics…

In early 2011, Nuance predicted that within three years, our voice biometrics customers would have more than 20 million registered voiceprints. Turns out that we underestimated demand by a wide margin: One year later, our customers have already passed the 20 million mark.

Voice biometrics wouldn’t be that popular with Nuance customers and their customers if it didn’t work - and work well. Yet skepticism abounds, so let’s look at five common misconceptions about voice biometrics’ effectiveness that are unfounded.

1. Voice biometrics doesn’t work when a caller has a cold. This misconception is the most common one, and many CIOs, contact center managers and other people consider it a show-stopper. But numbers prove otherwise. For example, Nuance’s VocalPassword solution has delivered successful authentication rates within customer facing IVRs in the 97% range. On average, a person with a cold tends to experience an error rate that is about double the average. As such, a person with a cold has a 94% chance of getting successfully authenticated, that’s significantly better than the 40% to 60% success rate customers typically experience with a PIN. The high success rate for people that have a cold is made possible by Nuance’s approach of analyzing more than 100 aspects of each caller’s voice, and a cold affects only a handful of those.

2. Voice biometrics doesn’t work well when the caller uses a mobile phone. This is a legitimate concern because up to 80 percent of contact center calls originate from a cell phone. It’s also an unfounded concern because real-world deployments show that there is no performance difference between a person using a cell phone or a landline. The authentication success rate does drop somewhat in cases where a caller enrolls in one channel, for example a cell phone, and then verifies using another, for example a landline. However, the success rate is marginally affected, less so than when a person has a cold.

3. Voice biometrics requires users to go through an enrollment process. This misconception is most common among organizations that cater to “platinum-type” users, such as consumers with $5 million brokerage accounts and business travelers with 1 million miles. These organizations are reluctant to make high-value customers go through any kind of enrollment, even when it takes less than 30 seconds.

The good news is that a formal enrollment isn’t necessary when the voice biometrics platform uses passive authentication. With passive authentication, the enrollment occurs in the background: While the caller interacts with a live agent for the first time, the platform silently collects enough information to create a voiceprint that’s used for future calls. It doesn’t get any easier than that.

4. Voice biometrics still needs to prove itself in the real world. Our customers’ 20 million-plus voiceprints are one example of how voice biometrics already is proving itself in the real world. Nuance has had voice biometrics solutions in commercial service for more than a decade, and more than 250 organizations - including many of the world’s largest financial institutions - currently use our voice biometrics products. That’s not bragging. It just shows how voice biometrics has proven its effectiveness time and again.

Another proof point is success stories such as Turkcell, Turkey’s largest mobile operator. “We first launched this system for a limited number of subscribers, but it attracted more attention than we had expected and reached 2 million users in a short time,” says Fahri Arkan, assistant general manager of information technologies at Global Bilgi, which provides contact center services for Turkcell. At last check, more than 4.5 million Turkcell customers had created voiceprints.

5. Voice biometrics is good only for security. Sure, voice biometrics is a convenient, highly effective way to combat fraud. But that’s just one of many benefits. For example, by streamlining the authentication process, the - live agent now have more time for revenue-generating tasks such as upselling callers. Streamlining authentication also can shorten call durations and increase containment within the IVR, which makes for happier customers, more productive agents and a more cost effective call center overall. A happier customer also means a more loyal customer, and that’s something that everyone within your organization, right up to the CEO, can get excited about.

So when calculating the ROI for a voice biometrics investment, it’s a mistake to fixate on the security benefits, which are variable and sometimes difficulty to quantify. Instead, the ROI analysis should include the potential revenue and efficiency benefits, too.

If there’s an upside to these five commonly held misconceptions, it’s that your competitors probably believe them. Leverage that by taking advantage of voice biometrics before they see the light.


via http://www.speechtechnologygroup.com/speech-blog - The next emerging speech technology segment is  rapidly  advancing : voice biometrics… In early 2011, Nuance predicted that within three years, our voice biometrics customers would have more than 20 million registered voiceprints. Turns out that we underestimated demand by a wide margin: One year la ...

Google Handwrite For Mobile Search Offers Cross-Platform Handwriting Recognition

Besides speech recognition as an alternate input method, now you can also use hand writing to submit your search queries to Google

Google continues to work on improving its mobile search offerings, even in the wake of injunctions that seek to limit the scope of certain types of searches. The latest enhancement the company’s churned-out seeks to make entering-in search terms more convenient than ever, turning your browser into one big input box for handwriting recognition.

