English

DDSP-based Singing Vocoders: A New Subtractive-based Synthesizer and A Comprehensive Evaluation

Sound 2022-08-22 v2 Audio and Speech Processing

Abstract

A vocoder is a conditional audio generation model that converts acoustic features such as mel-spectrograms into waveforms. Taking inspiration from Differentiable Digital Signal Processing (DDSP), we propose a new vocoder named SawSing for singing voices. SawSing synthesizes the harmonic part of singing voices by filtering a sawtooth source signal with a linear time-variant finite impulse response filter whose coefficients are estimated from the input mel-spectrogram by a neural network. As this approach enforces phase continuity, SawSing can generate singing voices without the phase-discontinuity glitch of many existing vocoders. Moreover, the source-filter assumption provides an inductive bias that allows SawSing to be trained on a small amount of data. Our experiments show that SawSing converges much faster and outperforms state-of-the-art generative adversarial network and diffusion-based vocoders in a resource-limited scenario with only 3 training recordings and a 3-hour training time.

Keywords

Cite

@article{arxiv.2208.04756,
  title  = {DDSP-based Singing Vocoders: A New Subtractive-based Synthesizer and A Comprehensive Evaluation},
  author = {Da-Yi Wu and Wen-Yi Hsiao and Fu-Rong Yang and Oscar Friedman and Warren Jackson and Scott Bruzenak and Yi-Wen Liu and Yi-Hsuan Yang},
  journal= {arXiv preprint arXiv:2208.04756},
  year   = {2022}
}

Comments

Accepted at ISMIR 2022