On variable-scale piecewise stationary spectral analysis of speech signals for ASR.
Vivek TyagiChristian WellekensHervé BourlardPublished in: INTERSPEECH (2005)
Keyphrases
- speech signal
- spectral analysis
- non stationary
- automatic speech recognition
- speech recognition
- noisy environments
- background noise
- linear prediction
- vocal tract
- hidden markov models
- blind source separation
- scale space
- automatic speech recognition systems
- spectral features
- speech enhancement
- speech sounds
- heart rate variability
- speech synthesis
- multiresolution
- sound signals
- multiscale