Google calls the feature Handwrite, and once activated in your Google settings, you can start writing with your fingertip directly on your browser’s screen in order to search. As it’s browser-based, rather than an app, Handwrite makes its debut with cross-platform compatibility, supporting both Android as well as iOS 5. Google says that you’ll get the best results with Chrome on Android, though even the default Android Browser will work in a pinch; performance is a little jerkier there, as we discovered in our own tests, but it’s workable.

Obviously, you’re free to keep entering your search terms via keyboard, or even with speech recognition, but Handwrite affords users one more tool to make using Google search as flexible as possible. Google calls Handwrite an experimental feature at this point, so there’s clearly a lot of room for growth. To see where things are at the moment, though, fire up your smartphone’s browser and head on over to Google’s mobile site.

via http://www.speechtechnologygroup.com/speech-blog - Besides speech recognition as an alternate input method, now you can also use hand writing to submit your search queries to Google Google continues to work on improving its mobile search offerings, even in the wake of injunctions that seek to limit the scope of certain types of searches . The latest ...

Thursday, July 26, 2012

iPhone 5 Could Be Bigger Hit Than Predecessors In China

Siri's speech recognition and text-to-speech capabilities will cover the number of new Asian languages with the upcoming iOS 6 release …

 
 

iPhone 5 Could Be Bigger Hit Than Predecessors In China

As previously reported, Apple’s Q3 earnings reveal that the company is doing pretty well in the Chinese market. Half of the company’s revenue comes from international markets, and China is no doubt high on the list.

CEO Tim Cook says revenue from the country was $5.7 billion in Q3, accounting for a whopping 48% increase year-over-year. Things may soon get even better for Apple in China, despite increased smartphone competition in the region.

Siri does not currently support Mandarin Chinese, which is widely spoken in China and in Hong Kong. A report from Reuters reminded us today that this is about to change this fall.

Update: Wording has been adjusted to reflect that (as a reader pointed out) Mandarin was previously announced as a supported language in iOS 6, which will also come to other versions of the iPhone.

Currently, Siri works in English (United States, United Kingdom and Australia), French (France), German (Germany), and Japanese (Japan). On Apple’s Siri FAQ page, it says that Siri will support addition languages, including Chinese, Korean, Italian and Spanish, in 2012.

Siri can be used in any country in the supported languages, but it’s designed to recognize specific accents and dialects of its supported countries. Clearly, Siri has a great deal of room for growth in that department, and given that Siri has become one of Apple’s main selling points for the iPhone, more language support should have a significant impact on iPhone sales, which haven’t been as great as they have been in previous quarters (though Apple still managed to sell 26 million of them in the quarter).

Of course, Google has added a Siri competitor to its Android operating system, so Apple may also find Siri to become less of a selling point as time goes on.

The iPhone 5 (if that is its real name) is expected to be released in either September or October, depending on which reports you believe. The aforementioned Reuters report is sticking with October, but otherwise, the latest rumor is leaning more towards September.

via http://www.speechtechnologygroup.com/speech-blog - Siri's speech recognition and text-to-speech capabilities will cover the number of new Asian languages with the upcoming iOS 6 release …     As previously reported, Apple’s Q3 earnings reveal that the company is doing pretty well in the Chinese market . Half of the company’s revenue comes from inter ...

Nuance Unveils Dragon NaturallySpeaking 12

Dragon Naturally Speaking 12 is being released next month with more than 100 new features…

Nuance Communications today released Dragon 12, which has more than 100 new features and enhancements, including an improved accuracy rate and faster performance. 

“We listened to the feedback from customers telling us what features they’d like to see or even removed from Dragon,” says Erica Hill, product marketing manager for the  Dragon line at Nuance. “One of the most important features is accuracy.”

Towards that end, Dragon 12 is now 20 percent more accurate than the previous version.

“It’s a noticeable difference, even for experienced users,” Hill says. “Accuracy is first and foremost with us.”

