Robust feature-estimation and objective quality assessment for noisy speech recognition using the Credit Card corpus

It is well known that the introduction of acoustic background distortion into speech causes recognition algorithms to fail. In order to improve the environmental robustness of speech recognition in adverse conditions, a novel constrainediterative feature-estimation algorithm, which was previously formulated for speech enhancement, is considered and shown to produce improved feature characterization in a variety of actual noise conditions such as computer fan, large crowd, and voice communications channel noise. In addition, an objective measure based MAP estimator is formulated as a means of predicting changes in robust recognition performance at the speech feature extraction stage. The four measures considered include i) NIST SNR ii) Itakura4aito log-likelihood iii) log-area-ratio iv) the weighted-spectral slope measure. A continuous distribution, monophone based, hidden Markov model recognition algorithm is used for objective measure based MAP estimator analysis and recognition evaluation. Evaluations were based on speech data from the Credit Card corpus (CCDATA). It is shown that feature enhancement provides a consistent level of recognition improvement for broadband, and low-frequency colored noise sources. Average improvement across nine noise sources and three noise levels was +9.22%, with a corresponding decrease in recognition rate variability as represented by standard deviation in recognition from 12.4 to 6.5. As the ~ t a t i o ~ r i t y assumption for a given noise source breaks down, the ability of feature enhancement to improve recognition performance decreases. Finally. the log-likelihood based MAP estimator was found to be the best predictor of recognition performance, while the NIST SNR based MAP estimator was found to be poorest recognition predictor across the 27 noise conditions considered.