Additional use of phoneme duration hypotheses in automatic speech segmentation.
Karlheinz StöberWolfgang HessPublished in: ICSLP (1998)
Keyphrases
- speech recognition
- speech synthesis
- fully automatic
- visual speech recognition
- automatic speech recognition systems
- automatic speech recognition
- level set
- image segmentation
- statistical classification
- speech signal
- segmentation algorithm
- segmentation method
- hypothesis formation
- phoneme recognition
- text to speech
- semi automatic
- energy function
- hidden markov models
- speaker dependent
- speech sounds
- visual speech
- speech recognizer
- multiscale
- image analysis
- vocal tract
- spoken language
- segmentation accuracy
- features extraction
- speech recognition systems
- prosodic features
- context dependent
- symbol recognition
- automatic segmentation
- medical imaging
- language model
- markov random field