English

Muskits-ESPnet: A Comprehensive Toolkit for Singing Voice Synthesis in New Paradigm

Sound 2024-10-14 v2 Audio and Speech Processing

Abstract

This research presents Muskits-ESPnet, a versatile toolkit that introduces new paradigms to Singing Voice Synthesis (SVS) through the application of pretrained audio models in both continuous and discrete approaches. Specifically, we explore discrete representations derived from SSL models and audio codecs and offer significant advantages in versatility and intelligence, supporting multi-format inputs and adaptable data processing workflows for various SVS models. The toolkit features automatic music score error detection and correction, as well as a perception auto-evaluation module to imitate human subjective evaluating scores. Muskits-ESPnet is available at \url{https://github.com/espnet/espnet}.

Keywords

Cite

@article{arxiv.2409.07226,
  title  = {Muskits-ESPnet: A Comprehensive Toolkit for Singing Voice Synthesis in New Paradigm},
  author = {Yuning Wu and Jiatong Shi and Yifeng Yu and Yuxun Tang and Tao Qian and Yueqian Lin and Jionghao Han and Xinyi Bai and Shinji Watanabe and Qin Jin},
  journal= {arXiv preprint arXiv:2409.07226},
  year   = {2024}
}

Comments

Accepted by ACMMM 2024 demo track