Feature generation based on maximum normalized acoustic likelihood for improved speech recognition - researchr publication related

researchr

You are not signed in
Sign in
Sign up

Xiang Li, Richard M. Stern. Feature generation based on maximum normalized acoustic likelihood for improved speech recognition. In 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2004, Montreal, Quebec, Canada, May 17-21, 2004. pages 545-548, IEEE, 2004. [doi]

The following publications are possibly variants of this publication:

Parallel feature generation based on maximizing normalized acoustic likelihoodXiang Li, Richard M. Stern. interspeech 2004: 953-956 [doi]

Feature generation based on maximum classification probability for improved speech recognitionXiang Li, Richard M. Stern. interspeech 2003: 845-848 [doi]

runs on WebDSL