Maximum conditional mutual information projection for speech recognition.
Mohamed Kamal OmarMark Hasegawa-JohnsonPublished in: INTERSPEECH (2003)
Keyphrases
- speech recognition
- conditional mutual information
- mutual information
- hidden markov models
- language model
- speech synthesis
- automatic speech recognition
- pattern recognition
- speech processing
- selection criterion
- speech signal
- speech recognizer
- speech recognition technology
- speech understanding
- speech recognition systems
- noisy environments
- speaker identification
- keyword spotting
- similarity measure
- speech recognition errors
- speaker dependent
- speaker diarization
- mobile devices
- speech retrieval
- feature selection
- speech recognizers