5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

Discriminative Feature and Model Design for Automatic Speech Recognition

Mazin Rahim, Yoshua Bengio, Yann LeCun

AT&T Labs - Research, Florham Park, NJ, USA

A system for discriminative feature and model design is presented for automatic speech recognition. Training based on minimum classification error using a single objective function is applied for designing a set of parallel networks performing feature transformation and a set of hidden Markov models performing speech recognition. This paper compares the use of linear and non-linear functional transformations when applied to conventional recognition features, such as spectrum or cepstrum. It also provides a framework for integrated feature and model training when using class-specific transformations. Experimental results on telephone-based connected digit recognition are presented.

Full Paper

Bibliographic reference.  Rahim, Mazin / Bengio, Yoshua / LeCun, Yann (1997): "Discriminative feature and model design for automatic speech recognition", In EUROSPEECH-1997, 75-78.