voice recognition
Latest
VoiceUtils makes your iPhone 4S wish into a Siri command (video)
In the event you haven't tired of Siri hacks, here comes yet another unintended use of the ole robo-handmaiden. This time, however, her jailbroken powers of automation are strictly for vanilla iOS purposes, so you won't find any demonstrations of car stereo or TV channel changing here. Instead, recently liberated iPhone 4S owners can look forward to a software package called VoiceUtils, available through Cydia, that allows Cupertino's best gal to open first- and third-party apps, unlock your phone (barring password protection) and even reboot. See? It's not exactly the most exciting exploit of Apple's much-touted software, but it is resoundingly practical. If you haven't taken a swig of greenpois0n's Absinthe just yet and are keen to extend your iDevice's voice recognition functionality, now might be the time to drink deeply.
Joseph Volpe01.23.2012Intel partnering with Nuance to bring voice recognition to Ultrabooks
So far in the last hour, we've learned that future Ultrabooks will have NFC, possibly larger screens and touchscreens (maybe even touch-enabled palm rests). Well, we've got one more marquee feature to add to the list: Intel just announced that it's partnering with Nuance to bring voice recognition to Ultrabooks. And it sounds like Intel's vision is comprehensive: the company envisions consumers being able to launch applications, compose emails, update social networks and control media playback. During the keynote, Intel PC client head Mooly Eden even said he would one day like to speak to the computer and have this words appear in a different language. Will that be a feature in the 1.0 product? We'll have to see when it starts hitting Ultrabooks later this year. Billy Steele contributed to this report.
Dana Wollman01.09.2012LG waves its wand, unveils Magic Remote for Cinema 3D sets
LG whipped out the magic wand at CES this morning, with the announcement of an enhanced Magic Remote. With this new tool, users will be able to control their Cinema 3D Smart TVs with an expanded set of functions, including voice recognition, a "wheel" function, "magic" gestures and pointing. Expanding beyond the realm of simple push-button functionality, the Magic Remote's voice recognition capabilities allow viewers to enter text and other commands without even lifting a finger, while its wheel, perched at the center of the device, allows them to seamlessly scroll up and down their TVs as they would on a PC. Alternatively, users could simply point the Remote at their displays to move their onscreen cursors around the screen, or input gesture commands to control their Smart TVs with their arms or wrists. The device also features a dedicated button that allows users to instantly convert 2D to 3D, and can be used to control set-top boxes, as well. No word yet on pricing or availability, but you can head past the break for more details in the full PR.
Amar Toor01.09.2012Nuance's Dragon TV offers voice recognition platform for connected televisions
Nuance isn't skipping a beat in Las Vegas, as the speech recognition company is busy launching a brand new platform that focuses on bringing its technology to connected TVs. According to the company, the platform, called Dragon TV, can be used to build customized voice and touch apps that run on televisions, set-top boxes, phones and tablets. Essentially, the technology will allow the viewer to use their voice to conduct searches, send messages and access plenty of other features, and mobile devices can be used to act as a remote to control the TV. Nuance's new platform is available now for OEMs, developers and operators to take advantage of, and supports Linux, Android and iOS as well as all major TV, set-top box and remote control standards. Head past the break for the full press release, and make your way to the company's site below to get more details.
Brad Molen01.09.2012Nuance gobbles up Vlingo, yearns to transcribe its own announcement
Apparently, if you can't (legally) beat them, you buy them. Such is the thinking over at Nuance, who has decided to acquire its competitor and former courtroom dance partner, Vlingo. Should make for some nice additions to the former's voice recognition tubes -- technology which powers everything from Apple's Siri, Dragon dictation and even various autos. No indications as to how many greenbacks exchanged hands, but the newlyweds were happy to boast their "complementary research and development efforts" will result in a company "stronger together than alone." We'll have to see about that. PR after the break.
Dante Cesa12.21.2011Android 4.0 Ice Cream Sandwich review
The next version of each smartphone's operating system is always the best. We impatiently wait for the latest and greatest firmware to come around, expecting it to liberate us from the shackles of last year's code and features that haven't shown up yet. This happens incessantly with Google's Android OS, and version 4.0 -- unveiled at this year's I/O conference in May -- is no different. Known as Ice Cream Sandwich (referred to henceforth as ICS), the last word in the title indicates the merging of Gingerbread, the most recent phone platform, and Honeycomb, the version optimized for use on tablets. We knew this much, but were otherwise left with conjecture as to how the company planned to accomplish such a feat -- and what else the new iteration had in store. Which devices will get Ice Cream Sandwich? Hands-on screenshot gallery Galaxy Nexus and ICS roundup But now the time of reckoning is upon us, and the Samsung Galaxy Nexus -- Android 4.0's mother ship -- is slowly spreading across the globe, its users being treated to this year's smartphone dessert. ICS is one of the largest and most important upgrades we've witnessed from Android since its humble beginnings, making a huge change in user experience as well as a massive number of bullet points on the list of features. Now that we've had the opportunity to take it for a spin, where does it stand in the ranks of mobile operating systems? Follow us beneath as we dig into the layers of this sweet sandwich.
