English

Sequence-to-sequence Singing Voice Synthesis with Perceptual Entropy Loss

Audio and Speech Processing 2021-03-01 v2 Machine Learning Sound

Abstract

The neural network (NN) based singing voice synthesis (SVS) systems require sufficient data to train well and are prone to over-fitting due to data scarcity. However, we often encounter data limitation problem in building SVS systems because of high data acquisition and annotation costs. In this work, we propose a Perceptual Entropy (PE) loss derived from a psycho-acoustic hearing model to regularize the network. With a one-hour open-source singing voice database, we explore the impact of the PE loss on various mainstream sequence-to-sequence models, including the RNN-based, transformer-based, and conformer-based models. Our experiments show that the PE loss can mitigate the over-fitting problem and significantly improve the synthesized singing quality reflected in objective and subjective evaluations.

Keywords

Cite

@article{arxiv.2010.12024,
  title  = {Sequence-to-sequence Singing Voice Synthesis with Perceptual Entropy Loss},
  author = {Jiatong Shi and Shuai Guo and Nan Huo and Yuekai Zhang and Qin Jin},
  journal= {arXiv preprint arXiv:2010.12024},
  year   = {2021}
}

Comments

Accepted by ICASSP2021

R2 v1 2026-06-23T19:34:20.417Z