Automatic Training Set Segmentation for Multi-pass Speech Recognition.
Mark Z. MaoVincent VanhouckeBrian StropePublished in: ICASSP (1) (2005)
Keyphrases
- speech recognition
- training set
- visual speech recognition
- fully automatic
- hidden markov models
- speech synthesis
- speech processing
- speech recognizer
- image segmentation
- language model
- speech understanding
- automatic speech recognition
- speech signal
- speech recognition technology
- pattern recognition
- noisy environments
- training data
- speaker identification
- speaker independent
- classification accuracy
- speech recognition systems
- handwriting recognition
- speaker diarization
- keyword spotting
- speaker recognition
- word segmentation
- low contrast
- speech recognition errors
- edge detection
- speech recognizers
- isolated word