This paper describes a new multi-channel method of noisy speech recognition, which estimates the log spectrum of speech at a close-talking microphone based on the multiple regression of the log spectra (MRLS) of noisy signals captured by the distributed microphones. The advantages of the proposed method are as follows: 1 The method does not make any assumptions about the positions of the speaker and noise sources with respect to the microphones. Therefore, the system can be trained for various sitting positions of drivers. 2 The regression weights can be statistically optimized over a certain length of speech segments (e.g., sentences of speech) under particular road conditions. The performance of the proposed method is illustrated by speech recognition of real in-car dialogue data. In comparison to the nearest distant microphone and multi-microphone adaptive beamformer, the proposed approach obtains relative word error rate (WER) reductions of 9.8% and 3.6% respectively.
展开▼
