KLT-based classified VQ for the speech signal.
Moo Young KimW. Bastiaan KleijnPublished in: ICASSP (2002)
Keyphrases
- speech signal
- speaker recognition
- vector quantization
- speech recognition
- automatic speech recognition
- speaker identification
- vocal tract
- linear prediction
- non stationary
- image compression
- image coding
- background noise
- spectral analysis
- hidden markov models
- automatic speech recognition systems
- noisy environments
- vector quantizer
- speech quality
- frame rate
- speech enhancement
- cepstral coefficients
- hearing aids
- neural network
- inter frame
- noisy images
- gaussian mixture model
- face recognition
- image sequences
- fundamental frequency
- image processing