Signal Processing for Speech Recognition in Noisy Environment

This paper studies noise subtraction methods and distance measures for speech recognition in a noisy environment, and investigates noise robustness of the distance measures applied to the problem of isolated word recognition in white Gaussian and colored noise (vehicle noise) environments. Noise subtraction methods which can be used as a pre-processor for the speech recognition system, such as the spectral subtraction method, autocorrelation subtraction method, adaptive noise cancellation and acoustic beamforming are studied, and distance measures such and Log Likelihood Ratio (), cepstral distance measure (), weighted cepstral distance measure (), spectral slope distance measure () and cepstral projection distance measure () are also investigated. Testing of the distance measures for speaker-dependent isolated word recognition in a noisy environment indicate that which weigh higher order cepstral coefficients more heavily give considerable performance improvement over . In addition, when no pre-emphasis is performed, the recognizer can maintain higher performance under high noise conditions.