Integration of acoustic and visual speech signals using neural networks.
Ben P. YuhasMoise H. Goldstein Jr.Terrence J. SejnowskiPublished in: IEEE Commun. Mag. (1989)
Keyphrases
- speech signal
- neural network
- speech sounds
- acoustic features
- sound source
- speech recognition
- automatic speech recognition
- visual speech
- vocal tract
- pattern recognition
- background noise
- speaker identification
- low level
- automatic speech recognition systems
- noisy speech
- visual features
- hidden markov models
- formant frequencies
- spectral analysis
- noisy environments
- visual information
- blind source separation
- sound signals
- genetic algorithm
- linear prediction
- speech enhancement
- speech quality
- non stationary
- input image
- image processing