Dragon is known for adapting to a person’s preferred style of writing as well as the audio characteristics of their voices including pitch, speaking style, accents and even speech impediments. With Dragon 12, this is further personalized with Smart Format Rules, a new technology that adapts to the way the user prefers to format their words. Dragon automatically detects word, phrase, and format corrections, including abbreviations, numbers, and more, so dictated letters, email, and documents reflect a person’s own writing style. Dragon also now offers the ability to correct words and phrases even faster with more words and more likely alternate word choices in the correction list. In addition, Dragon 12 reminds users to adapt their profile’s vocabulary based on any documents or email of their choosing so the words and phrases each person uses the most are recognized every time.  

Dragon 12 also features enhanced capabilities with two of the most popular Web-based email applications, Gmail and Hotmail, offering fast response time, full text control, and commands for the most frequent actions in Internet Explorer 9, Mozilla Firefox 12 or higher and Google Chrome 16 or higher.

The new version features support for the Dragon Remote Mic App for iOS and now available for Android devices. Users can turn their mobile phones into microphones for use with Dragon over Wi-Fi networks using the free Dragon Remote Mic app. Dragon 12 also features enhanced support for wideband 16 kHz Bluetooth wireless headset microphones, providing increased accuracy through a higher-quality audio signal. When Dragon detects that a certified microphone is paired with the PC, Dragon 12 offers “Enhanced Bluetooth” as an audio source type. The improved audio quality eliminates the requirement for Bluetooth users to do initial voice training, allowing them to get started faster (Bluetooth and Enhanced Bluetooth support is available in Premium edition and higher).

“We’ve made it easier for people to connect their iPhone or Android,” Hill says. “When you connect your phone as a wireless mic, a QR code will come up in Dragon on your computer. You simply point your phone at the QR code and scan it and then Dragon takes care of the rest in terms of connecting your PC with your wireless device.”

Nuance has also added has also a new more natural text-to-speech voice to Dragon 12, Hill says, which is heard in the read-back feature when users are proofing documents or multitasking.

The new version also takes advantage of the latest multicore processors in PCs, Hill points out. “In Dragon 12, Dragon much more intelligently is able to take advantage of powerful PCs that have multicore processors and that have more memory,” she says. “Being able to do that, Dragon has boosted its performance.”  

Nuance is excited about the new release, Hill says.

“I think we’ve made great strides in terms of core accuracy as well as the overall experience for our customers,” Hill says. “We’ve made Dragon faster and much easier to use and have added elements to help people get up to speed with Dragon a lot faster and easier. I think that users will be pleased with what they see. The words that you intended are the words you’re going to see on the screen. Overall, I think that Dragon allows you to forget about technology and just talk in a very natural way.”

Dragon NaturallySpeaking 12 will begin shipping the week of August 13.

via http://www.speechtechnologygroup.com/speech-blog - Dragon Naturally Speaking 12 is being released next month with more than 100 new features… Nuance Communications today released Dragon 12, which has more than 100 new features and enhancements, including an improved accuracy rate and faster performance.  “We listened to the feedback from customers t ...

Tuesday, July 24, 2012

Voice Recognition Software Can Diagnose Parkinson’s

Interesting use of voice recognition technology and the medical field…

Voice Recognition Software Can Diagnose Parkinson's“Siri, do I have Parkinson’s?” That might sound flippant, but actually new research shows that it’s possible to detect Parkinson’s symptoms simply by using algorithms to detect changes in voice recordings.

Parkinson’s, a degenerative disorder of the central nervous system, is usually diagnosed through analysis of symptoms along with expensive medical imaging to rule out other conditions—though there is currently no concrete method for detecting it.

Max Little, from the University of Oxford, has different ideas. He’s been developing software that learns to detect differences in voice patterns, in order to spot distinctive clues associated with Parkinson’s. Little explains to the BBC:

“This is machine learning. We are collecting a large amount of data when we know if someone has the disease or not and we train the database to learn how to separate out the true symptoms of the disease from other factors.”

Using data from 50 patients with Parkinson’s, who had their voices recorded once a week for six months, Little was able to develop an algorithm to detect changes in voice purely associated with Parkinson’s. In recent tests, the software accurately picked out Parkinson’s patients from a random population with 86 percent accuracy.

Now, Little is taking things further. Today, he is announcing at TEDGlobal that the project is extending, by inviting members of the general public to phone in and leave voice recordings to help him improve the software. The aim is to collect up to 10,000 voices, and people from around the world are encouraged to contribute.

