A controlled study of the suitability and limitations of static modeling of speech

Author

Chan, Tat-Chung ; Tat-Chung Chan

Author_Institution

Dept. of Comput. Sci., Hong Kong Univ., Hong Kong

fYear

1992

Firstpage

272

Abstract

A static model (SM) in the form of a single vector is proposed to represent the temporal properties of a sequence of speech feature vectors. In contrast to a hidden Markov model which captures the conditional probabilities of state transitions of consecutive observations x_t and x_t+1 over time, an SM captures their average joint probabilities of belonging to a pair of phonetic classes ω_i and ω_j without any Markovian assumption. An artificial vocabulary of ten words is designed to study the limitations of SM. Experimental results indicate that apart from a rather mild limitation of SM in handling certain types of vocabulary, SM performs better in terms of recognition rate as far as isolated word recognition is concerned

Keywords

speech recognition; artificial vocabulary; average joint probabilities; conditional probabilities; hidden Markov model; phonetic classes; speech feature vectors; state transitions; static modeling of speech; temporal properties; Acoustic testing; Computer science; Databases; Hidden Markov models; Samarium; Speech recognition; System testing; Training data; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

TENCON '92. ''Technology Enabling Tomorrow : Computers, Communications and Automation towards the 21st Century.' 1992 IEEE Region 10 International Conference.

Conference_Location

Melbourne, Vic.

Print_ISBN

0-7803-0849-2

Type

conf

DOI

10.1109/TENCON.1992.271941

Filename

271941