{"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/a-comparison-of-discrete-and-soft-speech","title":"A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion","arxiv_id":"2111.02392","date":"2021-11-03","proceeding":null,"authors":["Benjamin van Niekerk","Marc-André Carbonneau","Julian Zaïdi","Mathew Baas","Hugo Seuté","Herman Kamper"],"abstract":"The goal of voice conversion is to transform source speech into a target voice, keeping the content unchanged. In this paper, we focus on self-supervised representation learning for voice conversion. Specifically, we compare discrete and soft speech units as input features. We find that discrete representations effectively remove speaker information but discard some linguistic content - leading to mispronunciations. As a solution, we propose soft speech units. To learn soft units, we predict a distribution over discrete speech units. By modeling uncertainty, soft units capture more content information, improving the intelligibility and naturalness of converted speech. Samples available at https://ubisoft-laforge.github.io/speech/soft-vc/. Code available at https://github.com/bshall/soft-vc/.","url_abs":"https://arxiv.org/abs/2111.02392v2","url_pdf":"https://arxiv.org/pdf/2111.02392v2.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":"a-comparison-of-discrete-and-soft-speech","repo_url":"https://github.com/bshall/soft-vc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-comparison-of-discrete-and-soft-speech","repo_url":"https://github.com/bshall/hubert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"voice-conversion","task_name":"Voice Conversion"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.02392","atlas_url":"https://app.syntology.ai/?focus=2111.02392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02392"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/bshall/hubert","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bshall/soft-vc","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":1},"by_repo_kind":{"listed":{"samples":2,"ran":1,"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":"36a04dd5b3d4483e","entry":"load_checkpoint","repo":"bshall/hubert","repo_kind":"listed","path":"hubert/utils.py","file_url":"https://github.com/bshall/hubert/blob/HEAD/hubert/utils.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":"36a04dd5b3d4483e"}},{"code_sha256_prefix":"cde0e3ee233b7f09","entry":"kmeans100","repo":"bshall/hubert","repo_kind":"listed","path":"hubconf.py","file_url":"https://github.com/bshall/hubert/blob/HEAD/hubconf.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":"cde0e3ee233b7f09"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}