Multiple Regression of Log Spectra for In-Car Speech Recognition Using Multiple Distributed Microphones

Weifeng LI  Tetsuya SHINDE  Hiroshi FUJIMURA  Chiyomi MIYAJIMA  Takanori NISHINO  Katunobu ITOU  Kazuya TAKEDA  Fumitada ITAKURA 

Publication
IEICE TRANSACTIONS on Information and Systems  Vol.E88-D  No.3  pp.384-390
Publication Date: 2005/03/01
Online ISSN: 
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Section on Corpus-Based Speech Technologies)
Category: Feature Extraction and Acoustic Medelings
Keyword: 
speech recognition,  microphone arrays,  adaptive beamforming,  signal-to-deviation ratio,  multiple regression, 

Full Text: PDF(567.2KB)

Summary: 
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 distributed microphones. The advantages of the proposed method are as follows: 1) The method does not require a sensitive geometric layout, calibration of the sensors nor additional pre-processing for tracking the speech source; 2) System works in very small computation amounts; and 3) Regression weights can be statistically optimized over the given training data. Once the optimal regression weights are obtained by regression learning, they can be utilized to generate the estimated log spectrum in the recognition phase, where the speech of close-talking is no longer required. 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.