Muskits: an End-to-End Music Processing Toolkit for Singing Voice Synthesis

TL;DR

Muskits is an open-source, end-to-end music processing toolkit that enables fair comparison and advanced singing voice synthesis research across multiple models and scenarios.

Contribution

It introduces Muskits, the first platform supporting reproducible comparisons of SVS models and advanced functionalities like multilingual training and transfer learning.

Findings

Supports state-of-the-art SVS models including RNN, transformer, XiaoiceSing

Enables fair comparison of different SVS methods

Demonstrates effectiveness in single, multi-singer, multilingual, and transfer learning scenarios

Abstract

This paper introduces a new open-source platform named Muskits for end-to-end music processing, which mainly focuses on end-to-end singing voice synthesis (E2E-SVS). Muskits supports state-of-the-art SVS models, including RNN SVS, transformer SVS, and XiaoiceSing. The design of Muskits follows the style of widely-used speech processing toolkits, ESPnet and Kaldi, for data prepossessing, training, and recipe pipelines. To the best of our knowledge, this toolkit is the first platform that allows a fair and highly-reproducible comparison between several published works in SVS. In addition, we also demonstrate several advanced usages based on the toolkit functionalities, including multilingual training and transfer learning. This paper describes the major framework of Muskits, its functionalities, and experimental results in single-singer, multi-singer, multilingual, and transfer learning scenarios. The toolkit is publicly available at https://github.com/SJTMusicTeam/Muskits.