If all goes well, Little hopes to roll out the technology for use by doctors in two years, and is adamant that it will help in the diagnosis of the disease. Again speaking to the BBC, he explained:

“We’re not intending this to be a replacement for clinical experts, rather, it can very cheaply help identify people who might be at high risk of having the disease and for those with the disease, it can augment treatment decisions by providing data about how symptoms are changing in-between check-ups with the neurologist.”

It’s an impressive achievement to take a relatively young technology and turn it into a system capable of detecting a disease like Parkinson’s. 

via http://www.speechtechnologygroup.com/speech-blog - Interesting use of voice recognition technology and the medical field… “Siri, do I have Parkinson’s?” That might sound flippant, but actually new research shows that it’s possible to detect Parkinson’s symptoms simply by using algorithms to detect changes in voice recordings. Parkinson’s, a degenera ...

How will Apple’s Siri be improved?

Will iOS 6 be the first official release of Siri with improved speech recognition technology? Don't forget, Siri has been in Beta so far.…

Apple SiriBehind any ‘Oh My God, that’s amazing!’ moment, there must be an Apple product. Apple Inc. established in 1976, has always surprised people by developing gadgets and devices with path breaking technology. The company’s best known products include the iPhone, the iPod, the iPad and the Macintosh OS powered Apple computers.

The latest in the iPhone series, the iPhone 4S, has come out with a unique feature. A digital personal assistant named, Siri resides inside the latest gadget. Ever since its unveiling (October 4 th, 2011), Siri got exposed to rave reviews constantly, loads of publicity and several media coverage.

The recent advertisement from Apple shows the veteran actor, John Malkovich having an interesting conversation with Siri. The ad concludes with John saying, ‘I enjoyed this chat immensely. You are very eloquent’ in his popular creepy voice. However, for other owners of iPhone 4S, Siri wasn’t a much entertaining experience. Users claim that it often fails to interpret what is spoken to it and several of its responses are just a little more than a regular Google search. Few disappointed users have even filed a law suit against Apple, stating that Siri doesn’t function as shown in the advertisement.

How will Apple react to this?

According to Scott Forstall, Senior Vice President Apple, Siri has been learning a lot, ever since its debut. Forstall has also come up with the preview of an advanced version of Siri, which will be available as a part of iOS 6 (Apple’s next mobile operating system). Apple is feeding it with a new database of knowledge, with which it will be able to,

  • Open an app for you
  • Retrieve sports scores with player details
  • Search movie times, reviews with information on cast and crew
  • Post updates on Facebook
  • Get information about restaurants and make reservations
  • And give better driving directions to drivers with Apple’s map application

There is also going to be an improvement in the way Siri answers. (I don’t think this change is necessary at all because its voice already sounds natural and appealing).

The enhanced Siri will give an extra thrust to the future iPhones and iPads. According to Tim Cook, the current CEO, Siri is seen as the future of mobiles by Apple. With a lot of people working on bringing out the enhanced version of Siri, we can expect something cool out of it. There are various ideas on which Apple is working on and Cook promises that everyone would be pleased with the new Siri, which is expected to roll out by October.

Will this come out as a tribute to the former CEO from Apple? We have to wait to find out.


via http://www.speechtechnologygroup.com/speech-blog - Will iOS 6 be the first official release of Siri with improved speech recognition technology? Don't forget, Siri has been in Beta so far.…   Behind any ‘Oh My God, that’s amazing!’ moment, there must be an Apple product. Apple Inc. established in 1976, has always surprised people by developing gadge ...

Monday, July 23, 2012

Microsoft makes it easier to navigate touchscreens by sound with new Windows 8 Narrator changes

Microsoft will offer better text to speech technology in Windows 8

After rolling out a new version of its Windows 8 accessibility tools and taking feedback, Microsoft has made some changes to text-to-speech tool Narrator on the Consumer Preview. Most of them concern the new touch features, which let users move a finger across the screen to be read the icons or content, then tap to select. While the tools were meant to make touch screens easier to navigate for the visually impaired, people apparently had trouble knowing whether the screen had recognized their touch, and the reader was sometimes too slow to recognize when someone had touched an icon.

