European and American Audio-Visual Speech Recognition, Using SVM in Portuguese Language

Author

de Andrade Bresolin, A. ; Da Silva Freitas, Diamantino Rui ; Neto, Adrião Duarte Dória ; Alsina, Pablo Javier

Author_Institution

UTFPR, Technol. Fed. Univ. of the Parana, Curitiba, Brazil

fYear

2008

fDate

25-27 March 2008

Firstpage

511

Lastpage

511

Abstract

This paper proposes an audio-visual speech recognition system using SVM (support vector machine) in European and American Portuguese language. The main objective in this work is to find a model that can be used in both languages. Furthermore, two new methods to extract the mouth region (ROI-Region of interest) and lip contour are presented. Two audio and four video features are used in the experiments. These features are combined in pairs, totalizing eight tests in the speaker dependent-case. Experiments were performed at various SNRs (0-40dB) with additive white Gaussian noise. The results showed that the proposed method can be used in both languages without any adaption.

Keywords

AWGN; audio signal processing; linguistics; speech recognition; support vector machines; video signal processing; American Portuguese language; European language; SVM; additive white Gaussian noise; audio-visual speech recognition system; support vector machine; Acoustics; Data compression; Data engineering; Mel frequency cepstral coefficient; Mouth; Natural languages; Principal component analysis; Speech recognition; Support vector machines; Testing; Image Pattern Recognition; Neural Networks; Speech Recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Data Compression Conference, 2008. DCC 2008

Conference_Location

Snowbird, UT

ISSN

1068-0314

Print_ISBN

978-0-7695-3121-2

Type

conf

DOI

10.1109/DCC.2008.32

Filename

4483338