{"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/diffusion-based-voice-conversion-with-fast","title":"Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme","arxiv_id":"2109.13821","date":"2021-09-28","proceeding":"ICLR 2022 4","authors":["Vadim Popov","Ivan Vovk","Vladimir Gogoryan","Tasnima Sadekova","Mikhail Kudinov","Jiansheng Wei"],"abstract":"Voice conversion is a common speech synthesis task which can be solved in different ways depending on a particular real-world scenario. The most challenging one often referred to as one-shot many-to-many voice conversion consists in copying the target voice from only one reference utterance in the most general case when both source and target speakers do not belong to the training dataset. We present a scalable high-quality solution based on diffusion probabilistic modeling and demonstrate its superior quality compared to state-of-the-art one-shot voice conversion approaches. Moreover, focusing on real-time applications, we investigate general principles which can make diffusion models faster while keeping synthesis quality at a high level. As a result, we develop a novel Stochastic Differential Equations solver suitable for various diffusion model types and generative tasks as shown through empirical studies and justify it by theoretical analysis.","url_abs":"https://arxiv.org/abs/2109.13821v2","url_pdf":"https://arxiv.org/pdf/2109.13821v2.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":"diffusion-based-voice-conversion-with-fast","repo_url":"https://github.com/huawei-noah/Speech-Backbones","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"diffusion-based-voice-conversion-with-fast","repo_url":"https://github.com/playvoice/grad-svc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"diffusion-based-voice-conversion-with-fast","repo_url":"https://github.com/trinhtuanvubk/diff-vc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"diffusion-based-voice-conversion-with-fast","repo_url":"https://github.com/huawei-noah/Speech-Backbones/tree/main/Grad-TTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"voice-conversion","task_name":"Voice Conversion"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.13821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.13821"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huawei-noah/Speech-Backbones","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/trinhtuanvubk/diff-vc","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huawei-noah/Speech-Backbones/tree/main/Grad-TTS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/playvoice/grad-svc","reach":null}],"summary":{"ran_honours":1,"ran":3,"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"listed":{"samples":7,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":9,"samples":[{"code_sha256_prefix":"59ae0708b1e8d94b","entry":"convert_pad_shape","repo":"trinhtuanvubk/diff-vc","repo_kind":"listed","path":"model/utils.py","file_url":"https://github.com/trinhtuanvubk/diff-vc/blob/HEAD/model/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"59ae0708b1e8d94b"}},{"code_sha256_prefix":"7137577cbef51217","entry":"discriminator_loss","repo":"trinhtuanvubk/diff-vc","repo_kind":"listed","path":"hifi-gan/models.py","file_url":"https://github.com/trinhtuanvubk/diff-vc/blob/HEAD/hifi-gan/models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"7137577cbef51217"}},{"code_sha256_prefix":"e453b51f0ed5fb28","entry":"feature_loss","repo":"trinhtuanvubk/diff-vc","repo_kind":"listed","path":"hifi-gan/models.py","file_url":"https://github.com/trinhtuanvubk/diff-vc/blob/HEAD/hifi-gan/models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"e453b51f0ed5fb28"}},{"code_sha256_prefix":"1a9d74439d969cfd","entry":"generator_loss","repo":"trinhtuanvubk/diff-vc","repo_kind":"listed","path":"hifi-gan/models.py","file_url":"https://github.com/trinhtuanvubk/diff-vc/blob/HEAD/hifi-gan/models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"1a9d74439d969cfd"}},{"code_sha256_prefix":"98cc9f3aed7a8480","entry":"load_bigv_model","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"98cc9f3aed7a8480"}},{"code_sha256_prefix":"051895a532dbea48","entry":"load_gvc_model","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"051895a532dbea48"}},{"code_sha256_prefix":"e34c9a8aed8fe01a","entry":"mse_loss","repo":"trinhtuanvubk/diff-vc","repo_kind":"listed","path":"model/utils.py","file_url":"https://github.com/trinhtuanvubk/diff-vc/blob/HEAD/model/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"e34c9a8aed8fe01a"}},{"code_sha256_prefix":"41fa4c2a7be952b8","entry":"save_audio","repo":"trinhtuanvubk/diff-vc","repo_kind":"listed","path":"api.py","file_url":"https://github.com/trinhtuanvubk/diff-vc/blob/HEAD/api.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"41fa4c2a7be952b8"}},{"code_sha256_prefix":"71ed8b8d6ed2bf01","entry":"sequence_mask","repo":"trinhtuanvubk/diff-vc","repo_kind":"listed","path":"model/utils.py","file_url":"https://github.com/trinhtuanvubk/diff-vc/blob/HEAD/model/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"71ed8b8d6ed2bf01"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}