Memory space reduction for hidden Markov models in low-resource speech recognition systems.
Sergey AstrovPublished in: INTERSPEECH (2002)
Keyphrases
- hidden markov models
- memory space
- speech recognition
- speech recognition systems
- memory requirements
- speech recognizer
- speaker independent
- automatic speech recognition
- conditional random fields
- high efficiency
- sequential data
- markov models
- speech signal
- noisy environments
- neural network
- pattern recognition
- feature extraction
- language model
- hidden states
- information extraction
- baum welch