Quality enhancement of CELP coded speech by using an MFCC based Gaussian mixture model.
D. G. RazaC. F. ChanPublished in: INTERSPEECH (2003)
Keyphrases
- gaussian mixture model
- linear predictive
- mel frequency cepstral coefficients
- speaker identification
- speaker recognition
- mixture model
- feature vectors
- cepstral coefficients
- em algorithm
- expectation maximization
- gaussian mixture
- background subtraction
- speech signal
- speech recognition
- gaussian distribution
- maximum likelihood
- speech quality
- probabilistic neural network
- feature space
- reinforcement learning
- audio visual
- automatic speech recognition
- hidden markov models
- gaussian mixture modeling