A CIF-Based Speech Segmentation Method for Streaming E2E ASR.
Yuchun ShuHaoneng LuoShiliang ZhangLongbiao WangJianwu DangPublished in: IEEE Signal Process. Lett. (2023)
Keyphrases
- segmentation method
- automatic speech recognition
- speech recognition
- speech signal
- word error rate
- spontaneous speech
- region growing
- speech corpus
- broadcast news
- active contours
- image segmentation
- video segmentation
- object segmentation
- hidden markov models
- noisy environments
- energy function
- automated segmentation
- segmentation algorithm
- language model
- superpixels
- watershed segmentation
- method for image segmentation
- ultrasound image segmentation
- shape prior
- segmented images
- segmentation result
- region merging
- intensity information
- pattern recognition
- active contour model
- segmentation scheme
- image segmentation methods
- model based segmentation
- similarity measure
- edge information
- color features
- watershed transform
- non stationary
- image registration
- multiscale