On the use of phone duration and segmental processing to label speech signal.
Philippe DepambourRégine André-ObrechtBernard DelyonPublished in: EUROSPEECH (1997)
Keyphrases
- speech signal
- speech recognition
- hidden markov models
- automatic speech recognition
- spectral analysis
- automatic speech recognition systems
- speaker identification
- non stationary
- linear prediction
- vocal tract
- noisy environments
- background noise
- neural network
- speaker recognition
- speech enhancement
- speech quality
- image quality
- bayesian networks
- feature extraction
- fundamental frequency
- hearing aids
- face recognition