ByteSing: A Chinese Singing Voice Synthesis System Using Duration Allocated Encoder-Decoder Acoustic Models and WaveRNN Vocoders.
Yu GuXiang YinYonghui RaoYuan WanBenlai TangYang ZhangJitong ChenYuxuan WangZejun MaPublished in: CoRR (2020)
Keyphrases
- video codec
- decoding process
- distributed video coding
- acoustic models
- error control
- low complexity
- noisy channel
- wyner ziv
- successive approximation
- speech recognition
- rate distortion
- discriminative training
- distributed source coding
- video coding
- hidden markov models
- motion estimation
- word segmentation
- speech recognizer
- broadcast news
- bit rate
- machine learning
- packet loss
- pattern recognition
- image sequences