Microsoft Debuts Full-Body Controller-less Gaming At E3

At today’s Electronic Entertainment Expo press briefing, Microsoft unveiled Project Natal, a technology that eliminates the controller from gaming on the Xbox 360. In one demo, a player used her arms and legs to hit balls in an attempt to destroy a brick wall, and in another game, an employee threw virtual “paint” on a canvas to create a painting, even drawing an elephant using a silhouette feature. An accompanying video also demonstrated automatic login using facial recognition, videoconferencing with other Xbox Live members, and participating in a gameshow against another family through the Internet using speech recognition.

Windows Mobile gets enhanced voice-command capability

Microsoft Corp. has high hopes that a new speech-recognition application for the forthcoming Windows Mobile operating system will be attractive enough to draw people to the phone platform.

Microsoft today planned to announce a new service that will work on Windows Mobile 6.5 devices and will let people speak into the phone to search the Internet, make phone calls and dictate text messages. Thetechnology comes from Tellme Networks Inc., a company that offers hosted voice recognition services and was acquired by Microsoft in 2007.

TellMe cuts the cord to Nuance

TellMe just had their best quarter so far. It's taken them over two years to upgrade their platform to lose reliance on Nuance technology.

When TellMe was founded in 1999, they used speech recognition technology produced by the original Nuance. Over time, they upgraded their platform and continued to use Nuance technology even after ScanSoft bought out Nuance and changed it's name to Nuance. 

Now, TellMe has announced vast improvements to their platform, "the most substantial ... since Microsoft bought it in May 2007." and "the improvements ... take advantage of cloud computing..."

The article states that "The improvements  include speech recognition technology developed by other units of Microsoft." 

Microsoft Unveils Recite

This week at Mobile World Congress Microsoft will release a free technology preview ofMicrosoft Recite. Microsoft Recite runs on Windows Mobile 6.0 or higher and allows the user to record voice notes and then store, search and retrieve information from them bysimply speaking a word that they want to search for. [click heading for more]

SpeechMagic chosen as the preferred speech recognition technology for Microsoft Amalga HIS and Amalga RIS/PACS

Royal Philips Electronics announced today that it has signed a global licensing agreement with Microsoft Corp. to bring industrial grade speech recognition to Microsoft’s Amalga family of enterprise healthcare solutions. Microsoft will offer Philips SpeechMagic to customers using Microsoft Amalga Hospital Information System (Amalga HIS) and Amalga RIS/PACS, with the goal of helping healthcare providers generate accurate, actionable information that is sharable, searchable and contributes to making clinical improvements. [click heading for more]

Tellme and Aspect Software to Deliver Innovative Solution to Contact Center Customers

Tellme(R), a Microsoft(R) subsidiary, and Aspect Software today announced anagreement to bring together the Aspect unified contact center solution and services with Tellme's proven voice services platform to deliver a flexible, cost effective joint contact center solution. The agreement between Tellme and Aspect expands on the strategic, multi-year alliance that Aspectand Microsoft made earlier this year to deliver contact center solutions withdeeper unified communications capabilities. [click heading for more]

JetBlue dials in to Microsoft's speech-recognition technology

A recent move by JetBlue is allowing the airline's passengers to retrieve flight information with a voice-activated interface when they call in. It's a simple scenario that most of us are familiar with: You call a toll-free number, speak the flight numbers, arrival and departure cities, and flight times, and you are provided with the information you need. The headlines from a recent Webinar regarding JetBlue's phone changes show the affordability side: "How JetBlue is Replacing their $1,000 Speech Recognition Licenses for $15".

So where does Microsoft come into play on all of this? Well, there are usually steep costs involved with speech recognition. Aumtech, however, collaborated with Microsoft to leverage the speech recognition services built into Office and Vista, resulting in a lower-cost solution. By lower cost, I mean 75 percent lower than competitively placed solutions, according to some accounts.

Here are some of the numbers: When JetBlue wanted to increase its existing Philips/Nuance ASR application license (which had an 88 percent accuracy rate and 60 percent call completion rate), the airline was looking at a price tag of $175,000. Aumtech said it could do it better and for less, $47,500. JetBlue says the system now has an accuracy rate of 90 percent and call completions are at 82 percent with the capability to handle three times the call volume than the previous system. .

[click heading for more]

Mobile Search: Look, Ma, No Hands

No matter how the soap opera of Microsoft's (MSFT) efforts to acquire Yahoo! (YHOO) turns out, there's one area where a merger would clearly benefit consumers. Both companies have launched voice-based mobile search services, and Yahoo oneSearch and Microsoft Tellme have strengths and weaknesses that neatly complement each other.
At best, it will be a long time before these services are consolidated. In the meantime, consumers can take advantage of two interesting experiments in speech recognition. [click heading for more]

The Future of Video is Audio … (Text Actually)

Let’s face it - we developed a text based internet. All of our systems and tools do a great job of parsing text and building models for targeting and/or dynamic content creation. However, video has not enjoyed the same flexibility and matchability at as granular a level as text-based content due to technical restrictions that prevent us from easily understanding the context of the content. Audio-to-text technology, in theory, should solve all of that. In reality - have you seen any systems that work perfectly yet? [click heading for more]

Microsoft applies to patent "answering machine detection using speech recognition"

The US system of patents is patently (pun intended) very different from the UK
one. It seems to me that Microsoft's latest patent application is decidely
obvious, and is not-very-far-removed from techniques already in use for
outbound dialling systems; basically it amounts to a "liveness" test of what's
on the other end of phone... which is all very well until I implement a
speech-enabled voicemail application that answers back :-) The abstract
follows:

An answering machine detection module is used to determine whether a call
recipient is an actual person or an answering machine. The answering machine
detection module includes a speech recognizer and a call analysis module. The
speech recognizer receives an audible response of the call recipient to a call.
The speech recognizer processes the audible response and provides an output
indicative of recognized speech. The call analysis module processes the output
of the speech recognizer to generate an output indicative of whether the call
recipient is a person or an answering machine.[click heading for more]