Lowresource speech recognition with automatically learned sparse inverse covariance matrices.
Weibin ZhangPascale FungPublished in: ICASSP (2012)
Keyphrases
- speech recognition
- covariance matrices
- automatically learned
- covariance matrix
- maximum likelihood
- vector space
- hidden markov models
- gaussian mixture model
- language model
- speaker identification
- gaussian distribution
- speech synthesis
- speech signal
- speech recognizer
- automatic speech recognition
- pattern recognition
- distance measure
- noisy environments
- gaussian mixture
- speech recognition technology
- feature vectors
- speech recognition systems
- high dimensional
- sparse representation
- linear classifiers
- sample size
- support vector machine
- data mining
- speaker independent
- neural network