W3C home > Mailing lists > Public > w3c-wai-ig@w3.org > October to December 2002

RE: Voice content searching

From: George Kerscher <kerscher@montana.com>
Date: Sun, 15 Dec 2002 18:55:36 -0700
To: <blaplant@mindspring.com>, <blaplant@census.gov>, "'wai Interest Group'" <w3c-wai-ig@w3.org>
Message-ID: <002501c2a4a6$3b16c6b0$0300000a@dell>


This is very interesting technology. It is based on phonetic analysis.
From what I understand, the digitized human speech is broken down to its
phonetic components and an index is created. Then  the text search is
broken down into its phonetic parts and compared to the index. . I
understand the technology works across languages, but that some tables
need to be created. I am not sure what languages are supported so far.
The applications that exist are in court report and in phone tapping.
This is not cheap technology.

I'm sure you can see the application for Digital Talking Books (DTB).

By the way, if you have not visited the DAISY Web site recently, you may
want to go to:  http://www.daisy.org  


-----Original Message-----
From: w3c-wai-ig-request@w3.org [mailto:w3c-wai-ig-request@w3.org] On
Behalf Of Bill LaPlant
Sent: Sunday, December 15, 2002 9:16 AM
To: wai Interest Group
Subject: Voice content searching

Hi -- is anyone aware of any efforts voice content to develop search 
capability?  I'm aware that this is not a trivial problem and would 
require major advances in voice recognition technology.  IMHO we are 
approaching a time of both need and availability of hardware power to 
make such efforts feasible.

William P. LaPlant, Jr.     US Census; Technology Research Staff
Computer Scientist      SRD; Rm.3000-4/9100; Washington DC 20233
--                       phones-301-457-4887,  Home:703-360-9184
I am  committed to Children  inheriting a  culture  of unlimited
possibilities;  Technology empowering  miraculous lives.
Received on Sunday, 15 December 2002 20:53:18 UTC

This archive was generated by hypermail 2.3.1 : Tuesday, 13 October 2015 16:21:21 UTC