Logo image
Back
Joint Speech Enhancement and Speaker Identification Using Approximate Bayesian Inference
Journal article   Peer reviewed

Joint Speech Enhancement and Speaker Identification Using Approximate Bayesian Inference

Ciira wa Maina and J M Walsh
IEEE transactions on audio, speech, and language processing, v 19(6), pp 1517-1529
Aug 2011
DOI: https://doi.org/10.1109/TASL.2010.2092767

Abstract

Bayesian methods Noise variational Bayesian inference Signal processing algorithms Speech enhancement Speech Approximation algorithms speaker identification Joints
We present a variational Bayesian algorithm for joint speech enhancement and speaker identification that makes use of speaker dependent speech priors. Our work is built on the intuition that speaker dependent priors would work better than priors that attempt to capture global speech properties. We derive an iterative algorithm that exchanges information between the speech enhancement and speaker identification tasks. With cleaner speech we are able to make better identification decisions and with the speaker dependent priors we are able to improve speech enhancement performance. We present experimental results using the TIMIT data set which confirm the speech enhancement performance of the algorithm by measuring signal-to-noise (SNR) ratio improvement and perceptual quality improvement via the Perceptual Evaluation of Speech Quality (PESQ) score. We also demonstrate the ability of the algorithm to perform voice activity detection (VAD). The experimental results also demonstrate that speaker identification accuracy is improved.

Metrics

6 Record Views
12 citations in Web of Science
15 citations in Scopus

Details

InCites Highlights

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

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