Multi-stream hidden Markov models and wavelets for vocal tract disease detection and pronunciation correction.
Evgeny I. BovbelIgor E. KheidorovY. V. PachkovskiPublished in: DSP (2002)
Keyphrases
- hidden markov models
- multi stream
- speech recognition
- vocal tract
- speech synthesis
- speech signal
- noisy environments
- automatic speech recognition
- conditional random fields
- speech enhancement
- sequential data
- speaker independent
- multiresolution
- audio visual
- acoustic models
- speech recognizer
- machine learning
- image acquisition
- wavelet transform
- low level
- image processing