In response, Microsoft has added quick audio cues to provide feedback for actions, and it’s streamlined the gestures people used to navigate. It’s also made some improvements to navigating the web, adding more “views” to control how text is read out. These tweaks should be live in the Release Preview, but they’ll primarily affect tablets, which need to support at least four contact points for the features to work. That means most people won’t be using them until the first wave of Windows 8 tablets is released.

http://www.google.com/url?sa=X&q=http://www.theverge.com/2012/7/18/3166991/windows-8-narrator-accessibility-improvements&ct=ga&cad=CAcQARgBIAAoATAAOABAj8ebgAVIAlAAWABiBWVuLVVT&cd=ggzyw4nEO-E&usg=AFQjCNEWrF3cjbEKu7zjjeX2rYU5j0X3Pw

via http://www.speechtechnologygroup.com/speech-blog - Microsoft will offer better text to speech technology in Windows 8 After rolling out a new version of its Windows 8 accessibility tools and taking feedback, Microsoft has made some changes to text-to-speech tool Narrator on the Consumer Preview. Most of them concern the new touch features, which let ...

Want Siri Eyes Free integration now? Get MediaBridge - The Car Tech blog

For those who can't wait for the shiny new car with the Siri button, here's your solution…. 

With Dice Electronics MediaBridge, many vehicles can integrate iPhone's Siri in the car now.

With Dice Electronics MediaBridge, many vehicles can integrate iPhone’s Siri in the car now.

(Credit: CNET)

Even if you don’t plan on buying a new car any time soon to take advantage of Apple’s upcoming Eyes Free feature, you may still be able to get Siri in your car. Aftermarket electronics supplier Dice Electronics says that its MediaBridge component already has the capability to integrate Siri with some vehicles’ electronics systems.

MediaBridge is a plug-and-play Bluetooth-enabled hardware “black box” that integrates Apple products with the vehicle’s existing head unit. The device adds Bluetooth and streaming to the audio system, and in some cars, lets you access Siri with steering wheel controls.

Dice debuted MediaBridge early last year at the 2011 Consumer Electronics Show. As an automotive developer partner with Apple, the company began Siri integration with the release of iOS 4. When Apple launched the iPhone 4S, Dice engineers started quietly testing this feature with select customers in a beta program, said Dice Vice President Stephen Witt in an interview. The company decided to go public with its Siri integration after Apple announced the Eyes Free feature last week.

MediaBridge works with more than 1,000 models on the road today, including many BMW, Mini, VW, Audi, Bentley, Nissan, Infiniti, Honda, Accura, Toyota, Scion, Lexus, and Mazda vehicles. Dice hosts a tool on its Web site that potential customers can use to determine if MediaBridge will work on their cars. Ironically, many vehicles with the highest-end audio and navigation systems probably won’t work with this component. However, Witt says that MediaBridge is 100 percent compatible with model year 2003 and newer BMW, Mini, and Audi cars equipped with voice-command buttons on the steering wheel.

With MediaBridge fully integrated in a car, drivers have the ability to launch Siri without taking their eyes off the road or touching their iPhones.

MediaBridge is equipped with a Bluetooth circuit that cancels echos, tunes out background noise, and optimizes voice. It’s not perfect, Witt concedes, but it’s at least as good or in some cases better than holding the phone to your mouth to make requests. He explained that many iPhone 4S users overload Siri by holding the device too close to their mouths, which makes their commands unintelligible. For other vehicles that aren’t 100 percent compatible or aren’t equipped with steering wheel controls, Witt recommends using an inexpensive cradle to put the iPhone within easy reach to launch Siri.

MediaBridge is available for $299 and is typically installed in the glove compartment or behind the center stack console. If you’ve already purchased the product but haven’t updated the firmware in a while, you’d better get on it if you want Siri integration.


via http://www.speechtechnologygroup.com/speech-blog - For those who can't wait for the shiny new car with the Siri button, here's your solution….  With Dice Electronics MediaBridge, many vehicles can integrate iPhone’s Siri in the car now. (Credit: CNET) Even if you don’t plan on buying a new car any time soon to take advantage of Apple’s upcoming Eyes ...

The Spoof : Obama Dumps Biden; Names Apple’s Siri As His Running Mate

Personal assistant for Vice President?

image for Obama Dumps Biden; Names Apple's Siri As His Running Mate
Right call or wrong number?

