 Speech ComputingWhere Speech Meets Computing |
|
User loginRegistering and logging in removes this ad.
--- Registering and logging in removes this ad. |
Google Voice voicemail transcription extremely good!
Submitted by reckoner on Mon, 07/13/2009 - 01:10.
Even over a noisy phone line, the transcription of voicemail is extremely good. Whatever speech recognition technology they are using is excellent. Anybody know what it is? By the way, Google Voice used to be known as Grand Central before Google bought them.  |
NavigationPopular content
Who's onlineThere are currently 0 users and 3 guests online.
|
NOTICE OF DISCLAIMER: All readers, visitors and/or users of this site is/are hereby given notice that any and all either express or implied views, opinions, suggestions, advice, product promotions, and/or any apparent statements of truths or facts that have been, presently are or in the future may be placed on this site are to be understood to be solely those of the party posting same. In no regard or event are any or all express or implied views, opinions, suggestions, advice, product promotions, and/or any apparent statements of truths or facts posted on this site in any way whatsoever to be either directly or indirectly understood, interpreted, construed or relied upon by any readers, visitors and/or users of this site as being expressed or purveyed by or representative of the host of this site, nor shall same be directly or indirectly understood, interpreted, construed or relied upon by any readers as an endorsement of same by the host of this site. Any and all such express or implied views, opinions, suggestions, advice, product promotions, and any/or apparent statements of truths or facts posted on this site should be thoroughly investigated independently by any and all readers, visitors and/or users of this site prior to relying or acting upon same in any way or at any time.
© 2005-2010 Speech Computing
Best Viewed at 1024x768 and higher resolutions
The secret is not in the
The secret is not in the technology, it's in the methodology. Also, Google is not the first to do this. The original concept was developed by IBM.
The methodology that they use is to continue to collect a large corpus of acoustic data on-the-fly from everyone who calls in voicemail to be transcribed. As the variety and size of the data increases, so does the accuracy.
Nothing special, just a different approach, which is actually what Nuance has done with their speaker independent Acoustic Model.
Chuck Runquist
Owner, GEMCCON - The Choice of Intelligence
Speech Recognition Consulting and Training
"It ain't what you don't know that gets you into trouble. It's what you know for sure that just ain't so." -- Mark Twain