NN-SVS

Neural network-based singing voice synthesis library for research.

Demo

Neural network-based singing voice synthesis demo using kiritan_singing database (Japanese)

Audio samples

• Kiritan samples: https://soundcloud.com/r9y9/sets/dnn-based-singing-voice

Installation

python setup.py develop

Repository structure

• Core library: nnsvs/
• Command line programs: nnsvs/bin/ and its configurations nnsvs/bin/conf/
• Recipes: egs/

Python docstring style

https://sphinxcontrib-napoleon.readthedocs.io/en/latest/example_google.html

Recipes

A recipe is a set of scripts and configuraitons that are used to reproduce experiments. All the steps used to conduct experiments are provided in a self-contained way. Please have a look at the egs directory if you want to build your singing voice systems.

Background

As of Feb. 2020, NEUTRINO, a DNN-based singing voice synthesis tool, has started gaining its popularity in Japan. Because of the powerful DNN-based approach, users can create expressive and natural singing voices even without manual tuning which is typically required to achieve satisfactory quality using the existing tools.

While NEUTRINO is a great tool for creative purposes, it is not open-source software. In fact, there are only a few open-source toolkits to the best of our knowledge. To advance the singing voice synthesis research, we aim to provide a modern DNN-based singing voice synthesis tool for researchers and developers.

That being said, I was just curious to see if I can make a better one than NEUTRINO. We’ll see :)

History

See HISTORY.md

Related projects

• English support for nnsvs: https://github.com/DynamiVox/nnsvs-english-support
• NNSVSのモデルをUTAUで使えるようにするツール (UTAU plugin software powered by NNSVS): https://github.com/oatsu-gh/ENUNU
• NNSVS向け教師データ作成支援ツール Vocal2lab: https://github.com/148nasuka/Vocal2lab

References

• Y. Hono et al, "Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System", Journal of IEEE/ACM TASLP https://arxiv.org/abs/2108.02776
• Y. Hono et al, "Recent Development of the DNN-based Singing Voice Synthesis System — Sinsy," Proc. of APSIPA, 2017. (PDF)
• A fork of sinsy: https://github.com/r9y9/sinsy
• Python wrapper for sinsy: https://github.com/r9y9/pysinsy
• NEUTRINO: https://n3utrino.work/