Brad Molen12.01.2011Developer teases voice control of Zune, using PC and Windows Phone (video)
The great thinkers of the world have long known a secret that we're now happy to disclose: it's not necessity that's the mother invention, but rather laziness. Fortunately, expending a great deal of effort on a project -- simply to perform a task effortlessly -- sometimes brings very cool results. A concept app known as ZuneVoice easily passes muster in this realm, which is used to control Zune software on the PC with only a standard microphone and spoken commands. As you can see in the demo video, its creator, keyboardp, is able to play individual songs, issue commands such a "pause" or "next song", and even display full-screen music videos from YouTube. The developer even crafted an app for his Lumia 800 known as PhoneZune, which serves as a remote control for times when he's away from the box. Neither application is yet publicly available, though feedback is welcome. Next, we're told to expect Kinect integration. Perhaps one day, these gems will see the light of day.
Zachary Lutz11.29.2011Jailbroken iOS 5 devices get Siri0us, tap into Nuance's dictation servers (video) (update)
Sure, it's leaps and bounds away from all the parlor tricks that Siri is able to perform, but now, jailbroken iPhone 4, iPhone 3GS and iPod Touch devices -- that have been upgraded to iOS 5 -- may access the dictation portion of Siri's prowess. Thanks to Siri0us, the free app available through Cydia, users will gain the option to speak messages and search queries rather than type them, which could be a huge time saver -- unless there's a series of mistakes, anyway. Rather than accessing Apple's own system, the app works by tapping into Nuance's Dragon Go servers for speech recognition. Rather subversive, don't you think? If you'd like to get in on the fun (before Nuance breaks up the party), just check the video following the break. Update: Well, who didn't see this one coming? Nuance has pulled the rug out from under Siri0us, and the app has been yanked from Cydia while the developer searches for another speech recognition server. Happy hunting, dude.
Zachary Lutz11.29.2011Hallooo computarrrr! Siri not yet compatible with Scottish accents
Let's open with a reality check: Siri is still in beta. Apple's new voice recognition service is just getting started, and many of us have found out the hard way that Apple's definition of "beta" is closer to what many other developers would call "alpha." That having been said, The Daily Mail's reports of Scottish accents flummoxing Siri still had us trading Sean Connery jokes back and forth in the TUAW newsroom. According to The Daily Mail, numerous videos have surfaced of Scottish users trying (and failing) to interact with Siri. One tells Siri, "Gonnae no dae that," which Siri interprets as "Going Akila." Siri interprets a Scot's charming "Can you dance with me?" as "Can you dutch women?" Siri's confusion doesn't stop at Scottish accents, of course. My father's wife is from the Philippines, and Siri has difficulty understanding her. I'm quite curious to see how Siri responds to me; my accent has become a somewhat corrupted melange of Pacific Northwest English and New Zealand English. Apple's more primitive predecessor to Siri, Voice Control, correctly interprets my commands only about 75 percent of the time. Somewhat predictably, the paper tries to spin this as a disaster for Apple -- "Disgruntled messages have littered gadget websites and forums" according to the Mail. That response comes across as reactionary and a bit unfair, especially since one of the YouTube videos embedded on the Mail's own page (and embedded below) shows Siri reacting to a Scottish accent with rather impressive accuracy. Of course, another video shows a Scot trying to get Siri to "create a reminder" for close to two minutes without success, so the service definitely has some room for improvement. Despite decades of work, voice recognition software is still basically in its infancy. I think my dog probably understands some spoken commands better than Siri does despite all the work that's gone into the software. Then again, my dog is a genius, and Siri has been in public beta for less than two weeks. Give it some time to scale, and eventually I'm sure Siri will far exceed my greyhound's ability to interpret verbal interactions. It may even exceed my abilities someday -- I have a Scottish friend in Christchurch (hallooo Stuarrrrt), and I can understand maybe one out of every five words he says.
Chris Rawson10.27.2011Siri shows up on an iPod Touch, no longer plays favorites in the iOS family
That Siri gal is certainly making the rounds these days. When she's not answering your questions on a 4S, she's showing up on iPads and elder iPhones. Not one to play favorites, Siri's now lending her considerable talents to an iPod touch. Two enterprising young hackers, euwars and rud0lf77, are the ones who put Siri on the iPod, and you can see the results of their labor in the video after the break. Of course, Apple's servers still aren't as friendly as the virtual voice assistant, so Siri's latest cameo remains a silent one -- but some Siri's better than none, right?
