Simultaneous speech segmentation and phoneme recognition using dynamic programming.
Raminder Singh BajwaRobert Michael OwensThomas P. KelliherPublished in: ICASSP (1996)
Keyphrases
- dynamic programming
- speech recognition
- speech synthesis
- automatic speech recognition
- segmentation algorithm
- image segmentation
- automatic speech recognition systems
- level set
- segmentation accuracy
- speaker dependent
- segmentation method
- speech signal
- image analysis
- hidden markov models
- fully automatic
- text to speech
- shape prior
- speech recognizer
- fully unsupervised
- phoneme recognition
- region growing
- single machine
- greedy algorithm
- background subtraction
- medical images
- audio visual
- automatic segmentation
- coarse to fine
- spoken language
- speaker recognition
- audio signals
- energy function
- scheduling problem
- dp matching
- feature vectors
- feature extraction