NNSVS: A Neural Network-based Singing Voice Synthesis Toolkit

Abstract

This paper describes the design of NNSVS, an open-source software for neural network-based singing voice synthesis research. NNSVS is inspired by Sinsy, an open-source pioneer in singing voice synthesis research, and provides many additional features such as multi-stream models, autoregressive fundamental frequency models, and neural vocoders. Furthermore, NNSVS provides extensive documentation and numerous scripts to build complete singing voice synthesis systems. Experimental results demonstrate that our best system significantly outperforms our reproduction of Sinsy and other baseline systems. The toolkit is available at https://github.com/nnsvs/nnsvs.

Stats

• citations11
• S2 citations—
• github stars738
• HF likes0
• heat score13.83
• arxiv keyyamamoto2022nnsvs

Code

• nnsvs/nnsvs—

Related papers

• N-singer: A Non-autoregressive Korean Singing Voice Synthesis System For Pronunciation Enhancement (2021)8.60
• Muskits-espnet: A Comprehensive Toolkit For Singing Voice Synthesis In New Paradigm (2024)12.50
• Muskits: An End-to-end Music Processing Toolkit For Singing Voice Synthesis (2022)5.02
• Visinger2+: End-to-end Singing Voice Synthesis Augmented By Self-supervised Learning Representation (2024)4.52
• Singing Voice Synthesis Using Deep Autoregressive Neural Networks For Acoustic Modeling (2019)9.92
• Fast And High-quality Singing Voice Synthesis System Based On Convolutional Neural Networks (2019)8.82
• Visinger: Variational Inference With Adversarial Learning For End-to-end Singing Voice Synthesis (2021)12.99
• A Neural Parametric Singing Synthesizer (2017)10.97