{"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/improving-zero-shot-voice-style-transfer-via-1","title":"Improving Zero-shot Voice Style Transfer via Disentangled Representation Learning","arxiv_id":"2103.09420","date":"2021-03-17","proceeding":"ICLR 2021 1","authors":["Siyang Yuan","Pengyu Cheng","Ruiyi Zhang","Weituo Hao","Zhe Gan","Lawrence Carin"],"abstract":"Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker. Previous works have made progress on voice conversion with parallel training data and pre-known speakers. However, zero-shot voice style transfer, which learns from non-parallel data and generates voices for previously unseen speakers, remains a challenging problem. We propose a novel zero-shot voice transfer method via disentangled representation learning. The proposed method first encodes speaker-related style and voice content of each input voice into separated low-dimensional embedding spaces, and then transfers to a new voice by combining the source content embedding and target style embedding through a decoder. With information-theoretic guidance, the style and content embedding spaces are representative and (ideally) independent of each other. On real-world VCTK datasets, our method outperforms other baselines and obtains state-of-the-art results in terms of transfer accuracy and voice naturalness for voice style transfer experiments under both many-to-many and zero-shot setups.","url_abs":"https://arxiv.org/abs/2103.09420v1","url_pdf":"https://arxiv.org/pdf/2103.09420v1.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":"improving-zero-shot-voice-style-transfer-via-1","repo_url":"https://github.com/jackaduma/CycleGAN-VC2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"style-transfer","task_name":"Style Transfer"},{"task_slug":"voice-conversion","task_name":"Voice Conversion"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.09420","atlas_url":"https://app.syntology.ai/?focus=2103.09420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.09420"}},"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/jackaduma/CycleGAN-VC2","reach":null}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"listed":{"samples":4,"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":"cae1876ac552d841","entry":"GLU","repo":"jackaduma/CycleGAN-VC2","repo_kind":"listed","path":"model_tf.py","file_url":"https://github.com/jackaduma/CycleGAN-VC2/blob/HEAD/model_tf.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cae1876ac552d841"}},{"code_sha256_prefix":"b41611857928b628","entry":"ResidualLayer","repo":"jackaduma/CycleGAN-VC2","repo_kind":"listed","path":"model_tf.py","file_url":"https://github.com/jackaduma/CycleGAN-VC2/blob/HEAD/model_tf.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b41611857928b628"}},{"code_sha256_prefix":"43418e4ef92ab761","entry":"downSample_Generator","repo":"jackaduma/CycleGAN-VC2","repo_kind":"listed","path":"model_tf.py","file_url":"https://github.com/jackaduma/CycleGAN-VC2/blob/HEAD/model_tf.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"43418e4ef92ab761"}},{"code_sha256_prefix":"0c065c351f7c323f","entry":"Generator","repo":"jackaduma/CycleGAN-VC2","repo_kind":"listed","path":"model_tf.py","file_url":"https://github.com/jackaduma/CycleGAN-VC2/blob/HEAD/model_tf.py","link_basis":"first_harvest_node","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":"0c065c351f7c323f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}