Thursday, August 9, 2012

Interact-AS Speech to Text, Text to Speech Translation Software

Speech technology for the vision impaired community continues to evolve….
Interact-AS(TM) is speech recognition software for your PC laptop, netbook or tablet that can allow deaf and hard of hearing individuals to directly communicate with people who do not know sign language. The person who is hard of hearing can read a transcript of what’s being said, while someone with difficulty writing or typing can dictate memos or generate text for documents and emails.

The Interact-AS Consumer Edition is a scaled down version of Interact-AS ideal for communicating with a few people. It features:

  • Microsoft’s speech recognition and voice synthesis engines
  • Support for speech, typing and handwriting input
  • Instant closed captioning of conversations that can be saved
  • Complete suite of Visualize Tools including built-in sketch pad
  • Auto translate feature

Interact-AS(TM) can remove multiple communication barriers. Compare Interact-AS versions.

  • Individuals who are deaf can directly communicate with people who do not know sign language
  • A person who is hard of hearing can instantly see a closed-caption transcript of what’s being said in conversations, a conference room discussion, a radio broadcast, or a video program
  • People who have difficulty writing or typing but have verbal skills can use their voice to dictate memos, answer test questions, or generate text for documents and emails
  • Interact-AS gives a voice back to individuals who have lost the ability to speak by voicing aloud whatever a person types or writes

Features:

  • Supports written, typed and spoken input
  • Spoken words are instantly transcribed and displayed
  • Transcript includes an optional synchronized audio recording
  • Written or typed words are instantly spoken aloud so a non-verbal person can participate in classroom discussions
  • Use the Visualize feature to sketch ideas or make notes on pictures

Load Interact-AS onto your PC laptop, netbook or tablet and you are ready to go. Interact-AS makes it simple to communicate—whatever you type or write is spoken out loud. Plus, using an external or built-in computer microphone, speech can be translated into text that is displayed on your screen, so you no longer need to rely on pen and paper. Take Interact-AS wherever you go: to work or school, stores, restaurants and more for easier communication anywhere, anytime, with anyone.

 

Advanced Features

  • Visualize is just one of Interact-AS’s many features. Use the visualize tab to show pictures, video clips or maps. Use the sketch pad where you can draw and discuss ideas.
  • Select the gender of the voice output you want to use
  • Save a transcript of the conversation for later reference
  • Add your own unique terms to the system



via http://www.speechtechnologygroup.com/speech-blog - Speech technology for the vision impaired community continues to evolve…. Interact-AS(TM) is speech recognition software for your PC laptop, netbook or tablet that can allow deaf and hard of hearing individuals to directly communicate with people who do not know sign language. The person who is hard ...

Making the Case for Hands Free Poker Voice Recognition Software

Are you up for a game of poker? Just use your voice. Speech recognition in the gaming and industry.....

In 2011, Two Plus Two forum member “Jeff_S” officially launched Hands Free Poker, an innovative way to play online poker without ever having to click a mouse or use a video game controller. I can remember speaking to Jeff personally about his MTT tool years ago and how it came about because of hand pain he experienced from long hours of online play.

Hands Free Poker allows players to play long sessions online through its voice recognition software and there is even a YouTube video out there that shows it in action. Keeping in mind that Hands Free Poker is in need of several improvements (PokerStars Zoom Poker compatibility as well as Lock and Merge support, just to name a few), we’ve decided to publish an article outlining how the software works in hopes that requests for updates from the poker community will be heeded. To begin with, this software (and others that are sure to follow in its path) has a considerable amount of potential in today’s “on the fly” online poker environment provided that certain voice command issues and mass multi-tabling compatibility can be achieved. Hands Free Poker recognizes voice commands and begins by labeling each table in progress as “1,” “2,” “3,” and “4.” For example, if a player is participating at four tables at a time, a large number will appear in the top right window of each table designating its specific number. In order to move to that table, a voice command with the corresponding number is required.

The voice recognition software recognizes basic commands such as “Fold,” “Call,” “All-In,” and “Raise.” So, if you wanted to shove pre-flop on the second table, all you would have to do is say “Two” and “All-In” and your chips will fly into the middle of that table just as if you had physically clicked the all-in button with your mouse. It truly is an amazing thing to see.

