Paper Info
Title
Improved cepstral mean and variance normalization using Bayesian framework
Abstract
Cepstral Mean and Variance Normalization (CMVN) is a computationally efficient normalization technique for noise robust speech recognition. The performance of CMVN is known to degrade for short utterances, due to insufficient data for parameter estimation and loss of discriminable information as all utterances are forced to have zero mean and unit variance. In this work, we propose to use posterior estimates of mean and variance in CMVN, instead of the maximum likelihood estimates. This Bayesian approach, in addition to providing a robust estimate of parameters, is also shown to preserve discriminable information without increase in computational cost, making it particularly relevant for Interactive Voice Response (IVR)-based applications. The relative WER reduction of this approach w.r.t. Cepstral Mean Normalization, CMVN and Histogram Equalization are (i) 40.1%, 27% and 4.3% with the Aurora2 database for all utterances, (ii) 25.7%, 38.6% and 30.4% with the Aurora2 database for short utterances, and (iii) 18.7%, 12.6% and 2.5% with the Aurora4 database.
Year
DOI
Venue
2013
10.1109/ASRU.2013.6707722
Automatic Speech Recognition and Understanding
Keywords
Field
DocType
Bayes methods,maximum likelihood estimation,speech recognition,Aurora2 database,Aurora4 database,Bayesian framework,CMVN,IVR,WER reduction,discriminable information loss,histogram equalization,improved cepstral mean and variance normalization,interactive voice response-based applications,maximum likelihood estimates,noise robust speech recognition,normalization technique,parameter estimation,short utterances,Bayesian estimation,CMVN,HEQ,Robust speech recognition,VTS
Zero mean,Normalization (statistics),Pattern recognition,Computer science,Maximum likelihood,Speech recognition,Cepstral Mean and Variance Normalization,Artificial intelligence,Estimation theory,Histogram equalization,Cepstral mean normalization,Bayesian probability
Conference
Citations 
PageRank 
References 
10
0.68
7
Authors
2
Name
Order
Citations
PageRank
N. Vishnu Prasad1100.68
Srinivasan Umesh29316.31