Microsoft has had speech recognition in Windows Phone since it first debuted, but it looks like the company is preparing a fairly significant upgrade. In a leaked video from Microsoft’s TechFest earlier this month, the research team demonstrates speech recognition speed and accuracy improvements, and a new “streaming mode” that can be enabled to allow Windows Phone users to search while they speak.
It looks similar to Android’s latest implementation, but Bing’s method goes one step further by adding the ability to produce inline search results while you’re still talking. Microsoft doesn’t offer up any promises on when this will be delivered, and it could still be a research project, but the company is preparing a Windows Phone Blue…
Video from Automation Fair 2012: Martha Dickey from FIRST (For Inspiration and Recognition of Science and Technology) describes the competition in which young people discover how interesting and rewarding it is to be engineers and researchers. Teams are challenged to solve a common problem in a six-week timeframe using a standard kit of parts and a common set of rules to build robotic solutions. Students are rewarded for design excellence, team spirit, gracious professionalism and maturity, and the ability to overcome obstacles. Learn more at www.facebook.com/FIRSTRobotics.Related Posts:
Samsung teased a Series 7 all-in-one running Windows 8 — on a 10-point touch display — at Computex in June, and today the machine gets official with pricing and specs. The Series 7 will be available in 23- and 27-inch flavors, both of which run Microsoft’s latest OS on a 1080p screen. The setup includes a redesigned keyboard, which is small enough to tuck under the display’s metal stand, and the AIOs will support gesture recognition. The 23-inch Series 7 costs $ 1,099 and runs a Core i5 CPU with 6GB of RAM, 1TB of storage and Intel Graphics 4000. The 27-inch model offers a Core i7 processor, 8GB of RAM, 1TB of storage and a 16GB graphics card, all for $ 1,699.
In addition to refreshing its Series 7 machines, Samsung is introducing the 21.5-inch Series 5 all-in-one, which it describes as a “kitchen-style PC.” Its legs are on either end of the display, leaving room to stow the keyboard under the screen and freeing up your desk (or counter) space. The Series 5 will go for $ 749, and it includes a Core i3 processor, 4GB of RAM and 500GB of storage. All three AIOs will go on sale October 26th. You know the drill — head past the break for our hands-on photos.
Filed under: Household
Newark, NJ-based iSpeech may be best known for its DriveSafe.ly app and the mobile SDK it launched last summer, but now the company plans to bring its speech expertise to a different environment — your home.
Today iSpeech announced the launch of a new voice recognition platform called (what else?) iSpeech Home for hardware manufacturers and OEMs to integrate into their household gadgetry.
“Speech is the user interface of the future,” said iSpeech COO Yaron Oren, who was quick to cite Siri as an influence.
Oren and the iSpeech team seem to take umbrage with the complex and confusing interfaces that have a habit of appearing in household electronics. Should iSpeech’s vision come to pass, users will eventually be able to issue verbal commands like “record ‘Doctor Who’ season premiere” to their televisions, or “turn off the lights in the dining room” to their home automation system.
Sure, voice controlled home automation isn’t exactly a new concept, as more than a few companies (not to mention plenty of devoted hobbyists) have put together their own solutions in recent years. The difference here is that iSpeech’s platform is capable of capturing and interpreting more natural voice commands, as opposed to simply relying on a preset list.
It sounds like potentially wonderful stuff, but as usual, it all comes down to adoption. If the voice recognition platform doesn’t pick up any steam among OEMs and hardware manufacturers, then there goes the ball game. That said, iSpeech already seems to have made some progress on that front. According to Oren, the company has already met with nearly a dozen companies (though he wouldn’t specify which ones) about iSpeech Home, all of whom are in “various stages of evaluation.”
