Exploiting primitive grouping constraints for noise robust automatic speech recognition : studies with simultaneous speech
Significant strides have been made in the field of automatic speech recognition over the past three decades. However, the systems are not robust; their performance degrades in the presence of even moderate amounts of noise. This thesis presents an approach to developing a speech recognition system t...
| Main Author: | |
|---|---|
| Published: |
University of Sheffield
2008
|
| Subjects: | |
| Online Access: | http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.489378 |
| Summary: | Significant strides have been made in the field of automatic speech recognition over the past three decades. However, the systems are not robust; their performance degrades in the presence of even moderate amounts of noise. This thesis presents an approach to developing a speech recognition system that takes inspiration firom the approach of human speech recognition. |
|---|