{"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/differentiable-time-varying-linear-prediction","title":"Differentiable Time-Varying Linear Prediction in the Context of End-to-End Analysis-by-Synthesis","arxiv_id":"2406.05128","date":"2024-06-07","proceeding":null,"authors":["Chin-Yun Yu","György Fazekas"],"abstract":"Training the linear prediction (LP) operator end-to-end for audio synthesis in modern deep learning frameworks is slow due to its recursive formulation. In addition, frame-wise approximation as an acceleration method cannot generalise well to test time conditions where the LP is computed sample-wise. Efficient differentiable sample-wise LP for end-to-end training is the key to removing this barrier. We generalise the efficient time-invariant LP implementation from the GOLF vocoder to time-varying cases. Combining this with the classic source-filter model, we show that the improved GOLF learns LP coefficients and reconstructs the voice better than its frame-wise counterparts. Moreover, in our listening test, synthesised outputs from GOLF scored higher in quality ratings than the state-of-the-art differentiable WORLD vocoder.","url_abs":"https://arxiv.org/abs/2406.05128v3","url_pdf":"https://arxiv.org/pdf/2406.05128v3.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":"abstracts"},"code_links":[{"paper_slug":"differentiable-time-varying-linear-prediction","repo_url":"https://github.com/yoyololicon/golf","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"differentiable-time-varying-linear-prediction","repo_url":"https://github.com/yoyololicon/torchlpc","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"differentiable-time-varying-linear-prediction","repo_url":"https://github.com/diffapf/torchlpc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"differentiable-time-varying-linear-prediction","repo_url":"https://github.com/iamycy/golf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"audio-synthesis","task_name":"Audio Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}