A codec for speech recognition in a wireless system

We consider a distributed speech recognition system where representative parameters of the speech signal are extracted at the wireless terminal and transmitted to a centralized automatic speech recognition (ASR) server. Several error protection schemes are proposed for the ASR feature stream. In addition, a "soft-feature" error concealment strategy is introduced at the ASR server that uses the marginal distribution of only the reliable features during likelihood computation. The performance of the error protection and concealment schemes is evaluated over typical cellular wireless channels and it is shown to reduce ASR error rate up to 65% for certain channels.

[1]  Phil D. Green,et al.  ROBUST ASR WITH UNRELIABLE DATA AND MINIMAL ASSUMPTIONS , 1999 .

[2]  Ponani S. Gopalakrishnan,et al.  Compression of acoustic features for speech recognition in network environments , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[3]  Joachim Hagenauer,et al.  Rate-compatible punctured convolutional codes (RCPC codes) and their applications , 1988, IEEE Trans. Commun..

[4]  Francisco J. Valverde-Albacete,et al.  Avoiding distortions due to speech coding and transmission errors in GSM ASR tasks , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[5]  Wu Chou,et al.  Decision tree state tying based on segmental clustering for acoustic modeling , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[6]  John Cocke,et al.  Optimal decoding of linear codes for minimizing symbol error rate (Corresp.) , 1974, IEEE Trans. Inf. Theory.

[7]  Carl-Erik W. Sundberg,et al.  The performance of rate-compatible punctured convolutional codes for digital mobile radio , 1990, IEEE Trans. Commun..