Multi-stream speech recognition: Ready for prime time?
Janin
Adam
author
Ellis
Daniel P. W.
author
Columbia University. Electrical Engineering
Morgan
Nelson
author
Columbia University. Electrical Engineering
originator
text
Articles
1999
manuscript version
English
Multi-stream and multi-band methods can improve the accuracy of speech recognition systems without overly increasing the complexity. However, they cannot be applied blindly. In this paper, we review our experience applying multi-stream and multiband methods to the Broadcast News corpus. We found that multi-stream systems using different acoustic front-ends provide a significant improvement over single stream systems. However, despite the fact that they have been successful on smaller tasks, we have not yet been able to show any gain using multi-band methods. We report various insights gained from the experience in applying these methods in a large-vocabulary task.
Electrical engineering
Artificial intelligence
Eurospeech 99: 6th European Conference on Speech Communication and Technology: Budapest, Hungary, September 5-9, 1999
Bonn
ESCA
1999
http://hdl.handle.net/10022/AC:P:13834
NNC
NNC
2012-07-03 12:47:45 -0400
2012-07-03 12:49:25 -0400
7836
eng