Combining Visual and Acoustic Speech Signals with a Neural Network Improves Intelligibility.
Terrence J. SejnowskiBen P. YuhasMoise H. Goldstein Jr.Robert E. JenkinsPublished in: NIPS (1989)
Keyphrases
- speech signal
- speech recognition
- neural network
- acoustic features
- speech sounds
- visual speech
- sound source
- automatic speech recognition
- noisy speech
- speaker identification
- hidden markov models
- automatic speech recognition systems
- linear prediction
- noisy environments
- background noise
- visual features
- visual information
- vocal tract
- formant frequencies
- spectral analysis
- mel frequency cepstral coefficients
- sound signals
- pattern recognition
- blind source separation
- signal to noise ratio
- language model
- speech enhancement
- multi modal