Speaker identification in shouted talking environments based on novel Third-Order Hidden Markov Models.
Ismail ShahinPublished in: ICAILP (2014)
Keyphrases
- hidden markov models
- speaker identification
- speech recognition
- speech signal
- speech processing
- speaker independent
- gaussian mixture model
- automatic speech recognition
- audio signals
- noisy environments
- feature extraction
- sequential data
- speech recognizer
- speaker dependent
- pattern recognition
- continuous hidden markov models
- reinforcement learning
- multiscale
- visual speech
- neural network
- denoising
- training set