Third International Conference on Spoken Language Processing (ICSLP 94)

Yokohama, Japan
September 18-22, 1994

An Hmm-Based Cepstral-Domain Speech Enhancement System

C. W. Seymour, M. Niranjan

Cambridge University Engineering Department, Cambridge, UK

This paper describes a method of enhancing speech corrupted by additive uncorrelated noise. The approach adopted is to use cepstral-domain hidden Markov models to determine statistics of the clean speech and noise processes. A compensated model of speech corrupted by noise is generated using parallel model combination. MMSE and linear non-homogeneous estimators of the clean speech signal are derived. The enhancement system gives natural-sounding speech without the artifacts introduced by systems such as spectral subtraction. HMM recognition tests performed on the enhanced speech using the NOISEX-92 database show a significant reduction in error rate.

Full Paper

Bibliographic reference.  Seymour, C. W. / Niranjan, M. (1994): "An hmm-based cepstral-domain speech enhancement system", In ICSLP-1994, 1595-1598.