This paper introduces a novel combination of Artificial Neural Networks (ANNs) and Hidden Markov Models (HMMs) for Automatic Speech Recognition (ASR), relying on ANN non-parametric estimation of the emission probabilities of an underlying HMM. A gradient-ascent global training technique aimed at maximizing the likelihood (ML) of acoustic observations given the model is presented. A maximum a-posteriori variant of the algorithm is also proposed as a viable solution to the "divergence problem" that may arise in the ML setup. A 46.34% relative word error rate reduction with respect to standard HMMs was obtained in a speaker-independent, continuous ASP, task with a small vocabulary.

Trentin, E., Gori, M. (2001). Continuous speech recognition with a robust connectionist/markovian hybrid model. In Proceedings of ICANN 2001 (International Conference on Artificial Neural Networks) (pp.577-582). Springer.

Continuous speech recognition with a robust connectionist/markovian hybrid model

Trentin E.;Gori M.
2001-01-01

Abstract

This paper introduces a novel combination of Artificial Neural Networks (ANNs) and Hidden Markov Models (HMMs) for Automatic Speech Recognition (ASR), relying on ANN non-parametric estimation of the emission probabilities of an underlying HMM. A gradient-ascent global training technique aimed at maximizing the likelihood (ML) of acoustic observations given the model is presented. A maximum a-posteriori variant of the algorithm is also proposed as a viable solution to the "divergence problem" that may arise in the ML setup. A 46.34% relative word error rate reduction with respect to standard HMMs was obtained in a speaker-independent, continuous ASP, task with a small vocabulary.
2001
Trentin, E., Gori, M. (2001). Continuous speech recognition with a robust connectionist/markovian hybrid model. In Proceedings of ICANN 2001 (International Conference on Artificial Neural Networks) (pp.577-582). Springer.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11365/5147
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo