Most speaker-independent acoustic-phonetic decoding systems are based on hidden Markov models. Such systems lack a real temporal control for the phonetic models. Furthermore, inter-speaker variability makes speaker adaptation necessary. In order to solve these problems, we introduce two original approaches. On the one hand, discontinuities detected with the Forward-Backward Divergence method are used to constrain phonetic transitions and to perform a more accurate temporal control. On the other hand, an efficient inter-speaker measure, based on AR-vector models, allows the selection of a speaker neighbourhood and the adaptation of the phonetic models. The contribution of these two methods is estimated on the TIMIT database.
Bibliographic reference. Barras, C. / Caraty, M.-J. / Montacie, C. (1995): "Temporal control and training selection for HMM-based system", In EUROSPEECH-1995, 27-30.