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: ISCSLP (2021)
Keyphrases
- video codec
- decoding process
- acoustic models
- distributed video coding
- noisy channel
- error control
- low complexity
- discriminative training
- wyner ziv
- successive approximation
- rate distortion
- speech recognition
- video coding
- distributed source coding
- hidden markov models
- motion estimation
- automatic speech recognition
- music information retrieval
- broadcast news
- bit rate
- word segmentation
- speech recognizer
- training data
- pattern recognition
- image processing
- motion vectors
- neural network