A general model for the representation of the spoken language is proposed. It is based on Ergodic Hidden Markov Models and allows the introduction of linguistically consistent sub-phonetic units, accounting for the stationary and transitional behaviour of the spoken message. The main characteristics of the proposed model are analysed, and some applications to speech recognition and coding are presented.
Phonetic Units and Phonotactical Structure Inference by EHMM / P., Pierucci; Falaschi, Alessandro; M., Giustiniani. - STAMPA. - (1990), pp. 77-82. (Intervento presentato al convegno Proceedings of the NATO Advanced Study Institute tenutosi a Cetraro, Italy nel July 1-13, 1990).
Phonetic Units and Phonotactical Structure Inference by EHMM
FALASCHI, Alessandro;
1990
Abstract
A general model for the representation of the spoken language is proposed. It is based on Ergodic Hidden Markov Models and allows the introduction of linguistically consistent sub-phonetic units, accounting for the stationary and transitional behaviour of the spoken message. The main characteristics of the proposed model are analysed, and some applications to speech recognition and coding are presented.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
