Dynamic Speaker Representations Adjustment and Decoder Factorization for Speaker Adaptation in End-to-End Speech Synthesis.
Ruibo FuJianhua TaoZhengqi WenJiangyan YiTao WangChunyu QiangPublished in: INTERSPEECH (2020)
Keyphrases
- end to end
- speech synthesis
- speech recognition
- speaker adaptation
- vocal tract
- prosodic features
- speaker dependent
- speaker independent
- rate allocation
- speech recognizer
- pattern recognition
- automatic speech recognition
- language model
- hidden markov models
- text to speech
- speech signal
- scalable video
- congestion control
- noisy environments
- speaker identification
- speech recognition systems
- maximum likelihood
- speaker recognition
- speaker verification
- neural network
- low complexity
- feature extraction