There are clear signs that this concept could work successfully in the community as long as there are future updates and improvements made to its functionality. For one, this software has not received any meaningful official updates since Black Friday nor has there been any reply from Jeff in the official Two Plus Two forum thread in quite some time. This is understandable in some regards based on the significant impact Black Friday had on the overall poker market, especially those who formerly played online while residing in the United States. With the 2012 commercial release of Zoom Poker on PokerStars, many online poker players are now four-tabling the Zoom format and looking for ways to streamline their betting experience while not sacrificing any of their bottom line or hourly win rate.

It is unclear whether this type of voice recognition software will be able to revolutionize the game in the next 12 to 24 months due to heavy reliance on software applications such as Table Ninja along with marquee database software such as Holdem Manager and PokerTracker, but it will be interesting to see any new progress that comes to the Hands Free Poker application.

It may be that much more development work is needed in order to become compatible with the current versions of major poker sites and more importantly, to instantly adapt to any updates that are made to a site’s client.


BECOME A MEMBER of PokerSoftware.com today. You can chat with us and ask questions to our poker software experts in the forums and get access to EXCLUSIVE members-only content. Sign up today!

More articles

Member Comments

Jeff S (Hands Free Poker)’s Comment

2012-08-06 15:34:58

We had stopped development of the software due to Black Friday, but things look to be improving in the industry. The software still works for Poker Stars and we would like to see the online poker market open back up for US players to fully get back onto development and offer a tool for players to control with voice. I think this is a very fair review from pokersoftware.com, talks about the ups and downs, very fair.

Hand-Histories.com

Original Page: http://www.google.com/url?sa=X&q=http://www.pokersoftware.com/articles/2012/08/making-the-case-for-hands-free-poker-voice-recognition-software.html&ct=ga&cad=CAcQARgBIAAoATAAOABA1ciEgQVIAlAAWABiBWVuLVVT&cd=y3Z_kCcgYKo&usg=AFQjCNHQyvOUtfS4Qv8dfHQW64BkZW2HUw

Best,

Gerd
via http://www.speechtechnologygroup.com/speech-blog - Are you up for a game of poker? Just use your voice. Speech recognition in the gaming and industry..... In 2011, Two Plus Two forum member “Jeff_S” officially launched Hands Free Poker , an innovative way to play online poker without ever having to click a mouse or use a video game controller. I can ...

Wednesday, August 8, 2012

Ivee Voice Activated Alarm Clock » Coolest Gadgets

Now you can tell your alarm clock when to wake you up. Speech recognition on your nightstand…

I would presume that most of us rely on our smartphones as our alarm clocks, since we get to choose the kind of ringtone to wake up to. However, there are others who would like a dedicated alarm clock to get the job done, as it has always been that way, so it is nice to have it continue. Well, since we have moved on to voice commands in our smartphone operating systems like Samsung’s S Voice and Apple’s Siri, how about introducing voice commands to the humble alarm clock? This is what happened with the $59.99 Ivee Voice Activated Alarm Clock.

No longer do you need to smash your alarm clock to send it to snooze every morning when it rings, and you can always get out of bed on the right side by yelling directly at it. Unlike your pooch, this is one alarm clock that is obedient and actually listens to what you say! The Ivee Voice Activated Alarm Clock will also come equipped with a built-in FM radio and a timer, and it sports a rather generous 5″ LED display, where it will be accompanied by half a dozen natural, soothing sleep sounds, not to mention being able to respond to over 30 voice commands. Each snooze moment lasts for up to 9 minutes.


via http://www.speechtechnologygroup.com/speech-blog - Now you can tell your alarm clock when to wake you up. Speech recognition on your nightstand… I would presume that most of us rely on our smartphones as our alarm clocks, since we get to choose the kind of ringtone to wake up to. However, there are others who would like a dedicated alarm clock to ge ...

The Art of Frictionless Customer Service

Multi channel contact center and speech recognition and how it transforms into a smooth customer service experience…

If you haven’t heard the term “frictionless” yet, it’s time to add it to your customer service lexicon. The skyrocketing amount of inbound calls from mobile phones is a major reason. Some Nuance customers say that more half of their contact center interactions now involve a mobile device. That’s why so many organizations have made mobile customer service a priority this year.

In a frictionless environment, customer service channels are freed from their traditional silos and integrated with one another. For example, when the mobile app is integrated with the IVR, customers have convenient, seamless access to live agents. 

