I do have to say the voice recognition seems to be on the ball from the video; it is actually impressive when Sascha, the German chap in the vid, butchers the pronunciation of "Kanye West" (around 3:46 in video) and the computer lady still understands it and plays a song.

But why do you need this voice functionality baked into an all-in-one with such a big screen where you are bound to have your hands somewhat free to control the touchscreen? Though I guess, it could be useful for when in a kitchen before cooking up a MacGyver Chef creation. [Netbook News]

According to Asus CEO Jerry Shen:

...internally we have one team dedicated to studying voice recognition. Touch and gesture input is universal, whereas language is not universal...The first Eee PC or Eee Top products implementing voice-recognition and features will be ready by Q3/Q4 2009 – with our dedicated development team working with third parties in both Japan and the US and reporting directly to me. So this is something we will see very soon...

Hmm, it's a fine idea for home (if it works). But I'd rather not be talking to my netbook at Starbucks. [TechRadar]

It works by recording a soundbite, uploading it to Google's servers, which will crunch the data and return an answer "within seconds on a fast wireless network". Saul compared the function to that offered on Yahoo's, and found Google's to be more accurate, but still return junk results sometimes. AT&T and Microsoft also have handset voice recognition beyond simple dialing that many other phones offer. The app will be free and might be available to download as soon as Friday. [NYT]

Related: Gizmodo's Essential Iphone Apps

Press a button to start recording and say what you're searching for—the name of a business, for instance, and Tellme will search and locate matches in your vicinity. Great for when you can't stop and type in locations manually. Unfortunately the app doesn't appear to access your contacts for good ol' standard voice-dialing (at least in the BlackBerry version), so that's something we'll still have to wait for. Along with mobile MS Office for iPhone [Yahoo News/CNET]

• While machines that could accurately reproduce the sound of human speech, such as Wolfgang von Kempelen's talking head, have been around since the late 1700s, no device has been able to learn the syntactical rules necessary for generating conversation.
• Secondly, the act of hearing and interpreting is more difficult to instill in a machine because of the on-the-fly signal processing that would be required. The complexity of the ear allows it to pick up on the most subtle nuances in sound (according to the article, people can distinguish between hot and cold coffee just by hearing it poured into a glass.
• Roger Schank is a philosopher-programmer who has spent his professional live trying to create a conscious computer that not only has a memory, but can also learn. After years in the field, Schank is skeptical it will ever happen. He says replicating idle chatter and the sheer complexity of speech in general is beyond the abilities of current scientists.
• Steven Pinkner, a Harvard cognitive scientist, says that natural speech could rely on the breadth of one's knowledge, which is "extraordinarily difficult" to endow to a computer.
• R&D efforts in speech recognition began in the 1950s and '60s, but researchers are still hung up on the number of ways to communicate the word yes. Speech engineers for Nuance found that Southerners in the U.S. tend to add "sir" or "ma'am" to responses where as Northerners do not. And "Valley Girl" speak tends to make computers interpret declarative statements as questions.
• Finding it difficult to make a computer able to "learn," scientists turned to brute-force computing and algorithms that relied upon mass amounts of data. But in 1969, high-ranking Bell Labs staffer John Pierce wrote that a speech machine that could recognize, but not understand, was utterly pointless.
• The big emphasis on speech recognition has now moved to emotional analysis, which still uses algorithms to estimate a caller's state of mind. Stanford researcher Elizabeth Shriberg says its impossible to compare emotions in acted speech to emotions in real speech. The escalation of anger, for example, happens in smaller, more subtle increments with authentic speech.
• The most promising breakthrough in emotional recognition is an agression detector that has been deployed through out parts of Europe. Sound Intelligence were able to recreate the processes of the inner ear on a computer, which spawned a device that could learn the sounds of different objects in action and identify them. The Dutch city of Groningen has placed this technology in its pubs, where if it detects excessively aggressive speech in the pub, it will alert the nearest police station. But as Seabrook comments, "This is no HAL."
• Other research labs, like the Speech Analysis and Interpretation Laboratory, have turned to facial recognition to glean emotional insight, but have come up dry. "Emotions aren't discrete," lab chief Shrikanth Narayanan told the New Yorker. "They are a continuum, and it isnt clear to any one perceiver where one emotion ends and the other begins." To add insult to injury, there hasn't been any real demand for emotional recognition outside the call center arena.

So while we might not ever see a robot become a Nobel Laureate, there is one lession to be learned from this New Yorker piece — never talk freely while on hold with customer service. Seabrook learned while at B.B.N. Technologies that they still record the call while you're on hold to assess your emotional state. After a profanity-laced tirade, one annoyed caller took a couple of hits from his bong, waited a little longer, and hung up. [The New Yorker]

Although it will offer service, ThePudding isn't trying to claim a piece of the pie that Skype, Vonage and the cable companies have been wrassling over for years. According to the AP, it hopes to "license its speech-recognition service to other companies that use Voice over Internet Protocol." But AP tech writer Peter Svensson had mixed results when testing ThePudding's speech recognition:

"Relevant ads appeared when this reporter talked about restaurants and computers, but the software was oddly insistent that he should seek a career as a social worker, showing multiple ads and links pointing to that field."

It's for real (see update below). Sure will be nice to be able to use speech commands with the iPhone, telling it to call so-and-so on those mic-equipped earbuds while keeping the phone in the pocket.

UPDATE: We got this exclusive info from Chris LeBlanc at VoiceSignal: "It works just like our other apps, so it's speaker independent and needs no training at all to recognize names, numbers and general speech. We will demo the continuous voicemode on the iPhone soon, I've already seen it — and it's nearly ready." Chris has promised us a demo copy, so we'll give you a first look as soon as it arrives. [VoiceSignal]

The system is speaker-independent, so it doesn't need to be trained for each pilot's particular voice or way of speaking. Now this means that backseat drivers can actually have some real power. Let's just hope carmakers aren't tempted to try this shit. – Charlie White

Speech recognition technology allows voice control of aircraft systems [Gizmag]

What happens when a Microsoft employee demos the speech recognition in Windows Vista before it's ready? Check it out for yourselves. It's not a pretty sight.

Our buddies at Jalopnik pointed us to the flakey Windows Vista voice recognition demo shown at a recent event. We tried to record it off of CNBC but our computers melted over the weekend, luckily not in the Dell way.– Jason Chen

Update: Reader Guillermo tells us that the engineer who's "responsible" for the bug that caused the demo meltdown posted an update on his site.

Fun with Vista's speech recognition [Guardian Technology Blog]