W3C home > Mailing lists > Public > www-voice@w3.org > October to December 2002

ASR optimization

From: FOREST Laurent - MTR ( LForest@mtr.sema.slb.com ) <LForest@mtr.sema.slb.com>
Date: Thu, 17 Oct 2002 03:44:23 -0400 (EDT)
Message-ID: <D181DAC332B4D611A22B0090274580153AEF3E@MONTROUGE1>
To: MLL W3C Voice Browser <www-voice@w3.org>


I am quite new to speech recognition.
I have some questions related to recognition tuning and optimization

Where could I find an introduction to the following techniques:
- Accoustic model retraining | adaptation
- Hand-tuned pronunciations
- Utterance transcription
- Audio caching & streaming

Is there any other recognition optimization techniques?

What is the improvement usually measured after optimization?

Best regards.

Received on Thursday, 17 October 2002 03:47:09 GMT

This archive was generated by hypermail 2.2.0+W3C-0.50 : Monday, 30 October 2006 12:48:56 GMT