Model-based multirate representation of speech signals and its application to recovery of missing speech packets.
You-Li ChenBor-Sen ChenPublished in: IEEE Trans. Speech Audio Process. (1997)
Keyphrases
- speech signal
- speech recognition
- automatic speech recognition
- automatic speech recognition systems
- vocal tract
- speech enhancement
- linear prediction
- speech quality
- noisy environments
- non stationary
- speaker identification
- packet loss
- hidden markov models
- additive noise
- speech sounds
- spectral analysis
- filter bank
- background noise
- speaker recognition
- fundamental frequency
- spectral subtraction
- formant frequencies
- speech synthesis
- acoustic features
- subband
- text to speech
- gaussian mixture model
- denoising
- multiscale
- computer vision