Nonlinear mapping for feature extraction in automatic speech recognition
Number of patents in Portfolio can not be more than 2000
United States of America Patent
Stats
-
Aug 7, 2007
Grant Date -
N/A
app pub date -
Nov 16, 2000
filing date -
Nov 16, 1999
priority date (Note) -
Expired
status (Latency Note)
Importance
Abstract
The present invention successfully combines neural-net discriminative feature processing with Gaussian-mixture distribution modeling (GMM). By training one or more neural networks to generate subword probability posteriors, then using transformations of these estimates as the base features for a conventionally-trained Gaussian-mixture based system, substantial error rate reductions may be achieved. The present invention effectively has two acoustic models in tandem--first a neural net and then a GMM. By using a variety of combination schemes available for connectionist models, various systems based upon multiple features streams can be constructed with even greater error rate reductions.
First Claim
Family
International Classification(s)
Cited Art Landscape
Patent Citation Ranking
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