Given that major consumer electronics players like Samsung and its eternal rival LG have pushed to make the living room smarter with a host of voice-recognizing televisions, it comes as little surprise that iSpeech’s platform has gotten the most attention from other television manufacturers. Makers of thermostats, security systems, household appliances have also expressed their interest in the platform, and with any luck we’ll soon be chatting with our dishwashers with wreckless abandon. Be prepared for a bit of a wait though, as Oren expects to have iSpeech Home-friendly devices trickle into the market within the next 6-12 months.Related Posts:
1pcs smart Car Robot Plastic Tire Wheel + DC Gear Motor 3v 5v 6v for avr $1.04 (2 Bids)End Date: Thursday Jun-20-2013 2:10:05 PDTBid now | Add to watch list OWI OWI-535 ROBOTIC ARM EDGE KIT- Non Solder NEW!!! $45.71End Date: Thursday Jun-20-2013 19:32:22 PDTBuy It Now for only: $45.71Buy It Now | Add to watch listRelated Posts:
With Smart Interaction, Samsung is literally changing how you can interact with the TV. You will be able to ‘listen, see and do’ what you want, without ever touching a remote control. The TV will be even more intuitive to your needs. You will be able to interact with your Samsung Smart TVs just like we interact with people, using voice, gestures and face. Take a look. The face recognition seamlessly logs in each family member to their own Smart Hub profile. You will see your apps. Your family members will see theirs. That’s just a taste of what is possible with our Smart Interaction technology. What’s more, we will open our APIs to developers so they can unleash their creativity and build apps that use motion control, voice control and face recognition. Connect with Samsung USA: www.facebook.com www.twitter.com gplus.to Video Rating: 4 / 5Related Posts:
1pcs smart Car Robot Plastic Tire Wheel + DC Gear Motor 3v 5v 6v for avr $1.04 (2 Bids)End Date: Thursday Jun-20-2013 2:10:05 PDTBid now | Add to watch list OWI OWI-535 ROBOTIC ARM EDGE KIT- Non Solder NEW!!! $45.71End Date: Thursday Jun-20-2013 19:32:22 PDTBuy It Now for only: $45.71Buy It Now | Add to watch list Depco Inc. ER2U Robot Arm $112.50 (13 Bids)End Date: Thursday Jun-20-2013 7:49:27 PDTBid now | Add to watch listRelated Posts:
It’s that pop song again — you know, the one that forces you to flip the radio to anything else. But still, you’re dying to know what it’s called, if only to avoid hearing it ever again. Boom Boom? Heartbeat? Shazam! Super Bass, by Nicki Minaj. If you haven’t used Shazam, chances are you know someone that does, and often. Gracenote’s new Automatic Content Recognition (ACR) technology takes that same concept and applies it to TV shows and movies, and it’s coming soon to a smartphone or tablet near you. A yet-to-be-named app will let your device “listen” to whatever you’re watching, identifying TV shows and movies based on dialogue or the soundtrack, then displaying a variety of info about whatever’s on screen. Gracenote is also expanding its audio offerings, showing off both HABU and MoodGrid, which are mood-based music curation services for mobile devices and in-car systems, respectively. Software groups songs based on emotional themes, then plays them back depending on your selected mood. Happy? Sad? Intrigued? We’ll need to wait until CES for the full scoop from Gracenote.
Gallery: Gracenote ACR TV recognition
Permalink | | Email this | CommentsRelated Posts:
There’s seemingly no end to the clever things that people can do with a little know-how and a Kinect camera, and now it seems like the machine learning enthusiasts at ChaLearn want to use the Xbox accessory to change the way computers deal with gesture controls.
In short, they’re challenging the world’s data tinkerers to develop a learning system that allows a Kinect to recognize physical gestures in one shot.
Why one shot? The way ChaLearn looks at it, if gesture-based control is ever going to become a staple of how we interact with our technology, there can’t be an overly-complex process to define those gestures. What ChaLearn wants teams to accomplish is a way for a gesture to be defined and subsequently recognized after it’s been performed only once. After all, if a human can do it, why shouldn’t a machine be able to?
The competition is being run using Kaggle, the data modelling competition platform that just wrapped up an $ 11 million funding round not long ago. The gesture-learning challenge is one of nearly 30 that Kaggle hosts, which run the gamut from asking users to determine if a car bought at an auction is a lemon to predicting which patients will be admitted to a hospital by parsing claims data.
As you can imagine, only the hardiest of data crunchers need apply. Competitors are given a Kinect’s RGB video and spatial depth data of a subject performing a series of gestures, and are tasked with finding a way to predict the identity of those gestures as defined in a separate “truth file.”
Here’s a brief snippet from the challenge’s description that should give you an idea of the sort of work involved:
For each video, you provide an ordered list of labels R corresponding to the recognized gestures. We compare this list to the corresponding list of labels T in the prescribed list of gestures that the user had to play. These are the “true” gesture labels (provided that the users did not make mistakes). We compute the so-called Levenshtein distance L(R, T), that is the minimum number of edit operations (substitution, insertion, or deletion) that one has to perform to go from R to T (or vice versa). The Levenhstein distance is also know as “edit distance”.
It’s going to be a lot of work even if you’ve boned up on your Levenhstein distances, but the winning teams will be handsomely rewarded. Thanks to the prominent use of Kinects in the challenge, Microsoft has thrown the competition their support in the form of $ 10,000 to be split among the top three teams. What’s more, if Microsoft is fond of your solution, they have the option of licensing your work in exchange for a payout as large as $ 100,000.
The solution development period starts now and runs though April 6, 2012, and the last chance to upload your learning solution comes 4 days after that. Better get cracking if you want to take home that prize (oh, and potentially change the course of human-computer interaction).
Continue reading Bose’s OE2 and OE2i on-ear headphones pack brand recognition, little else
PermalinkRelated Posts: | | Email this | Comments