Self-learning speaker adaptation based on spectral bias source decomposition, using very short calibration speech
Number of patents in Portfolio can not be more than 2000
United States of America Patent
Stats
-
Aug 11, 1998
Issued Date -
N/A
app pub date -
Sep 12, 1996
filing date -
Apr 29, 1993
priority date (Note) -
Expired
status (Latency Note)
Importance
Abstract
A speaker adaptation technique based on the separation of speech spectra variation sources is developed for improving speaker-independent continuous speech recognition. The variation sources include speaker acoustic characteristics, and contextual dependency of allophones. Statistical methods are formulated to normalize speech spectra based on speaker acoustic characteristics and then adapt mixture Gaussian density phone models based on speaker phonologic characteristics. Adaptation experiments using short calibration speech (5 sec./speaker) have shown substantial performance improvement over the baseline recognition system.
First Claim
Family
International Classification(s)
Cited Art Landscape
Patent Citation Ranking
Advertisement
Advertisement
Advertisement
Recipient Email Address
Recipient Email Address
Comment
Recipient Email Address
Add to Portfolio(s)
To add this patent to one, or more, of your portfolios, simply click the add button.
This Patent is in these Portfolios:
Add to additional portfolios:
Last Refreshed On:
Changes done successfully