Improved MLLR speaker adaptation using confidence measures for conversational speech recognition.
Michael PitzFrank WesselHermann NeyPublished in: INTERSPEECH (2000)
Keyphrases
- speaker adaptation
- speech recognition
- confidence measures
- automatic speech recognition
- speech recognizer
- ground truth
- stereo vision
- language model
- hidden markov models
- speaker independent
- maximum likelihood
- pattern recognition
- confidence measure
- speech synthesis
- speaker identification
- multi modal
- speech signal
- speaker dependent
- noisy environments
- optical flow
- spoken language
- speaker recognition
- feature extraction
- language processing
- vision system
- speech recognition systems
- neural network