COMPARISON OF SOME NOISE-COMPENSATION METHODS FOR SPEECH RECOGNITION IN ADVERSE ENVIRONMENTS

A comparative study is presented of three noise-compensation schemes, namely spectral subtraction, Wiener filters, and noise adaptation, for hidden-Markov-model-based speech recognition in adverse environments. The noise-compensation methods are evaluated on a spoken-digit databa se, in the presence of car noise and helicopter noise at different sig nal-to-noise ratios. Experimental results demonstrate that the noise-c ompensation methods achieve a substantial improvement in recognition a ccuracy across a wide range of signal-to-noise ratios. At a signal-to- noise ratio of -6 dB the recognition accuracy is improved from 11% to 83%. The use of cepstral-time matrices as an improved speech represent ation is also considered, and their combination with the noise-compens ation methods is shown. Experiments show that the cepstral-time matrix is a more robust feature than a vector of identical size, composed of a combination of cepstral and differential cepstral features.