Realizing Tibetan speech synthesis by speaker adaptive training.
Hongwu YangKeiichiro OuraZhenye GanKeiichi TokudaPublished in: APSIPA (2013)
Keyphrases
- speech synthesis
- speech recognition
- prosodic features
- vocal tract
- text to speech
- acoustic models
- language model
- speaker verification
- supervised learning
- automatic speech recognition
- speech corpus
- data sets
- speaker dependent
- speech signal
- test set
- pattern recognition
- speaker diarization
- training process
- training set
- information retrieval