Isolated spanish digit recognition based on audio-visual features

The performance of classical speech recognition techniques based on audio features is degraded in noisy environments. The inclu-sion of visual features related to mouth movements into the recogni-tion process improves the performance of the system. This paper proposes an isolated word speech recogni...

Descripción completa

Detalles Bibliográficos
Autores principales: Sad, Gonzalo D., Terissi, Lucas D., Gómez, Juan Carlos
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2013
Materias:
Ciencias Informáticas
Informática
speech recognition
audio-visual speech feature
Speech recognition and synthesis
Object recognition
Hidden Markov Models
Markov processes
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/31841
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-31841
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Informática
speech recognition
audio-visual speech feature
Speech recognition and synthesis
Object recognition
Hidden Markov Models
Markov processes
spellingShingle Ciencias Informáticas
Informática
speech recognition
audio-visual speech feature
Speech recognition and synthesis
Object recognition
Hidden Markov Models
Markov processes
Sad, Gonzalo D.
Terissi, Lucas D.
Gómez, Juan Carlos
Isolated spanish digit recognition based on audio-visual features
topic_facet Ciencias Informáticas
Informática
speech recognition
audio-visual speech feature
Speech recognition and synthesis
Object recognition
Hidden Markov Models
Markov processes
description The performance of classical speech recognition techniques based on audio features is degraded in noisy environments. The inclu-sion of visual features related to mouth movements into the recogni-tion process improves the performance of the system. This paper proposes an isolated word speech recognition system based on audio-visual features. The proposed system combines three classifiers based on au-dio, visual and audio-visual information, respectively. An audio-visual database composed by the utterances of the digits (in Spanish language) is employed to test the proposed system. The experimental results show a significant improvement on the recognition rates through a wide range of signal-to-noise ratios.
format Objeto de conferencia
Objeto de conferencia
author Sad, Gonzalo D.
Terissi, Lucas D.
Gómez, Juan Carlos
author_facet Sad, Gonzalo D.
Terissi, Lucas D.
Gómez, Juan Carlos
author_sort Sad, Gonzalo D.
title Isolated spanish digit recognition based on audio-visual features
title_short Isolated spanish digit recognition based on audio-visual features
title_full Isolated spanish digit recognition based on audio-visual features
title_fullStr Isolated spanish digit recognition based on audio-visual features
title_full_unstemmed Isolated spanish digit recognition based on audio-visual features
title_sort isolated spanish digit recognition based on audio-visual features
publishDate 2013
url http://sedici.unlp.edu.ar/handle/10915/31841
work_keys_str_mv AT sadgonzalod isolatedspanishdigitrecognitionbasedonaudiovisualfeatures
AT terissilucasd isolatedspanishdigitrecognitionbasedonaudiovisualfeatures
AT gomezjuancarlos isolatedspanishdigitrecognitionbasedonaudiovisualfeatures
bdutipo_str Repositorios
_version_ 1764820468902133761

Ejemplares similares