An Empirical Study on End-to-End Singing Voice Synthesis with Encoder-Decoder Architectures
This work enables non-experts to produce singing voice by arranging pitches, lyrics, and beats, but it appears incremental as it applies existing encoder-decoder architectures to this domain.
The paper tackled improving the quality and efficiency of singing voice synthesis by using encoder-decoder neural models and vocoders, achieving smooth, clear, and natural singing voice close to real human voice.
With the rapid development of neural network architectures and speech processing models, singing voice synthesis with neural networks is becoming the cutting-edge technique of digital music production. In this work, in order to explore how to improve the quality and efficiency of singing voice synthesis, in this work, we use encoder-decoder neural models and a number of vocoders to achieve singing voice synthesis. We conduct experiments to demonstrate that the models can be trained using voice data with pitch information, lyrics and beat information, and the trained models can produce smooth, clear and natural singing voice that is close to real human voice. As the models work in the end-to-end manner, they allow users who are not domain experts to directly produce singing voice by arranging pitches, lyrics and beats.