A Two-Channel Training Algorithm for Hidden Markov Model and Its Application to Lip Reading

Hidden Markov model (HMM) has been a popular mathematical approach for sequence classification such as speech recognition since 1980s. In this paper, a novel two-channel training strategy is proposed for discriminative training of HMM. For the proposed training strategy, a novel separable-distance f...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	EURASIP Journal on Applied Signal Processing 2005-06, Vol.2005 (9), p.1382-1399, Article 347367
Hauptverfasser:	Dong, Liang, Foo, Say Wei, Lian, Yong
Format:	Artikel
Sprache:	eng
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!