Improvement of a linear phonetic-context model for phoneme-based continuous speech recognition

Author

Abe, Y. ; Nakajima, K.

Author_Institution

Mitsubishi Electr. Corp., Kamakura, Japan

fYear

1991

fDate

14-17 Apr 1991

Firstpage

3669

Abstract

A model for coarticulator that considers changes in the degree of coarticularity effects according to the position in a phonetic segment, in a framework of the linear phonetic-context model (LPCM) is described. The position-dependent degree of the coarticulatory effects is represented by a halved Gaussian function, a function of the distance from the phonemic boundary. The standard deviation of the function controls a spread of the coarticulatory effects. The mean-squared error is minimized for a variety of speech data if the standard deviation is set near to 30 or 50 ms. Phoneme recognition experiments using sentences spoken with different speaking rates show that the improved LPCM increases the recognition rates for all cases, and is more robust to the difference of the speaking rate than the original LPCM

Keywords

speech recognition; statistical analysis; LPCM; coarticularity effects; coarticulation model; halved Gaussian function; linear phonetic-context model; mean-squared error; phoneme-based continuous speech recognition; phonemic boundary; phonetic segment position; speaking rates; standard deviation; Context modeling; Covariance matrix; Error correction; Information systems; Laboratories; Robustness; Speech recognition; Testing; Vectors; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference on

Conference_Location

Toronto, Ont.

ISSN

1520-6149

Print_ISBN

0-7803-0003-3

Type

conf

DOI

10.1109/ICASSP.1991.151072

Filename

151072