5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

Effectiveness of Phase-Corrected Rasta for Continuous Speech Recognition

Johan de Veth, Louis Boves

A2RT, Dept. of Language & Speech, University of Nijmegen, The Netherlands

Phase-corrected RASTA is a new technique for channel normalization that consists of classical RASTA filtering followed by a phase correction operation. In this manner, the channel bias is as effectively removed as with classical RASTA, without introducing a left context dependency. The performance of the phase-corrected RASTA channel normalization technique was evaluated for a continuous speech recognition task. Using context-independent hidden Markov models we found that phase-corrected RASTA reduces the best-sentence word error rate (WER) by 23 % compared to classical RASTA. For context-dependent models phase-corrected RASTA reduces WER by 15 % compared to classical RASTA.

Full Paper

Bibliographic reference.  Veth, Johan de / Boves, Louis (1998): "Effectiveness of phase-corrected rasta for continuous speech recognition", In ICSLP-1998, paper 0359.