DeepAI AI Chat
Log In Sign Up

ByteSing: A Chinese Singing Voice Synthesis System Using Duration Allocated Encoder-Decoder Acoustic Models and WaveRNN Vocoders

by   Yu Gu, et al.

This paper presents ByteSing, a Chinese singing voice synthesis (SVS) system based on duration allocated Tacotron-like acoustic models and WaveRNN neural vocoders. Different from the conventional SVS models, the proposed ByteSing employs Tacotron-like encoder-decoder structures as the acoustic models, in which the CBHG models and recurrent neural networks (RNNs) are explored as encoders and decoders respectively. Meanwhile an auxiliary phoneme duration prediction model is utilized to expand the input sequence, which can enhance the model controllable capacity, model stability and tempo prediction accuracy. WaveRNN neural vocoders are also adopted as neural vocoders to further improve the voice quality of synthesized songs. Both objective and subjective experimental results prove that the SVS method proposed in this paper can produce quite natural, expressive and high-fidelity songs by improving the pitch and spectrogram prediction accuracy and the models using attention mechanism can achieve best performance.


Pitch Preservation In Singing Voice Synthesis

Suffering from limited singing voice corpus, existing singing voice synt...

Singing Voice Synthesis Using Deep Autoregressive Neural Networks for Acoustic Modeling

This paper presents a method of using autoregressive neural networks for...

WeSinger: Data-augmented Singing Voice Synthesis with Auxiliary Losses

In this paper, we develop a new multi-singer Chinese neural singing voic...

An Empirical Study on End-to-End Singing Voice Synthesis with Encoder-Decoder Architectures

With the rapid development of neural network architectures and speech pr...

Attention and Encoder-Decoder based models for transforming articulatory movements at different speaking rates

While speaking at different rates, articulators (like tongue, lips) tend...

Singing-Tacotron: Global duration control attention and dynamic filter for End-to-end singing voice synthesis

End-to-end singing voice synthesis (SVS) is attractive due to the avoida...

Sequence-to-sequence Singing Voice Synthesis with Perceptual Entropy Loss

The neural network (NN) based singing voice synthesis (SVS) systems requ...