Michael Gorman10.25.2011Siri ported to iPad, still getting silent treatment from Apple servers
Developers wasted no time bringing Siri to the iPhone 4, and nine days later, it's been brought to the iPad as well. This version, running on a first-generation jailbroken Apple tablet, suffers from a similar problem as past non-iPhone 4S ports: it's still not talking to Apple's data servers. This means that until devs manage to get voice commands recognized and initiated, the iPad's unofficial virtual assistant will remain effectively gagged.
Mat Smith10.24.2011Android's Andy Rubin is not a fan of Siri
Siri is the talk of the town now that the iPhone 4S is in the hands of over four million customers. There has been a deluge of articles about using Siri, funny phrases it says and even clever hacks that let third-party companies tap into the service. Apple and its fans may be excited by the voice recognition technology, but one of Google's executives is not overly impressed. Speaking in Hong Kong at the AsiaD conference, Google's Android chief, Andy Rubin, was sour on the utility of Siri. Rubin said, I don't believe that your phone should be an assistant. Your phone is a tool for communicating. You shouldn't be communicating with the phone; you should be communicating with somebody on the other side of the phone. Rubin may not look favorably on Siri, but he does give Apple credit for waiting until the technology was mature before rolling it out on the iPhone 4S. He noted, In projecting the future, I think Apple did a good job of figuring out when the technology was ready to be consumer-grade. Though Rubin claims not to be fond of voice recognition on a mobile phone, he does oversee Android's development at Google and has allowed advanced voice recognition features to be built into this mobile OS.
Kelly Hodgkins10.20.2011Siri gets lost internationally, promises to do better next year
The iPhone 4S' Siri integration may be a potential game changer, but she's not quite the world traveler some of us would like her to be. In fact, it seems she's as lost outside of US borders as any unprepared tourist. Looking for a pub in London? Better find a traditional map. Need to know the time of day in Canada? Siri admits she has no idea, go buy a watch. Business search (via Yelp), directions, and traffic data search all appear to be US-only features for now, and Wolfram Alpha only works in English-speaking countries. The automated assistant's international failings aren't too big of a surprise, however -- Apple's own Siri page outs the service as a beta, noting that some features may vary by area. Stuck with sub-par international support? Sit tight, it's coming: Apple's Siri FAQ states that additional language support (including Japanese, Chinese, Korean, Italian and Spanish), maps and local search content are set to go international in 2012. Update: Wolfram Alpha works outside the US in English speaking countries, thanks to everyone in the comments for the clarification.
Sean Buckley10.15.2011Siri ported to an iPhone 4, old phone learns a new trick (Update: Better performance!)
Apple's iPhone 4 may not have the fancy dual core CPU of its successor, but thanks to the efforts of developer Steven Troughton-Smith and the folks at 9to5 Mac, it may soon have Siri. The port of the sultry voice assistant was accomplished by using the 4S Siri and Springboard files, and some serious elbow grease, no doubt. As you can see in the video below, it's far from perfect, but it can recognize spoken commands without issue. Currently, the hack is missing an iPhone 4 GPU driver that keeps things running buttery smooth on the elder phone, and Cupertino won't authenticate Siri's commands coming from it either. So, it isn't quite ready for primetime, but it should only be a matter of time before all you iPhone 4 owners can tell Siri what to do, too. Update: And in the space of just a few hours, Mr. Troughton-Smith has already managed to improve performance of the app on the iPhone 4 significantly, although Apple's servers are still unreachable. Check out a newer YouTube video showing off some seriously smooth scrolling action after the break. [Thanks, Ramzi]
Michael Gorman10.15.2011Google Translate for Android gets v2.2 update, adds more language support for speech-to-speech
Let the voice recognition battle begin! Siri's already thrown the first punch in the soon-to-be dicey (albeit very consumer friendly) voice service wars, but don't count Google out just yet. The folks over at Mountain View are doing their best to strike back, adding extra functionality to the Google Translate app for Android. So, what's new in this version 2.2 upgrade? The company's expanded the app's previously limited speech-to-speech repertoire with support for an additional 12 languages, accessible via the alpha-tagged Conversation Mode. And to prevent you from any awkward (and potentially hilarious) moments of unintended translation, there's now a post-edit ability to keep those two-way foreign exchanges PG. Alright, so it's not quite the hands-free, HAL-like cyber assistant update we'd like it to be, but there's always Ice Cream Sandwich for that -- we hope. In the meantime, go ahead and hit up the source below to test out the experimental wares for yourself or check out a video demo of Conversation Mode after the break.
