A variational approach to robust maximum likelihood estimation for speech recognition.
Mohamed Kamal OmarPublished in: INTERSPEECH (2007)
Keyphrases
- speech recognition
- maximum likelihood estimation
- noisy environments
- em algorithm
- hidden markov models
- maximum likelihood
- speech signal
- speech recognizer
- speech synthesis
- speech processing
- parameter estimation
- automatic speech recognition
- pattern recognition
- language model
- expectation maximization
- probability distribution
- speaker identification
- density function
- speech recognition technology
- speech recognition systems
- signal processing
- speaker adaptation
- speaker independent
- digital video library
- speech retrieval
- isolated word
- neural network
- mixture model
- unsupervised learning
- least squares
- video sequences
- image processing
- computer vision