Single-Channel Multiple Regression for In-Car Speech Enhancement

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 singlechannel 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). key words: speech enhancement, speech recognition, multi-layer perceptron, mean opinion score, pairwise preference test, environmental adaptation, K-means clustering