Improving Performance of Spectral Subtraction in Speech Recognition Using a Model for Additive Noise

N. B. Yoma, Fergus McInnes, Mervyn Jack

Research output: Contribution to journalArticlepeer-review

Abstract

Addresses the problem of speech recognition with signals corrupted by additive noise at moderate signal-to-noise ratio (SNR). A model for additive noise is presented and used to compute the uncertainty about the hidden clean signal so as to weight the estimation provided by spectral subtraction. Weighted dynamic time warping (DTW) and Viterbi (HMM) algorithms are tested, and the results show that weighting the information along the signal can substantially increase the performance of spectral subtraction, an easily implemented technique, even with a poor estimation for noise and without using any information about the speaker. It is also shown that the weighting procedure can reduce the error rate when cepstral mean normalization is also used to cancel the convolutional noise
Original languageEnglish
Pages (from-to)579-582
Number of pages4
JournalIEEE Transactions on Audio, Speech and Language Processing
Volume6
Issue number6
DOIs
Publication statusPublished - 1998

Keywords

  • Additive noise
  • Cepstral analysis
  • Error analysis
  • Hidden Markov models
  • Noise cancellation
  • Signal to noise ratio
  • Speech recognition
  • Testing
  • Uncertainty
  • Viterbi algorithm

Fingerprint

Dive into the research topics of 'Improving Performance of Spectral Subtraction in Speech Recognition Using a Model for Additive Noise'. Together they form a unique fingerprint.

Cite this