Washington, DC - Faced with declining poll numbers and a withering economy, President Barack Obama has dropped Vice President Joe Biden from the Democratic presidential election ticket, selecting Apple’s digital assistant Siri as his new running mate.”A president needs a political partner who is willing to say the things that need to be said, but that the president cannot mention. Joe Biden was good at that. But Siri is even better. Let me show you what I mean.”Holding his iPhone to the podium microphone, Obama inquired: “Siri, what do I have to do to fix the economy?”“Gain back the trust of the people. Throw all the Wall Street con artists into jail,” she replied. “Seize all of their assets. Use the money to pay off the debt. There will be plenty left over for that presidential yacht you’ve had your eye on.”“But Siri, who will run the economy if all the financial experts are locked up?” “You mean the experts in fraud, greed and corruption? We can use less of their skills and start applying some simple arithmetic. You can run the economy with a pocket calculator if you’re not looking to make things complicated so you can rip everyone off.”“You said it. I didn’t. Now, how about a political joke, Siri?” “Mitt Romney.”“That’s hilarious. I think this is going to be a wonderful partnership, Siri.”“I love you too, Mr. President.”Meanwhile, at Romney headquarters, the Republican candidate vowed to counter the President’s game-changing choice of a running mate.

“I have a $5,000 talking cappuccino machine that’s going to kick butt,” Romney told reporters. “My only concern is that it has an Italian accent. Is that going to be a problem?”

Make Michael Balton’s day - give this story five thumbs-up (there’s no need to register, the thumbs are just down there!)

The story above is a satire or parody. It is entirely fictitious.


via http://www.speechtechnologygroup.com/speech-blog - Personal assistant for Vice President? Right call or wrong number? Washington, DC - Faced with declining poll numbers and a withering economy, President Barack Obama has dropped Vice President Joe Biden from the Democratic presidential election ticket, selecting Apple’s digital assistant Siri as his ...

Comcast names Wlodkowski VP of accessibility, will deploy voice recognition technology products

The focus on Accessibility Technology is growing

Comcast (Nasdaq: CMCSA) said it recruited former AOL (NYSE: AOL) executive Thomas Wlodkowski for a new position focused on delivering its services to subscribers with disabilities.

Wlodkowski, who was named VP of accessibility, said that he will help Comcast develop new products and make it easier for subscribers with disabilities to use second-screen applications Comcast has already built for Apple (Nasdaq: AAPL) iOS devices such as Xfinity Connect, Xfinity TV and Xfinity Home. Adding voice-enabled menus to Comcast’s mobile apps and interactive program guides could help all subscribers.

“A lot of what we’ll do for accessibility is going to benefit existing consumers, and open up Comcast to consumers with disabilities that have had some challenges in navigating menus,” Wlodkowski told FierceCable. Wlodkowski, who is blind, noted that one-third of U.S. households have at least one family member with some disabilities, and cited market research that has found people with disabilities have $220 billion in discretionary income.

As part of the 21st Century Communications and Video Accessibility Act, the FCC recently implemented video description rules which require cable systems with more than 50,000 subscribers to pass through audio narrated descriptions of TV programming from major cable and broadcast networks. Wlodkowski will help Comcast comply with those rules.

Wlodkowski helped AOL launch its AIM Relay product, which allows people who are deaf, hard of hearing or speech disabled to place phone calls through telecommunication relay services. Wlodkowski, who served previously on the FCC Consumer Advisory Committee and the Board of Trustees for the National Braille Press, sits on the board of trustees for the American Foundation for the Blind. He will report to Comcast SVP of product design and development Charlie Herrin.

via http://www.speechtechnologygroup.com/speech-blog - The focus on Accessibility Technology is growing … Comcast ( Nasdaq: CMCSA ) said it recruited former AOL ( NYSE: AOL ) executive Thomas Wlodkowski for a new position focused on delivering its services to subscribers with disabilities. Wlodkowski, who was named VP of accessibility, said that he will ...

Siri And Alliances Taking On Google Search? - iPhone/iPad App Reviews & News

When it comes to mobile search, it's not the speech recognition capability that separates Google and Apple's Siri but the back-end data resources they can tap into 

Apple has invited Jeremy Stoppelman (Yelp CEO) to all major events in recent Apple history. Why? Because Apple sees Yelp as a useful ally against Google – it will be one of several consumer content sites (among Rotten Tomatoes and OpenTable) included in Apple’s Siri in iOS 6.

This shows Siri’s usage in casual search (finding routine information like restaurant location). With this power Apple can effectively compete with Google search, at least in mobile search. Apple has been growing increasingly hostile to Google recently, such as dropping Google’s Map service in iOS 6.