Here’s an example: A bank creates a smartphone app that’s speech-enabled with natural language understanding so customers can simply speak a request instead of typing it. Personal assistants like Dragon Go! are rapidly conditioning more customers to feel comfortable posing questions to an app rather than an agent. If the app determines that a live agent is the best way to answer a particular question, it can automatically establish that call.

At the same time, the app can take all of the information collected so far and provide it to the agent via a screen pop so the caller doesn’t have to repeat everything. That intelligence improves the customer service experience, shortens call durations and enables each agent to handle more callers. The analyst firm Ovum calls this kind of frictionless scenario “smart, connected interaction.”

“Applications that share information across platforms - and in doing so provide the contact center agent with current, accurate data about what the customer was doing before escalating the problem to a voice call - lead to better interactions,” Daniel Hong, lead analyst of Ovum said in a recent interview. “In other words, representatives that are aware of the context of the interaction can help resolve the customer issue, alleviate the situation and expedite the transaction.”

U.S. mobile operator MetroPCS, illustrates the benefits of frictionless customer service. When subscribers dial its customer service number from their mobile phone, the My Metro app that’s preloaded onto their handset would automatically launch and offer to help answer their question.

“It didn’t require a customer to be trained on how to use it,” says Jay Moore, MetroPCS customer operations manager. “It was a very easy application. The customer could look at it and decide if they want to use it. If not, [they could] move on to the IVR, or they could use it and take advantage of whatever features and products it offers. That was the biggest seller for us.”

This call intercept feature proved popular with MetroPCS customers because it provided a convenient, intuitive, self-service option that frequently met their needs. When it wasn’t, the app seamlessly - and frictionlessly - connected them to the IVR.

“With the IVR and My Metro application, we have a reduced amount of calls into our call center, which is pretty much hitting our bottom line in a very positive manner,” Moore says.

Today, most self-service customer experiences aren’t frictionless. That means implementing a frictionless strategy now is an opportunity to wow customers to the point that it becomes a powerful market differentiator.

Intrigued? Meet Nina - an innovative new solution from Nuance that gives enterprises a simple way to implement frictionless customer service.

via http://www.speechtechnologygroup.com/speech-blog - Multi channel contact center and speech recognition and how it transforms into a smooth customer service experience… If you haven’t heard the term “frictionless” yet, it’s time to add it to your customer service lexicon. The skyrocketing amount of inbound calls from mobile phones is a major reason. ...

Can voice recognition technology turn more people into bloggers?

Using speech recognition for dictation can take some time getting used to it, but the rewards can huge…. 

Voice Recognition

Note: This post was transcribed using an Android voice recorder sent via email. Total edit time: 3 minutes.

I was speaking to a friend today who had a very interesting concept that I thought he should share. I asked him if he had a blog and he told me that he did not. When I asked him why he didn’t he told me that he’s okay with speaking about a subject but putting it “on paper” doesn’t work.

My first thought as an old school journalist was to use a tape recorder. Transcribing later is an easy option if you could speak it first and then type it later. Then I remembered that Google and other companies have excellent voice recognition technology that can transcribe with a pretty high level of accuracy. With voice recognition software people who are not able to put their words on paper could easily write there stories and articles by saying them.

I wanted to test that theory out so I decided to write a blog post straight through my Android phone. It was annoying because I could only do one or two sentences at a time. The flow wasn’t what I was used to when typing. But for someone who doesn’t I blog anyway, I could see how this would still be better than not blogging at all.

Imagine if everyone had a blog. In many ways hundreds of millions of people already do through their social networks. There is likely “voice blogging” technology already available that I simply haven’t heard of or tools that allow people to transcribe directly to their blogs, but it’s definitely not mainstream yet. It should be.


via http://www.speechtechnologygroup.com/speech-blog - Using speech recognition for dictation can take some time getting used to it, but the rewards can huge….  Note: This post was transcribed using an Android voice recorder sent via email. Total edit time: 3 minutes. I was speaking to a friend today who had a very interesting concept that I thought he ...

Nuance Quarterly Profit Beats, But Apple Siri Voice Technology Firm’s Sales Miss NUAN

Based on the latest quarterly numbers from Nuance, speech recognition technology is truly on the rise. Interesting to note us the increased pricing for their cloud-based technology..…

Nuance Communications () early Tuesday reported fiscal Q3 earnings and sales that beat Wall Street’s view, but shares were down 1.4%.

