{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ddsp-based-singing-vocoders-a-new-subtractive","title":"DDSP-based Singing Vocoders: A New Subtractive-based Synthesizer and A Comprehensive Evaluation","arxiv_id":"2208.04756","date":"2022-08-09","proceeding":null,"authors":["Da-Yi Wu","Wen-Yi Hsiao","Fu-Rong Yang","Oscar Friedman","Warren Jackson","Scott Bruzenak","Yi-Wen Liu","Yi-Hsuan Yang"],"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.","url_abs":"https://arxiv.org/abs/2208.04756v2","url_pdf":"https://arxiv.org/pdf/2208.04756v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"ddsp-based-singing-vocoders-a-new-subtractive","repo_url":"https://github.com/yatingmusic/ddsp-singing-vocoders","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2208.04756","atlas_url":"https://app.syntology.ai/?focus=2208.04756","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}