Logo image
Log spectra enhancement using speaker dependent priors for speaker verification
Conference proceeding

Log spectra enhancement using speaker dependent priors for speaker verification

Ciira wa Maina, John MacLaren Walsh and IEEE
2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 4540-4543
May 2011

Abstract

Approximation methods Bayesian methods Mel frequency cepstral coefficient Noise Noise measurement Speaker verification Speech Speech enhancement variational Bayesian inference
We present a variational Bayesian algorithm that enhances the log spectra of noisy speech using speaker dependent priors. This algorithm extends prior work by Frey et al. where the Algonquin algorithm was introduced to enhance speech log spectra in order to improve speech recognition in noisy environments. Our work is built on the intuition that speaker dependent priors would work better than priors that attempt to capture global speech properties. Experimental results using the TIMIT data set and the NIST 2004 speaker recognition evaluation (SRE) data are presented to demonstrate the algorithm's performance.

Metrics

10 Record Views

Details

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Web of Science research areas
Acoustics
Engineering, Electrical & Electronic
Imaging Science & Photographic Technology
Logo image