Discriminative Pronunciation Modeling Using the MPE Criterion

Introducing pronunciation models into decoding has been proven to be benefit to LVCSR. In this paper, a discriminative pronunciation modeling method is presented, within the framework of the Minimum Phone Error (MPE) training for HMM/GMM. In order to bring the pronunciation models into the MPE train...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEICE transactions on information and systems 2015-05, Vol.E98.D (3), p.717-720
Hauptverfasser:	Song, Meixu, Pan, Jielin, Zhao, Qingwei, Yan, Yonghong
Format:	Artikel
Sprache:	jpn
Schlagworte:	Acoustics Criteria Decoding Errors Mathematical models Speech Tasks Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!