SYNTACC : Synthesizing Multi-Accent Speech By Weight Factorization.
Tuan-Nam NguyenNgoc-Quan PhamAlexander WaibelPublished in: ICASSP (2023)
Keyphrases
- speech recognition
- spoken language
- automatic speech recognition
- language model
- speech signal
- broadcast news
- speech synthesis
- matrix factorization
- spontaneous speech
- low rank
- real time
- singular value decomposition
- face recognition
- semi supervised
- hidden markov models
- pairwise
- video sequences
- weighting scheme
- dialogue system
- noisy environments
- multimedia
- speaker verification
- computer vision
- neural network