Joseph Volpe10.13.2011Microsoft reportedly preparing Silverlight-like app framework ahead of Xbox Live update
Earlier this month, Microsoft announced a new slate of Xbox Live partnerships with Verizon, Comcast, and a host of other content providers. Now, the company has unveiled new details about the code upon which these new apps will run. Sources close to the situation tell GigaOM that the new framework, code-named "Lakeview," will be based on Silverlight, but will also bring a few new features from Xbox Kinect, including voice recognition and gesture-based controls. More intriguing, perhaps, are insider claims that Microsoft's new content partners stream video using Apple's HTTP Live Streaming, rather than Redmond's Smooth Streaming. GigaOM's sources went on to say that Microsoft has been introducing major changes to the platform over the past few weeks, in the hopes of having it ready for third-party developers once the Xbox Live update rolls out. Spokespersons for Xbox and Silverlight said they have "nothing to announce" about the new framework, though GigaOM reports that Redmond is aiming to release the update on Black Friday.
Amar Toor10.10.2011Dragon Go for iPhone gets smarter
Dragon Go!, the all-purpose voice recognition search app from Nuance, is getting a significant upgrade today. In fact, it's almost a preview of some of the functionality we suspect will be in iOS5. The free app lets you speak conversationally with your iPhone, iPod touch or iPad. Say things like "What's the best steakhouse in Kansas City", or "Find me some pictures of Lady Gaga", and the app will parse what you said and nearly always return useable results. The update, which should hit the App Store today, adds many more options, including the ability to launch popular movie and TV streaming services; get direct access to more of the most popular names in mobile content, like Spotify; get answers to the toughest of questions from Wolfram|Alpha and Ask.com; and, find friends on Google+. I tried some of the new functions, and was impressed. For instance, I said "Watch Mad Men on Netflix," and Dragon Go initiated a Google search. When I clicked on the resulting link, my Netflix app launched and the show started. I also successfully searched TUAW for articles and had it define words using Dictionary.com. For apps that require a login, you'll have to set up Dragon Go! to link with those apps, but that's not a difficult task. Vlad Sejnoha, chief technology officer at Nuance said "We're deeply invested in continuing to evolve Dragon Go! with new features, more content providers and richer app integration, and ultimately opening new doors for the consumer mobile destination experience. This is another step towards the mobile semantic web, and we've just gotten started." These new services join Google, Bing, Yahoo, Wikipedia, Twitter, YouTube and many others that were already built into the app. I find Dragon Go! and Siri (now owned by Apple) to be two of the best demos for the iPhone around. If you already have Dragon Go! you should see the update today. If you don't have it, download it and impress yourself and your friends. %Gallery-135166%
Mel Martin09.29.2011Xbox Live Fall 2011 Dashboard update preview: Bing search, voice control, and a Metro overhaul
Autumn is fast approaching -- and you know what that means: it's round about time for an Xbox Dashboard update. Sure, we got a peek of Microsoft's upcoming harvest back at E3, but the good folks from Redmond invited us to take a closer look at what they're calling the "most significant update to the Dashboard since NXE." Senior project Manager Terry Ferrell was on-site to walk us through an early engineering beta and show us how an updated Metro UI, Bing search and deeper Kinect integration is going to change the way folks manage their entertainment content.
Sean Buckley09.09.2011New York Times' magic mirror helps you get dressed, puts the 'wall' in 'paywall' (video)
Forget crosswords and Krugman, because the New York Times has created a new bathroom companion that looks infinitely more entertaining than either of them. Like some of its Snow White-style predecessors, the Times' "magic mirror" prototype uses Microsoft Kinect to detect and follow your movements, while deploying voice recognition technology to execute your commands. With this omniscient slab affixed to your wall, you can surf the web, flip through your wardrobe and send reassuring e-mails to your teenage daughter, whom you should have driven to school a good 30 minutes ago. An RFID reader, meanwhile, can recognize tagged pharmaceuticals or other products, allowing you to instantly access information on your prescription meds by placing them in front of the reflective LCD. You could also use the mirror to browse through the Times' full slate of articles and video content, meaning you can read about extravagant weekend getaways and urban gentrification from the standing comfort of your sink. Unfortunately for all mankind, the magic mirror is still in the prototype phase and the NYT's Research & Development Group has yet to offer a timetable for its release -- but you can see it in action for yourself, after the break.
Amar Toor09.05.2011Apple patent application imagines iPhones that learn the sweet sound of your voice
Button-loathing Apple really wants people to stop dirtying its devices with sticky fingerprints. That's why it's applied for a patent that should improve the frustrating experience of using iOS's voice control -- precisely the kind of update we've been awaiting since Apple bought Siri last year. With the help of a technology billed as "User profiling for voice input processing," your device would identify your voice, check against a library of words associated with you without having to trawl through its entire dictionary. We just hope Apple doesn't do away with physical inputs entirely -- we'd hate to broadcast to the world all the guilty pleasures we have loaded on our iPods.
Daniel Cooper08.26.2011