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

Da-Yi Wu, Wen-Yi Hsiao,Fu-Rong Yang,Oscar Friedman, Warren Jackson, Scott Bruzenak,Yi-Wen Liu, Yi-Hsuan Yang

arxiv(2022)

引用 0|浏览21
暂无评分
摘要
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.
更多
查看译文
关键词
singing vocoders,synthesizer,ddsp-based,subtractive-based
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要