Speech recognition using stochastic phonemic segment model based on phoneme segmentation.
Chieko FuruichiKatsura AizawaKazuhiko InouePublished in: Systems and Computers in Japan (2000)
Keyphrases
- fully unsupervised
- speech recognition
- speech sounds
- speech synthesis
- automatic speech recognition
- automatic speech recognition systems
- optimal segmentation
- speech segments
- speech signal
- hidden markov models
- speaker dependent
- phoneme recognition
- speech recognizer
- vocal tract
- finite state transducers
- acoustic features
- image segments
- pattern recognition
- prosodic features
- multiscale
- image segmentation