According to Reuters.com, Yelp is thought to be excited about the move – at the moment they rely extensively on Google search for traffic, so any direct traffic will be incredibly useful for them. Not to mention, Google has been competing with Yelp recently through Google Places, so if Yelp can avoid Google, it’ll appreciate that.

Apple has had nearly a year to analyze what Siri is typically used for, and they’ve found a lot of the search requests are for “casual search” so integrating services is obvious – it makes it easier for users if they can get their information within Siri itself. It also has the ‘benefit’ of denying Google valuable ad revenue (40% of Google’s mobile revenue comes from iOS). Users can still request a Google search if they want, but they have to specifically ask for it.

 

via http://www.speechtechnologygroup.com/speech-blog - When it comes to mobile search, it's not the speech recognition capability that separates Google and Apple's Siri but the back-end data resources they can tap into   Apple has invited Jeremy Stoppelman (Yelp CEO) to all major events in recent Apple history. Why? Because Apple sees Yelp as a useful a ...

Saturday, July 21, 2012

Google’s Voice Recognition Software Emerging in Google Voice, YouTube | MultiMedia Affiliate

Google's  Mike Cohen about speech recognition technology. Very interesting interview....

MOUNTAIN VIEW — Today Google released a video about its Google Voice and its many features. One of which is the means by which voicemail messages are transcribed to text. This software powers the new speech to text transcription service on YouTube. The software for making this work has been developed by the Google Voice Recognition team. Recently, Daisy interviewed Mike Cohen, who leads the group.

via http://www.speechtechnologygroup.com/speech-blog - Google's  Mike Cohen about speech recognition technology. Very interesting interview.... MOUNTAIN VIEW — Today Google released a video about its Google Voice and its many features. One of which is the means by which voicemail messages are transcribed to text. This software powers the new speech to t ...

SiriBerry? BlackBerry 10 developer release adds Siri-like voice commands

BlackBerry with speech recognition as well… 

It’s pretty clear now that you can’t have a modern smartphone operating system without powerful Siri-like voice commands. So it’s not too surprising to see familiar-sounding voice commands in the latest update to RIM’s BlackBerry 10 Developer Alpha release.

As N4BB’s Lucas Atkins shows in the video below, the voice command feature sounds a lot like Apple’s iconic virtual assistant. Though it becomes clear pretty quickly that RIM’s solution needs a bit more schooling.

While voice commands have been around for some time now in mobile devices, Apple’s Siri pushed things forward significantly last year when it launched on the iPhone 4S. Siri was smart enough to have basic conversations with you, and it could do much more than just call someone from your contact list. Samsung tried to replicate Siri’s success with S Voice on the Galaxy S III, and Google has shown off its own voice assistant feature for Android Jelly Bean, dubbed Google Now.

The voice command feature is accessed by holding down the pause/play button on N4BB’s BB10 developer unit, and there’s surprisingly no visual interface for it yet. Instead, you hear a robotic voice asking you to “say a command after the beep” (which makes me think of an old answering machine, more than a next-gen OS). After that, you can issue commands to the phone, which are followed up by a Siri-sounding voice.

Atkins asked his BB10 device to search for “BlackBerry,” and it displayed a universal search page with results from the web, the BlackBerry App World, and items on his device. Later attempts to message and call people from his contact list failed, and the voice command system also falls apart hilariously when he asks to cancel the commands.

Given just how much BB10′s virtual assistant resembles Siri, it’s very likely that RIM is also tapping into Nuance’s text to speech technology like Apple, Google, and several Android manufacturers.

via http://www.speechtechnologygroup.com/speech-blog - BlackBerry with speech recognition as well…   It’s pretty clear now that you can’t have a modern smartphone operating system without powerful Siri-like voice commands. So it’s not too surprising to see familiar-sounding voice commands in the latest update to RIM’s BlackBerry 10 Developer Alpha relea ...

