Large vocabulary audio-visual speech recognition using active shape models
Authors:
- N. RajputNRN. Rajput
- L.V. SubramaniamLSL.V. Subramaniam
- 11 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 106-109
Abstract
Orthogonal information present in the video signal associated with the audio helps in improving the accuracy of a speech recognition system. Audio-visual speech recognition involves extraction of both the audio as well as visual features from the input signal. Extraction of visual parameters is done by the recognition of speech dependent features from the video sequence. The paper uses geometrical features to describe the lip shapes. Curve-based active shape models are used to extract the geometry. These geometrically represented visual parameters are used along with the audio cepstral features to perform an audio-visual classification. It is shown that the bimodal system presented gives an improvement in the classification results over classification using only the audio featuresKeywords
This publication has 7 references indexed in Scilit:
- Discriminative training of HMM stream exponents for audio-visual speech recognition2002
- Audio-visual large vocabulary continuous speech recognition in the broadcast domain1999
- Visual speech recognition using active shape models and hidden Markov models1996
- Feature extraction from faces using deformable templatesInternational Journal of Computer Vision, 1992
- Active Shape Models - 'smart snakes'1992
- Training Models of Shape from Sets of Examples1992
- Snakes: Active contour modelsInternational Journal of Computer Vision, 1988