We at Speech Tech Blog wish you and yours a Happy Thanksgiving.

In the spirit of Thanksgiving, we offer you a humble gift: The Talking Turkey Plush Toy.  Just squeeze this this little fellow and hear him say “gobble, gobble, gobble” which, in Turkey-Language, translates roughly to “help, don’t kill me, please.”

And of course it just wouldn’t be Thanksgiving at Speech Technology without an extra helping of my editor’s famous IVRice Pudding, the recipe for which can be found below:

IVRice Pudding Recipe

Ingredients
* 2 1/2 cups (600 ml) of whole milk
* 1/3 cup (66 grams) of long or short grain white rice
* 1/8 teaspoon salt
* 1 egg
* 1/4 cup (50 grams) dark brown sugar
* 1 teaspoon of pure vanilla extract
* 1/4 teaspoon of ground cinnamon
* 1/3 cup (40 grams) raisins

Method
1. In a medium heavy bottomed saucepan, combine milk, rice and salt and bring to a boil over high heat. Reduce heat to low and simmer until the rice is tender, about 20 minutes. Stir frequently to prevent the rice from sticking to the bottom of the pan.
2. In a small mixing bowl, whisk together egg and brown sugar until well mixed. Add a half cup of the rice mixture - a tablespoon at a time - beating to incorporate.
3. Add egg mixture back into the saucepan of rice and milk and stir, on low heat, for 10 minutes or so, until thickened. Be careful not to have the mixture come to a boil at this point. Stir in the vanilla. Remove from heat and stir in the raisins and cinnamon.

Serve warm or cold.  Serves 2-3.

Next Thanksgiving: I promise to reveal the secret recipe for Nuance’s Mouthwatering Cornbread STTuffing!

We’ll see you on Monday!  Happy Thanksgiving Everyone!!!!

Ever feel like manually pressing the buttons on that remote control is too much work?

Me too.

Well, fear not, Gentle Reader: Things are about to get a whole lot easier.

Oki Japan and a team from Waseda University are working on a speech recognition powered remote control that pulls a single target voice from background noise and the voices of other speakers.

Apparently, the new remote relies on four embedded microphones and “a proprietary algorithm for voice frequency analysis [that] detects talking that originates from directly in front of the device and automatically separates this out from other sounds being picked up by the microphones.”

Here are some links that are sadly not speech enabled and will have to be clicked:

Link 1

Link 2

Computer and Video Game Publisher Ubisoft has released Tom Clancy’s End War, which is controlled by Speech Recognition Technology.

Well, sort of.

From a review on bit-tech.net:

“The developer, Ubisoft Shanghai, has cheated a little though.  Rather than use the software to recognise actual words, it is used to recognise the sounds that make up those words – the system used looks out for particular sounds that go to make up a word. This cunningly gets around the need for a large amount of training generally required with standard speech recognition software, and also gets around the problem of accents: the main sounds of a word are essentially the same, regardless of your accent. The problem has been simplified even further by only recognising a handful of words – about eighty or ninety, according to Ubisoft.”

Below, check out a couple of stories about Tom Clancy’s End War:

Link 1

Link 2

In what could be another step toward a future in which humans are enslaved to vindictive, super-intelligent robot masters, Nintendo has released a multimodal “interactive cooking coach” for Nintendo DS.

Personal Trainer: Cooking features the electronic “DS Chef,” voice-recognition technology, two hundred forty recipes from around the world, and video cooking demonstrations.

The product can teach aspiring chefs basic cooking techniques and boasts a touch screen interface that allows you to check ingredients on an electronic shopping list that can be carried to the grocery store.

Personal Trainer: Cooking also lets users search recipes based on ingredients, calorie content, or cooking time.

And, if a your hands are “accidentally” scaled with red hot cooking oil and therefore unable to poke at the touch screen, the voice recognition feature allows users to tell the DS Chef–billed as a “friendly electronic cooking instructor”–to move on to the next step or repeat the last instructions.

I don’t know about you, but Sarah Connor and I are hunkering down in our bunker, eating canned beans, and never learning to cook.

Now that Google has released Voice Search for it’s Google Mobile App for iPhone, reports of problems with the speech recognition are being reported.

Evidently, Voice Search works really well in North America, but is posing some challenges for users Britain.

For example, one user spoke a search for “fish,” only to retrieve the search results for “sex.”

Of course, we at Speech Tech Blog can relate.  Every time I do any type of web search, I only get search results about sex.  But maybe that’s just me.

Below are a number of stories about similar problems with Voice Search:

Link 1

Link 2

Link 3

Link 4

As promised, the Speech Technology News Feature about Google’s new voice search for iPhone.

A few days ago, we brought you this post about Google’s new voice search for the iPhone.

And as expected, Google is being typically reticent about this development.

But fear not, gentle reader: We at Speech Tech Blog are not done yet.

In fact, as soon as I am done with this blog post, I have a strongly worded email to send to a certain massively-powerful-and-ridiculously-secretive-company.  A company that has access to all my personal information; a company that has a record of every Internet search I have ever made; a company that will, for obvious reasons. remain nameless.

But in the meantime, check out the following links for more information on Google’s voice search for iPhone.

Official Google Blog

Official Google Mobile Blog

Google Press Center

Today, we at Speech Tech Blog came across a strange and frightening video on YouTube.

It appears to be security tape footage of a very highly strung businessman having a meltdown in a hotel lobby.  He yells, punches walls, throws things, has a fit, is tackled by security.

At the end of the video, a domain name flashes across the screen: www.donthaveameltdown.com.  Go ahead, click the link or type in domain name.  It will bring you here.

Apparently, the entire thing is an advertisement for Cisco’s Unified Communications Solution.  And for that, Cisco receives High Marks from Speech Tech Blog.

The video is below:

According to a story in today’s New York Times, Google researchers have added voice recognition to their search software for the iPhone.

According to The Times, the new application will be free and available via the iTunes store.  Basically, users will be able to simply speak searches into their iPhone.  The results will then be displayed on their phone and include local information when applicable via iPhone features that detrmine user location.

We expect an announcement about this from Google, so keep your eyes peeled for a Speech Technology News Feature in the near future.

In the meantime, John Markoff’s New York Times story can be found here.

Dear Readers:

I am writing with a Major Announcement:  We here at Speech Technology and Speech Tech Blog are pregnant.

Soon, there will be another member of our ultra elite squad.  We will, of course, keep you posted as to his ETA, which is, as of today, scheduled for sometime in December.

Think of him as a living, breathing, blogging Festivus Gift!

That is all.

Regards,

Speech Tech Blog