7th International Conference on Spoken Language Processing
September 16-20, 2002
This paper presents a technique that exploits the denoised speech’s variance, estimated during the speech feature enhancement process, to improve noise-robust speech recognition. This technique provides an alternative to the Bayesian predictive classification decision rule by carrying out an integration over the feature space instead of over the model-parameter space, offering a much simpler system implementation and lower computational cost. We extend our earlier work  by using a new approach, based on a parametric model of speech distortion and thus free from the use of any stereo training data, to statistical feature enhancement, for which a novel algorithm for estimating the variance of the enhanced speech features is developed. Experimental evaluation using the full Aurora2 test data sets demonstrates an 11.4% digit error rate reduction averaged over all noisy and SNR conditions, compared with the best technique we have developed  prior to this work that did not exploit the variance information and that required no stereo training data.
Bibliographic reference. Deng, Li / Droppo, Jasha / Acero, Alex (2002): "Exploiting variances in robust feature extraction based on a parametric model of speech distortion", In ICSLP-2002, 2449-2452.