Advanced unsupervised joint prosody labeling and modeling for Mandarin speech and its application to prosody generation for TTS.
Chen-Yu ChiangSin-Horng ChenYih-Ru WangPublished in: INTERSPEECH (2009)
Keyphrases
- text to speech
- prosodic features
- speech synthesis
- speech recognition
- speaker verification
- unsupervised learning
- supervised learning
- word processing
- spontaneous speech
- active learning
- data driven
- image segmentation
- human machine interaction
- semi supervised
- unsupervised manner
- generation process
- weakly supervised
- restricted boltzmann machine
- pattern recognition
- information retrieval