Acoustic modeling based on the MDL principle for speech recognition.
Koichi ShinodaTakao WatanabePublished in: EUROSPEECH (1997)
Keyphrases
- speech recognition
- mdl principle
- speech recognition systems
- speaker independent
- speech recognizers
- hidden markov models
- acoustic models
- speech recognizer
- speech synthesis
- pattern recognition
- speech understanding
- language model
- speech signal
- automatic speech recognition
- speech processing
- speaker identification
- minimum description length
- speech recognition technology
- noisy speech
- noisy environments
- keyword spotting
- information theory
- neural network
- information retrieval
- speaker dependent
- machine learning
- learning algorithm
- speech retrieval