Isolated word recognition using continuous state transition-probability and DP-matching

Author

Takara, Tomio

Author_Institution

Dept. of Electron. & Inf. Eng., Ryukyus Univ., Okinawa, Japan

fYear

1989

fDate

23-26 May 1989

Firstpage

274

Abstract

A report is presented on a novel application of the Markov model to an automatic speech-recognition system, in which the feature vectors of speech represent the states of the Markov model, the transition probability of the states is represented by a multidimensional normal density function of the feature vector, and the DP (dynamic programming) matching algorithm is used for calculating the optimum time sequence of the states. Based on experimentation with the system in a speaker-independent mode, using a vocabulary of ten Japanese single-digit numerals, the current system is shown to be more effective than recognizers using Maharanobis´ distance, Euclidean distance, or the absolute distance

Keywords

Markov processes; dynamic programming; probability; speech recognition; DP-matching; Japanese single-digit numerals; Markov model; automatic speech-recognition system; continuous state transition-probability; dynamic programming; feature vectors; isolated word recognition; multidimensional normal density function; optimum time sequence; speaker-independent mode; vocabulary; Automatic speech recognition; Density functional theory; Dynamic programming; Euclidean distance; Hidden Markov models; Markov processes; Multidimensional systems; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1989. ICASSP-89., 1989 International Conference on

Conference_Location

Glasgow

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1989.266418

Filename

266418