A fast segmental clustering approach to decision tree tying based acoustic modeling

Author

Reichl, W. ; Chou, W.

Author_Institution

AT&T Bell Labs., Murray Hill, NJ, USA

fYear

1997

fDate

14-17 Dec 1997

Firstpage

185

Lastpage

191

Abstract

A fast two level segmental clustering approach to decision tree based state tying is proposed for large vocabulary speech recognition. This approach extends the conventional segmental K-means approach to phonetic decision tree tying based acoustic modeling. It achieves high recognition performances while reducing the model training time from days to hours, compared to approaches based on incremental Baum-Welch training. Experimental results for this fast segmental clustering approach are presented for resource management and the Wall Street Journal tasks

Keywords

decision theory; resource allocation; speech recognition; trees (mathematics); Wall Street Journal tasks; decision tree based state tying; decision tree tying based acoustic modeling; fast segmental clustering approach; fast two level segmental clustering; large vocabulary speech recognition; model training time; phonetic decision tree tying based acoustic modeling; recognition performance; resource management; segmental K-means approach; Clustering algorithms; Context modeling; Decision trees; Hidden Markov models; Management training; Parameter estimation; Robustness; Speech recognition; Training data; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Automatic Speech Recognition and Understanding, 1997. Proceedings., 1997 IEEE Workshop on

Conference_Location

Santa Barbara, CA

Print_ISBN

0-7803-3698-4

Type

conf

DOI

10.1109/ASRU.1997.659004

Filename

659004