{"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/speaking-style-conversion-with-discrete-self","title":"Speaking Style Conversion in the Waveform Domain Using Discrete Self-Supervised Units","arxiv_id":"2212.09730","date":"2022-12-19","proceeding":null,"authors":["Gallil Maimon","Yossi Adi"],"abstract":"We introduce DISSC, a novel, lightweight method that converts the rhythm, pitch contour and timbre of a recording to a target speaker in a textless manner. Unlike DISSC, most voice conversion (VC) methods focus primarily on timbre, and ignore people's unique speaking style (prosody). The proposed approach uses a pretrained, self-supervised model for encoding speech to discrete units, which makes it simple, effective, and fast to train. All conversion modules are only trained on reconstruction like tasks, thus suitable for any-to-many VC with no paired data. We introduce a suite of quantitative and qualitative evaluation metrics for this setup, and empirically demonstrate that DISSC significantly outperforms the evaluated baselines. Code and samples are available at https://pages.cs.huji.ac.il/adiyoss-lab/dissc/.","url_abs":"https://arxiv.org/abs/2212.09730v2","url_pdf":"https://arxiv.org/pdf/2212.09730v2.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":"speaking-style-conversion-with-discrete-self","repo_url":"https://github.com/gallilmaimon/DISSC","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"rhythm","task_name":"Rhythm"},{"task_slug":"voice-conversion","task_name":"Voice Conversion"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/voice-conversion-on-vctk","task":"Voice Conversion","dataset":"VCTK","model":"DISSC","rank_in_archive_order":1,"of":1,"metrics":{"Phone Length Error (PLE)":"0.023","Total Length Error (TLE)":"0.832","Word Length Error (WLE)":"0.056"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.09730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09730"}},"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/gallilmaimon/DISSC","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"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":0,"samples":[{"code_sha256_prefix":"7137577cbef51217","entry":"discriminator_loss","repo":"gallilmaimon/DISSC","repo_kind":"official","path":"sr/models.py","file_url":"https://github.com/gallilmaimon/DISSC/blob/HEAD/sr/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":true,"mcp_get_code":{"code_sha256":"7137577cbef51217"}},{"code_sha256_prefix":"e453b51f0ed5fb28","entry":"feature_loss","repo":"gallilmaimon/DISSC","repo_kind":"official","path":"sr/models.py","file_url":"https://github.com/gallilmaimon/DISSC/blob/HEAD/sr/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":true,"mcp_get_code":{"code_sha256":"e453b51f0ed5fb28"}},{"code_sha256_prefix":"1a9d74439d969cfd","entry":"generator_loss","repo":"gallilmaimon/DISSC","repo_kind":"official","path":"sr/models.py","file_url":"https://github.com/gallilmaimon/DISSC/blob/HEAD/sr/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":true,"mcp_get_code":{"code_sha256":"1a9d74439d969cfd"}},{"code_sha256_prefix":"ce7d4703ab7af4e5","entry":"init_loggers","repo":"gallilmaimon/DISSC","repo_kind":"official","path":"utils.py","file_url":"https://github.com/gallilmaimon/DISSC/blob/HEAD/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":true,"mcp_get_code":{"code_sha256":"ce7d4703ab7af4e5"}},{"code_sha256_prefix":"446926f352958627","entry":"interp","repo":"gallilmaimon/DISSC","repo_kind":"official","path":"utils.py","file_url":"https://github.com/gallilmaimon/DISSC/blob/HEAD/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":true,"mcp_get_code":{"code_sha256":"446926f352958627"}},{"code_sha256_prefix":"d4f65f83536dd467","entry":"len_carryover_correction","repo":"gallilmaimon/DISSC","repo_kind":"official","path":"infer.py","file_url":"https://github.com/gallilmaimon/DISSC/blob/HEAD/infer.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":true,"mcp_get_code":{"code_sha256":"d4f65f83536dd467"}},{"code_sha256_prefix":"38a9379fee62c6f7","entry":"morph_seq_len","repo":"gallilmaimon/DISSC","repo_kind":"official","path":"utils.py","file_url":"https://github.com/gallilmaimon/DISSC/blob/HEAD/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":true,"mcp_get_code":{"code_sha256":"38a9379fee62c6f7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}