Christophe Couvreur

Blind Model Selection for Automatic Speech Recognition in Reverberant Environments

This communication presents a new method for automatic speech recognition in reverberant environments. Our approach consists in the selection of the best acoustic model out of a library of models trained on artificially reverberated speech databases corresponding to various reverberant conditions. Given a speech utterance recorded within a reverberant room, a Maximum Likelihood estimate of the fullband room reverberation time is computed using a statistical model for short-term log-energy sequences of anechoic speech. The estimated reverberation time is then used to select the best acoustic model, i.e., the model trained on a speech database most closely matching the estimated reverberation time, which serves to recognize the reverberated speech utterance. The proposed model selection approach is shown to improve significantly recognition accuracy for a connected digit task in both simulated and real reverberant environments, outperforming standard channel normalization techniques.

Dictionary-based decomposition of linear mixtures of Gaussian processes

We consider the problem of detecting and classifying an unknown number of multiple simultaneous Gaussian processes with unknown variances given a finite length observation of their sum and a dictionary of candidate models for the signals. The optimal minimum description length (MDL) detector is presented. Asymptotic and quadratic approximations of the MDL criterion are derived, and regularization algorithms for their efficient implementation are described. The performance of the algorithms is illustrated by numerical simulations. Interpretations in terms of vector quantization and in model-based spectral analysis are discussed together with applications and possible extensions.

Modeling and estimation for Doppler-shifted Gaussian random processes

We address the problems of modeling Doppler-shifted wide-band Gaussian random processes and of estimating the Doppler parameter from a finite series of discrete-time samples. Relations between the continuous-time process, the Doppler shift parameter and the discrete-time process obtained by sampling are established. Approximate rational models are proposed. Various estimators are proposed for the Doppler parameter when the second-order statistics of the original continuous-time random process are known. The Cramer-Rao bound is derived. The estimators are compared experimentally on synthetic Doppler-shifted data. We also hint at some extensions of the method to non-stationary processes and time-varying Doppler shifts.