Robust gender-dependent acoustic-phonetic modelling in continuous speech recognition based on a new automatic male/female classification

Author

Vergin, Ravarol ; Farhat, Atarshid ; O´Shaughnessy, D.

Author_Institution

INRS Telecommun., Ile des Soeurs, Que., Canada

Volume

2

fYear

1996

fDate

3-6 Oct 1996

Firstpage

1081

Abstract

The authors present a new automatic male/female classification method based on the location in the frequency domain of the first two formants. This classification is based on a new automatic formant extraction which is faster than a peak picking technique. Gender-dependent acoustic-phonetic models stemming from this classification are used in the INRS continuous speech recognition system with the ATIS corpora. An improvement of 14% is obtained with these models in comparison to the baseline speaker-independent system

Keywords

feature extraction; gender issues; speech recognition; ATIS corpora; INRS continuous speech recognition system; automatic formant extraction; automatic male/female classification; baseline speaker-independent system; continuous speech recognition; frequency domain location; robust gender-dependent acoustic-phonetic modelling; Acoustic signal detection; Automatic speech recognition; Bandwidth; Business; Frequency; Iterative algorithms; Loudspeakers; Robustness; Speech recognition; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on

Conference_Location

Philadelphia, PA

Print_ISBN

0-7803-3555-4

Type

conf

DOI

10.1109/ICSLP.1996.607793

Filename

607793