Single-Channel Multiple Regression for In-Car Speech Enhancement

Weifeng LI  Katsunobu ITOU  Kazuya TAKEDA  Fumitada ITAKURA  

IEICE TRANSACTIONS on Information and Systems   Vol.E89-D   No.3   pp.1032-1039
Publication Date: 2006/03/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e89-d.3.1032
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Section on Statistical Modeling for Speech Processing)
Category: Speech Enhancement
speech enhancement,  speech recognition,  multi-layer perceptron,  mean opinion score,  pairwise preference test,  environmental adaptation,  K-means clustering,  

Full Text: PDF(505.6KB)>>
Buy this Article

We address issues for improving hands-free speech enhancement and speech recognition performance in different car environments using a single distant microphone. This paper describes a new single-channel in-car speech enhancement method that estimates the log spectra of speech at a close-talking microphone based on the nonlinear regression of the log spectra of noisy signal captured by a distant microphone and the estimated noise. The proposed method provides significant overall quality improvements in our subjective evaluation on the regression-enhanced speech, and performed best in most objective measures. Based on our isolated word recognition experiments conducted under 15 real car environments, the proposed adaptive nonlinear regression approach shows an advantage in average relative word error rate (WER) reductions of 50.8% and 13.1%, respectively, compared to original noisy speech and ETSI advanced front-end (ETSI ES 202 050).