Using expanded question sets in decision tree clustering for acoustic modelling

Author

Sjölander, Kåre ; Högberg, Jesper

Author_Institution

Dept. of Speech, Music & Hearing, R. Inst. of Technol., Stockholm, Sweden

fYear

1997

fDate

14-17 Dec 1997

Firstpage

179

Lastpage

184

Abstract

Phone-like units (PLUs) for automatic speech recognition are derived using a decision tree algorithm. In our approach we use information such as target phone label, immediate context, lexical stress level and function word affiliation in the decision tree analysis. The resulting PLUs are shown to improve phone and word recognition

Keywords

decision theory; speech processing; speech recognition; trees (mathematics); word processing; PLUs; acoustic modelling; automatic speech recognition; decision tree algorithm; decision tree analysis; decision tree clustering; expanded question sets; function word affiliation; immediate context; lexical stress level; phone like units; target phone label; word recognition; Auditory system; Automatic speech recognition; Clustering algorithms; Decision trees; Information analysis; Music; Speech analysis; Speech recognition; Stress; 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.1997.659003

Filename

659003

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=321484