The provider of speech recognition technology used in devices such as the Apple () iPhone reported earnings minus special items of 45 cents a share, up 29% from the year-ago quarter and above consensus estimates of 40 cents. It was its sixth quarter in a row of double-digit growth.

Non-GAAP revenue for the quarter ended June 30 rose 30% to $448.2 million, and includes $16.5 million in revenue lost to accounting treatment in conjunction with acquisitions. Analysts had expected non-GAAP revenue of $439.8 million, according to Thomson Reuters.

Nuance technology powers the Siri voice recognition feature in the iPhone. In its mobile and consumer segment, Nuance reported revenue of $132.4 million, up 42%. New customers signed in the quarter included HTC, Samsung, LG and Google’s () Motorola unit. New customers in the auto field included Nissan (), Toyota () and Volkswagen.

“We were pleased to see a strong performance in our mobile and consumer business, led by mobile phones, automobiles, televisions and other consumer electronics, as well as continued momentum in our health care business,” Tom Beaudoin, chief financial officer for Nuance, said in the company’s earnings release.

In its health care business, Nuance said revenue rose 32% to $184.5 million.

Nuance said customer interest in voice applications “is increasing rapidly.” New “virtual assistant capabilities” resulted in handset, TV and automobile bookings and design wins, it said.

Increased license fees for access to cloud-based services also drove revenue, said the company. It said this all offset lower revenue for its Dragon voice recognition software product ahead of last month’s launch of the new Dragon NaturallySpeaking 12


via http://www.speechtechnologygroup.com/speech-blog - Based on the latest quarterly numbers from Nuance, speech recognition technology is truly on the rise. Interesting to note us the increased pricing for their cloud-based technology..… Nuance Communications () early Tuesday reported fiscal Q3 earnings and sales that beat Wall Street’s view, but share ...

Google Now Takes On Siri Without Much Ado -

The Google knowledge graph is one of the key elements for better speech recognition performance.…

Even as Apple’s Siri was touted as the most able competitor to Google Search, the search giant launched Google Now at the recently-held I/O Conference which seems to have taken over its competitor very quietly but firmly.

As praises for the new app continue to pour in, gradually news of its amazing performance is filtering in. The USP of the application seems to be its ability to function as a digital assistant without much tutoring.

Powered by the Google Knowledge Graph, the tool compiles information from a host of sources and measures relationships between data. A report published in the Search Engine Journal cites how Google Knowledge is made up of over 500 million entities and 3.5 billion relational facts.

With Knowledge Graph being central to the search function, Google Now can provide more accurate information. And with Google Now being weaved into Android 4.1 aka Jelly Bean and capable of being extracted and ported into former versions of Android, including 4.0 Ice Cream Sandwich, more users are likely to check out the application and be wowed by its performance.

With Google Now also having access to the handset’s GPS information, it can figure out the areas where you spend most of your time. This apart, the app provides information pertaining to weather, traffic, appointments, travel, flights, public transit, places and sports. The application with built-in intuitive algorithm can automatically display relevant information on sensing a need without user intervention. This comes from data collected through search function over a period of time.

Follow us

Ably supported by Knowledge Graph, the application also stretches the search function to provide relevant information to the users. For instance, if the user searches for information on reaching a coffee shop, the app will show up the closest route to reach the destination and also information about the traffic and the time required to reach the spot.

The voice-powered application may not be available on iPhones but definitely it has taken on Siri. It is known that Apple will not rest quiet until it has introduced enhancements in Siri as featured in the article published in Business Insider but in real-time, Google Now has already made its mark.

With Jelly Bean scheduled to debut mid-July, those eager to check out the app can extract it from developer version of Jelly Bean found in the Android website and play with the app.

As for Android Gingerbread users, well, they have to wait till Google releases updates. It may take a while before Gingerbread users can fully leverage Google Now. The app can be extracted and ported to all devices running rooted Android 4.0, which is well elaborated in the Tech 2 article.


via http://www.speechtechnologygroup.com/speech-blog - The Google knowledge graph is one of the key elements for better speech recognition performance.… Even as Apple’s Siri was touted as the most able competitor to Google Search, the search giant launched Google Now at the recently-held I/O Conference which seems to have taken over its competitor very ...