Prosodic word boundary detection using statistical modeling of moraic fundamental frequency contours and its use for continuous speech recognition.
Koji IwanoKeikichi HirosePublished in: ICASSP (1999)
Keyphrases
- boundary detection
- statistical modeling
- continuous speech recognition
- fundamental frequency
- closed contours
- statistical models
- prosodic features
- image segmentation
- speech signal
- speech recognition
- object detection and recognition
- active contours
- detection algorithm
- berkeley segmentation dataset
- statistical model
- three dimensional
- speaker verification
- text to speech
- computer vision
- pairwise
- neural network
- nonparametric bayesian