From vocalic detection to automatic emergence of vowel systems

Author

Pellegrino, Franqois ; Andre-Obrecht, Régine

Author_Institution

IRIT, Toulouse, France

Volume

3

fYear

1997

fDate

21-24 Apr 1997

Firstpage

1651

Abstract

This paper presents our work on vowel system detection as part of a project of automatic language identification using phonological typologies. We have developed a vowel detection algorithm based on spectral analysis of the acoustic signal and requiring no learning stage. It has been tested with two telephone speech corpora: with a French corpus provided by the CNET, 7.4% of detections are false while about 25% of the vowels present in the signal are not found; and experiments with 5 languages of the OGI-TS corpus result in 88.1 % of correct detection and about 15 % of non-detection. We also present the vector quantization (VQ) LBG-Rissanen (1980, 1983) algorithm that we use for vowel system modeling. Preliminary experiments are reported

Keywords

feature extraction; natural languages; spectral analysis; speech processing; speech recognition; vector quantisation; French corpus; OGI-TS corpus; VQ LBG-Rissanen algorithm; VQ codebook; acoustic signal; automatic emergence; automatic language identification; correct detection; experiments; false detections; phonological typologies; spectral analysis; telephone speech corpora; vector quantization; vocalic detection; vowel detection algorithm; vowel system detection; vowel system modeling; Acoustic signal detection; Acoustic testing; Adaptive filters; Detection algorithms; Hidden Markov models; Natural languages; Spectral analysis; Speech analysis; Telephony; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on

Conference_Location

Munich

ISSN

1520-6149

Print_ISBN

0-8186-7919-0

Type

conf

DOI

10.1109/ICASSP.1997.598828

Filename

598828