Blind Model Selection for Automatic Speech Recognition in Reverberant Environments: Special Issue on Real World Speech Processing

Authors: Couvreur L.¹; Couvreur C.²

Source: The Journal of VLSI Signal Processing, Volume 36, Numbers 2-3, February 2004 , pp. 189-203(15)

Publisher: Springer

Buy & download fulltext article:

Price: $47.00 plus tax (Refund Policy)

Abstract:

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.

Keywords: room reverberation; maximum likelihood estimation; automatic speech recognition

Document Type: Research article

DOI: http://dx.doi.org/10.1023/B:VLSI.0000015096.78139.82

Affiliations: 1: Multitel—TCTS, Faculté Polytechnique de Mons, 1 Avenue Copernic, B-7000 Mons, Belgium 2: Speech & Language Technology Division, Scansoft, Inc., 32 Guldensporenpark, B-9820 Merelbeke, Belgium

Publication date: 2004-02-01