Detalle del congreso

Autores: Gonzalo Sad; Lucas D. Terissi; Juan C. Gómez.

Resumen: The performance of classical speech recognition techniques based on audio features is degraded in noisy environments. The inclusion of visual features related to mouth movements into the recognition 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 audio, 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.

Tipo de reunión: Conferencia.

Tipo de trabajo: Artículo Completo.

Producción: Isolated Spanish Digit Recognition based on Audio-Visual Features.

Reunión científica: XIX Congreso Argentino de Ciencias de la Computación - CACIC 2013.

Lugar: Mar del Plata.

Institución organizadora: Red de Universidades Nacionales con carreras en Informática (RedUNCI).

Publicado: Sí

Lugar publicación: Mar del Plata

Mes de reunión: 10

Año: 2013.

Página web: aquí