{"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/cyclegan-vc2-improved-cyclegan-based-non","title":"CycleGAN-VC2: Improved CycleGAN-based Non-parallel Voice Conversion","arxiv_id":"1904.04631","date":"2019-04-09","proceeding":null,"authors":["Takuhiro Kaneko","Hirokazu Kameoka","Kou Tanaka","Nobukatsu Hojo"],"abstract":"Non-parallel voice conversion (VC) is a technique for learning the mapping\nfrom source to target speech without relying on parallel data. This is an\nimportant task, but it has been challenging due to the disadvantages of the\ntraining conditions. Recently, CycleGAN-VC has provided a breakthrough and\nperformed comparably to a parallel VC method without relying on any extra data,\nmodules, or time alignment procedures. However, there is still a large gap\nbetween the real target and converted speech, and bridging this gap remains a\nchallenge. To reduce this gap, we propose CycleGAN-VC2, which is an improved\nversion of CycleGAN-VC incorporating three new techniques: an improved\nobjective (two-step adversarial losses), improved generator (2-1-2D CNN), and\nimproved discriminator (PatchGAN). We evaluated our method on a non-parallel VC\ntask and analyzed the effect of each technique in detail. An objective\nevaluation showed that these techniques help bring the converted feature\nsequence closer to the target in terms of both global and local structures,\nwhich we assess by using Mel-cepstral distortion and modulation spectra\ndistance, respectively. A subjective evaluation showed that CycleGAN-VC2\noutperforms CycleGAN-VC in terms of naturalness and similarity for every\nspeaker pair, including intra-gender and inter-gender pairs.","url_abs":"http://arxiv.org/abs/1904.04631v1","url_pdf":"http://arxiv.org/pdf/1904.04631v1.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":"cyclegan-vc2-improved-cyclegan-based-non","repo_url":"https://github.com/jackaduma/CycleGAN-VC2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"cyclegan-vc2-improved-cyclegan-based-non","repo_url":"https://github.com/takedarts/BandaiNamco-DSChallenge-3rdSolution","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"cyclegan-vc2-improved-cyclegan-based-non","repo_url":"https://github.com/2023-MindSpore-4/Code1/tree/main/CycleGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"cyclegan-vc2-improved-cyclegan-based-non","repo_url":"https://github.com/2023-MindSpore-4/Code10/tree/main/CycleGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"cyclegan-vc2-improved-cyclegan-based-non","repo_url":"https://github.com/2024-MindSpore-1/Code4/tree/main/CycleGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"cyclegan-vc2-improved-cyclegan-based-non","repo_url":"https://github.com/nafiuny/ICRCycleGAN-VC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"voice-conversion","task_name":"Voice Conversion"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"cycle-consistency-loss","method_name":"Cycle Consistency Loss"},{"method_slug":"gan-least-squares-loss","method_name":"GAN Least Squares Loss"},{"method_slug":"instance-normalization","method_name":"Instance Normalization"},{"method_slug":"patchgan","method_name":"PatchGAN"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.04631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.04631"}},"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/jackaduma/CycleGAN-VC2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nafiuny/ICRCycleGAN-VC","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-4/Code1/tree/main/CycleGAN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2024-MindSpore-1/Code4/tree/main/CycleGAN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/CycleGAN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/takedarts/BandaiNamco-DSChallenge-3rdSolution","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{},"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":1,"samples":[{"code_sha256_prefix":"1979c9d42c945db2","entry":"load_pickle_file","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":"1979c9d42c945db2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}