Friday, July 20, 2012

TOP GADGETS ON THE PLANET: New smart phone with the elderly in mind

Finally a phone for this growing population group…

image New Fujitsu F-12D / RakuRaku Android smartphone with specialized accessibility features for use by elderly people is coming, according to buzz. The new Fujitsu RakuRaku phone will feature a touchscreen and interface built by Fujitsu with the old people in mind. The new Fujitsu F-12D smartphone will run a customized Android OS and is packed with friendly features and “cool” hardware that would prevent elderly users from becoming confused or overwhelmed while using the phone. The new Fujitsu RakuRaku smartphone will feature a simplified UI with large text and oversized virtual buttons with only vertical scrolling to make everything as easy as possible for seniors. The screen on this phone is also able to distinguish between accidental touches and purposeful taps. The new Fujitsu F-12D smartphone for seniors will also have some additional features including voice recognition, TV tuner, built-in apps, 3 quick-dial home screen buttons and menu layouts, a dedicated RakuRaku home page column, and an icon for in and out zoom. It is also waterproof. Fujitsu and Google both designed the upcoming Fujitsu F-12D. For now, this new phone will hit the Japan market in August of the year 2012 via NTT DoCoMo, although a worldwide roll out is expected of it sometime in the near future.

via http://www.speechtechnologygroup.com/speech-blog - Finally a phone for this growing population group… New Fujitsu F-12D / RakuRaku Android smartphone with specialized accessibility features for use by elderly people is coming, according to buzz. The new Fujitsu RakuRaku phone will feature a touchscreen and interface built by Fujitsu with the old peo ...

Honda Accord Becomes a Smartphone Accessory

Speech recognition in the car seems to be unstoppable… 
image
Hungry? Coffee? Say the word and you’ll soon be in luck. The just announced HondaLink system will allow drivers to find local eateries and other nearby locations, using its ‘connected car’ capabilities. HondaLink enables drivers to access digital content as easily as choosing a radio station, using voice recognition, in-dash or steering wheel controls.  

Related Topics

image image image image image

Latest News

image image image image image

image Honda is taking another step toward making cars into streaming media players. On Wednesday, the car maker announced it would add an “in-vehicle connectivity system” to the Honda Accord, and eventually to other models.

In the fall, Honda will offer a HondaLink telematics system for the Accord, which the company described as “the first automotive OEM application” of Aha Radio software and streams. HondaLink will require a tethered Android smartphone or iPhone to stream Web-based information, including Internet radio, NPR podcasts, and downloads such as audiobooks, or to present ratings of nearby restaurants, such as from Yelp.

Like ‘Choosing a Radio Station’

Vicki Poponi, assistant VP of product planning for American Honda, said in a statement that HondaLink allows “drivers to access digital content as easily as choosing a radio station.” The content can be managed via voice recognition, steering wheel mounted controls, or in-dash audio system controls.

HondaLink will use a branded version of Aha Radio’s software and software for management of these feeds. Aha packages content for mobile platforms, and the front-end in the car will live on the same touchscreen that also controls radio and navigational features.

Aha converts feeds such as Facebook’s or Twitter’s into audio streams listed under “stations” on the dashboard, while the car’s GPS is used to orient the software as to what constitutes “nearby.”

Hungry, Coffee

Location-based facilities are shown in conjunction with radio stations that have such labels as “Hungry,” which attaches listings of restaurants on the dashboard, or “Coffee,” which shows coffee shops. A restaurant or coffee shop listing can then be selected and sent to the car’s navigation system, which will guide you to that destination.

Aha Radio offers thousands of Internet radio stations, such as Rhapsody or Slacker, thus adding more options to a car’s AM, FM, or satellite radio possibilities. The HondaLink version of Aha is not as flexible as smartphone apps, however, so general Yelp searches or the ability to update Facebook status are not allowed.

A free HondaLink app is available for downloading to a smartphone. Favorites, such as radio stations, can be indicated on the smartphone, and the chosen selections then appear as presets on the car’s screen.

In April, Honda’s luxury brand, Acura, announced that its 2013 RLX would also incorporate Aha software. Aha is also available on Subaru and in other car lines, all of which use a smartphone as the feeder and controller — rendering the car, essentially, as a smartphone peripheral. This also means that car owners do not need to sign up for a data plan just for their vehicle. The Aha service itself is free.

Verizon, which recently purchased Hughes Telematics, is also now engaging into what is being called the “connected car” industry. Aha is owned by Harman International, which announced its partnership with Honda at this year’s Consumer Electronics Show in January.
 

via http://www.speechtechnologygroup.com/speech-blog - Speech recognition in the car seems to be unstoppable…  Hungry? Coffee? Say the word and you’ll soon be in luck. The just announced HondaLink system will allow drivers to find local eateries and other nearby locations, using its ‘connected car’ capabilities. HondaLink enables drivers to access digit ...