5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

Combining Connectionist Multi-Band and Full-Band Probability Streams for Speech Recognition Of Natural Numbers

Nikki Mirghafori, Nelson Morgan

ICSI & UC Berkeley, USA

Multi-band automatic speech recognition is a new and exploratory area of speech recognition which has been getting much attention in the research community. It has been shown that multi-band ASR reduces word error in noisy conditions, particularly in the case of narrow band noise. In this work we show that multi-band ASR could be used to improve the speech recognition accuracy of natural numbers for clean speech when the multi-band (MB) information stream is used in addition to the full-band (FB) one. We also observe that a similar combination method significantly reduces the error rate on reverberant speech. Finally, we analyze the error patterns of the full-band and multi-band paradigms to understand why the combination of the two streams is effective.

Full Paper

Bibliographic reference.  Mirghafori, Nikki / Morgan, Nelson (1998): "Combining connectionist multi-band and full-band probability streams for speech recognition of natural numbers", In ICSLP-1998, paper 1150.