Shared-distribution hidden Markov models for speech recognition

Author

Hwang, Mei-Yuh ; Huang, Xuedong

Author_Institution

Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA

Volume

1

Issue

4

fYear

1993

fDate

10/1/1993 12:00:00 AM

Firstpage

414

Lastpage

420

Abstract

A shared-distribution hidden Markov model (HMM) is presented for speaker-independent continuous speech recognition. The output distributions across different phonetic HMMs are shared with each other when they exhibit acoustic similarity. This sharing provides the freedom to use a larger number of Markov states for each phonetic model. Although an increase in the number of states will increase the total number of free parameters, with distribution sharing one can collapse redundant states while maintaining necessary ones. The shared-distribution model reduced the word error rate on the DARPA Resource Management task by 20% in comparison with the generalized-triphone model

Keywords

acoustic signal processing; hidden Markov models; speech analysis and processing; speech recognition; DARPA Resource Management task; HMM; acoustic similarity; generalized-triphone model; phonetics; redundant states collapse; shared-distribution hidden Markov model; speaker-independent continuous speech recognition; word error rate reduction; Context modeling; Error analysis; Hidden Markov models; Interpolation; Iterative algorithms; Parameter estimation; Resource management; Speech recognition; Stochastic processes; Training data;

fLanguage

English

Journal_Title

Speech and Audio Processing, IEEE Transactions on

Publisher

ieee

ISSN

1063-6676

Type

jour

DOI

10.1109/89.242487

Filename

242487