Phonemic segmentation of fluent speech

Author

Grayden, David B. ; Scordilis, Michael S.

Author_Institution

Melbourne Univ., Parkville, Vic., Australia

Volume

i

fYear

1994

fDate

19-22 Apr 1994

Abstract

A hierarchical approach to phonemic segmentation of continuous, speaker-independent speech is presented. Each sentence is divided into distinct obstruent and sonorant regions using a Bayesian decision surface. Rules are then used to make context specific corrections with these regions. Finally, finer segmentation is performed using a number of rules specific to obstruent and sonorant boundaries. Around 80% of the boundaries are located with an insertion rate of 12%. The developed system is suitable for use in phoneme recognition and automatic labelling of speech

Keywords

Bayes methods; acoustic signal processing; speech processing; speech recognition; Bayesian decision surface; automatic speech labelling; continuous speaker-independent speech; continuous speech recognition; fluent speech; insertion rate; obstruent boundaries; obstruent regions; phoneme recognition; phonemic segmentation; sentence; sonorant boundaries; sonorant regions; Acoustic testing; Automatic speech recognition; Bayesian methods; Data mining; Frequency; Labeling; Low pass filters; Microwave integrated circuits; Spatial databases; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference on

Conference_Location

Adelaide, SA

ISSN

1520-6149

Print_ISBN

0-7803-1775-0

Type

conf

DOI

10.1109/ICASSP.1994.389352

Filename

389352