Improving performance of spectral subtraction in speech recognition using a model for additive noise

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. Wei...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on speech and audio processing Vol. 6; no. 6; pp. 579 - 582
Main Authors: Yoma, N.B., McInnes, F.R., Jack, M.A.
Format: Journal Article
Language:English
Published: New York, NY IEEE 01.11.1998
Institute of Electrical and Electronics Engineers
Subjects:
Additive noise
Applied sciences
Cepstral analysis
Error analysis
Exact sciences and technology
Hidden Markov models
Information, signal and communications theory
Noise cancellation
Signal processing
Signal to noise ratio
Speech processing
Speech recognition
Telecommunications and information theory
Testing
Uncertainty
Viterbi algorithm
Additive noise
Viterbi algorithm
Fast Fourier transformation
Speech recognition
Error rate
Performance analysis
Covariance matrix
Markov model
Dynamic programming
Speech processing
ISSN:1063-6676
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:1063-6676
DOI:10.1109/89.725325