Integration of context-dependent durational knowledge into HMM-based speech recognition

Author

Wang, Xue ; Ten Bosch, Louis F M ; Pols, Louis C W

Author_Institution

Inst. of Phonetic Sci., Amsterdam Univ., Netherlands

Volume

2

fYear

1996

fDate

3-6 Oct 1996

Firstpage

1073

Abstract

The paper presents research on integrating context-dependent durational knowledge into HMM-based speech recognition. The first part of the paper presents work on obtaining relations between the parameters of the context-free HMMs and their durational behaviour, in preparation for the context-dependent durational modelling presented in the second part. Duration integration is realised via rescoring in the post-processing step of the N-best monophone recogniser. The authors use the multi-speaker TIMIT database for the analyses

Keywords

hidden Markov models; speech processing; speech recognition; HMM-based speech recognition; N-best monophone recogniser; context-dependent durational knowledge integration; multi-speaker TIMIT database; post-processing step rescoring; Automatic speech recognition; Character generation; Computational complexity; Context modeling; Data analysis; Databases; Hidden Markov models; Speech recognition; Statistical analysis; Topology;

fLanguage

English

Publisher

ieee

Conference_Titel

Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on

Conference_Location

Philadelphia, PA

Print_ISBN

0-7803-3555-4

Type

conf

DOI

10.1109/ICSLP.1996.607791

Filename

607791