Deterministically annealed design of hidden Markov model speech recognizers.

Many conventional speech recognition systems are based on the use of hidden Markov models (HMM) within the context of discriminant-based pattern classification. While the speech recognition objective is a low rate of misclassification, HMM design has been traditionally approached via maximum likelih...

Descrizione completa

Dettagli Bibliografici
Pubblicato in:	IEEE Transactions on speech and audio processing 9, 2 (2001).
Autore principale:	Rao, A.V
Natura:	Articolo
Lingua:	English
Soggetti:	GPD method. HMM speech recognizers. ML method. Shannon entropy. Deterministically annealed design. Discriminant-based pattern classification. Entropy constraint. Error rate minimisation. Forward-backward algorithm. Generalized probabilistic descent. Hidden Markov model speech recognizers. Information theory. Isolated English letters. Maximum likelihood modeling. Nonrandom HMM classifiers. Random HMM classifier decision. Recognition error rates. Speech recognition systems. Statistical physics. Synthetic data.