PSST! Prosodic Speech Segmentation with Transformers.
Nathan RollCalbert GrahamSimon ToddPublished in: CoRR (2023)
Keyphrases
- speech recognition
- text to speech synthesis
- text to speech
- segmentation method
- multiscale
- segmentation algorithm
- brain mri
- region growing
- speech signal
- optimal segmentation
- level set
- object segmentation
- prosodic features
- image segmentation
- speech synthesis
- grey level
- pixel level
- audio visual
- shape prior
- medical imaging
- multiple objects
- word segmentation
- fully unsupervised
- motion segmentation
- segmentation errors
- medical images
- multiresolution
- endpoint detection
- computer vision