October 2010 -
What About Speech
August 2008 -
Is Speech Recognition FINALLY Ready
for Prime Time?
October 2007 - Docsoft: Video On Demand Portal
Incorporates Speech Recognition
April 2007 - ViaScribe Lecture Delivery System
Includes Automatic Captioning
2007 - Speech Recognition Empowers Cell Phones
February 2007 - New software writes
closed-captioning for videos
February 2007 - Speech recognition software sends voice messages as email
July 2006 - Here's a report on what's happening
at the leading edge of voice recognition technology.
May 2006 - Soundless voice recognition
March 2006 - Speech
recognition offered for handhelds
January 2006 - IBM Strives for Superhuman Speech Tech
May 2003 - Speech Recognition technology may be improving even faster
than we thought. A company called SpeechWorks has commercial programs in
use today that are doing amazing things. Here's the
April 2003 - Many of our technology advances come from the military.
Do they have a better voice recognition system? Read about how they're
using voice recognition in Iraq.
November 2001 - This is really exciting news! The Wisconsin Relay
Service is testing voice recognition for the relay.
I think voice recognition has huge potential for these types of
applications, so I'm anxious to hear how this works.
Automatic Speech Recognition was a topic at
good folks at the Northern Virginia Resource Center for Deaf and Hard of
Hearing Persons did an awesome job of recording the information, and
were kind enough to allow us to publish this article.
USC is conducting speech recognition research for the
Navy, and has recently developed a neural
based system that outperforms human listeners in some situations.
More on this and related
The cost of implementing systems such as CART,
CPrint, Typewell and automatic speech recognition can be significant, as
they require one transcriber to one lecturer to work. Yet
speech-recognition products, like Dragon NaturallySpeaking, turn spoken
words into text via a computer without being personally attended. Couldn't
this be a much more cost-effective solution for the classroom? Many
students with learning disabilities fi nd it much easier to speak their
words in preparing a research paper than to write them. And professors use
Naturally- Speaking as a time-saving tool to provide feedback to students
on papers and exams. While NaturallySpeaking is already well utilized in
education, it is neither designed nor advertised as a solution for
real-time transcription and captioning for academic lectures.
One vision we had dating back to 1980 when we
started speech recognition was to apply to this to the deaf. The idea is
that a deaf person would have a little display, which could be built into
their eyeglasses where they would basically get subtitles on the world.
On the one hand it's a demanding technology because it has to be
speaker-independent, have a large or unrestricted vocabulary, and support
continuous speech. On the other hand, it doesn't require perfect accuracy.
. . . I think we're pretty close to being able to do that at least in good
acoustic environments, maybe not at a cocktail party, but if the person is
being picked up, with pretty good accuracy.
The most impressive product is a voice-recognition
system from Nuance Communications Inc. that lets users control their
phones without lifting a thumb. The Nuance system goes far beyond the
"Call Bob" sort of voice control that many high-end cellphones
have offered for years. Without requiring any training to acclimate it
to your voice, Nuance allows users to dictate entire e-mails or to surf
Web sites or ask their phones for directions. A user might say,
"E-mail to Bob Jones. Subject: Tomorrow's Meeting. Text: Sorry to
do this, Bob, but an emergency is forcing me to cancel." The user's
voice will be sent to Nuance computers, which will create an e-mail and
send it back for approval in about 10 seconds. A simple "send"
ships the e-mail on its way.
There are a couple of services that provide voice mailboxes for when you
can't answer your phone, and also convert the voice message to text and
send it to you as an email. It sounds like a wonderful service for
people with hearing loss. And the most amazing part is that they claim
to do it with totally automated voice recognition software, and that
it's very accurate, even with cell phones, despite their notorious poor
sound quality. Here's
no one can hear you scream. Use a cell phone on a crowded commuter train
and everyone can. Charles Jorgensen is working to solve both problems,
using an uncanny technology called subvocal speech recognition. Jorgensen
demonstrates it at his offices at NASA's Ames Research Laboratory in
Mountain View, Calif. He attaches a set of electrodes to the skin of his
throat and, without his opening his mouth or uttering a sound, his words
are recognized and begin appearing on a computer screen. Jorgensen sees
abundant applications for his technology where audible speech is
now, something like "Call Mom" is the most advanced voice
command that most cell phones can handle. A maker of speech-recognition
software for personal computers hopes to change that. Nuance
Communications Inc. is trying to line up wireless carriers for a new
service allowing hands-free, speech-to-text messages or e-mails of
nearly unlimited length, as well as voice-command Web browsing and music
YORK -- IBM unveiled new speech recognition technology on Tuesday that
can comprehend the nuances of spoken English, translate it on the fly,
and even create on-the-fly subtitles for foreign-language television
programs. Historically, speech technology required the user to limit his
speech to a fixed set of phrases in order to interact with a device.
With IBM's Embedded ViaVoice 4.4 software package, introduced on
Tuesday, the company hopes to allow users to speak commands using
phrasing that is natural to them. Full