Other Software New chinese AI singing synth in development ByteSing

[Prism]

New Chinese ai voice synthesiser ByteSing is in development. ByteSing uses duration allocated encoder-decoder acoustic models and WaveRNN vocoders. It has along way to go but the results are amazing.

paper

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

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...

arxiv.org

demos

TTS demos

bytesings.github.io

 

[Leon]

This is super cool!! The demos sound amazing!

 

[lIlI]

Sounds great! The second singer is very expressive.

 

[aru ii]

Where can I download it

 

[peaches2217]

Where can I download it

To the best of my knowledge, it's not a publicly available synth, in a similar vein to VOCALOID AI. I hope a version of it will be made available someday though! It seems very promising.

 

[Prism]

It's not comercial available yet