Third International Conference on Spoken Language Processing (ICSLP 94)

Yokohama, Japan
September 18-22, 1994

Global Optimisation of HMM Input Transformations

Finn Tore Johansen

Norwegian Telecom Research, Kjeller, Norway

This paper deals with discriminative optimisation of HMMs and hybrid models for continuous speech recognition. Using the well-known, sentence discriminative MMI criterion, we have observed a mismatch between error criterion and Viterbi recognition rate. We show how to overcome this, either by total likelihood scoring in the decoder, or by state-sequence discriminative optimisation criteria. We apply discriminative optimisation to a hybrid model, consisting of a continuous density HMM, and a linear or non-linear input transformation. Results are presented for TIMIT phone recognition, both on a small 5-class task, and the "standard" 39-class task.

Full Paper

Bibliographic reference.  Johansen, Finn Tore (1994): "Global optimisation of HMM input transformations", In ICSLP-1994, 239-242.