{"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/diff-hiervc-diffusion-based-hierarchical","title":"Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation","arxiv_id":"2311.04693","date":"2023-11-08","proceeding":null,"authors":["Ha-Yeong Choi","Sang-Hoon Lee","Seong-Whan Lee"],"abstract":"Although voice conversion (VC) systems have shown a remarkable ability to transfer voice style, existing methods still have an inaccurate pitch and low speaker adaptation quality. To address these challenges, we introduce Diff-HierVC, a hierarchical VC system based on two diffusion models. We first introduce DiffPitch, which can effectively generate F0 with the target voice style. Subsequently, the generated F0 is fed to DiffVoice to convert the speech with a target voice style. Furthermore, using the source-filter encoder, we disentangle the speech and use the converted Mel-spectrogram as a data-driven prior in DiffVoice to improve the voice style transfer capacity. Finally, by using the masked prior in diffusion models, our model can improve the speaker adaptation quality. Experimental results verify the superiority of our model in pitch generation and voice style transfer performance, and our model also achieves a CER of 0.83% and EER of 3.29% in zero-shot VC scenarios.","url_abs":"https://arxiv.org/abs/2311.04693v1","url_pdf":"https://arxiv.org/pdf/2311.04693v1.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":"diff-hiervc-diffusion-based-hierarchical","repo_url":"https://github.com/hayeong0/Diff-HierVC","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"style-transfer","task_name":"Style Transfer"},{"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=2311.04693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04693"}},"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/hayeong0/Diff-HierVC","reach":{"status":"ok"}}],"summary":{"ran_honours":2,"ran":4,"unverified":3},"by_repo_kind":{"official":{"samples":9,"ran":6,"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":"hayeong0/Diff-HierVC","repo_kind":"official","path":"module/commons.py","file_url":"https://github.com/hayeong0/Diff-HierVC/blob/HEAD/module/commons.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"59ae0708b1e8d94b"}},{"code_sha256_prefix":"a26f85d7c72ef39a","entry":"get_padding","repo":"hayeong0/Diff-HierVC","repo_kind":"official","path":"module/commons.py","file_url":"https://github.com/hayeong0/Diff-HierVC/blob/HEAD/module/commons.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"code_sha256_prefix":"321604dda57bb02d","entry":"latest_checkpoint_path","repo":"hayeong0/Diff-HierVC","repo_kind":"official","path":"module/utils.py","file_url":"https://github.com/hayeong0/Diff-HierVC/blob/HEAD/module/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"321604dda57bb02d"}},{"code_sha256_prefix":"c647283e53cacacf","entry":"load_checkpoint","repo":"hayeong0/Diff-HierVC","repo_kind":"official","path":"module/utils.py","file_url":"https://github.com/hayeong0/Diff-HierVC/blob/HEAD/module/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c647283e53cacacf"}},{"code_sha256_prefix":"eb2648f22370878d","entry":"load_wav_to_torch","repo":"hayeong0/Diff-HierVC","repo_kind":"official","path":"module/utils.py","file_url":"https://github.com/hayeong0/Diff-HierVC/blob/HEAD/module/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eb2648f22370878d"}},{"code_sha256_prefix":"70a7614b3b3eb41f","entry":"unconstrained_rational_quadratic_spline","repo":"hayeong0/Diff-HierVC","repo_kind":"official","path":"module/transforms.py","file_url":"https://github.com/hayeong0/Diff-HierVC/blob/HEAD/module/transforms.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"70a7614b3b3eb41f"}},{"code_sha256_prefix":"c01a3efb274ff778","entry":"intersperse","repo":"hayeong0/Diff-HierVC","repo_kind":"official","path":"module/commons.py","file_url":"https://github.com/hayeong0/Diff-HierVC/blob/HEAD/module/commons.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c01a3efb274ff778"}},{"code_sha256_prefix":"ba6cafc4d658c14f","entry":"piecewise_rational_quadratic_transform","repo":"hayeong0/Diff-HierVC","repo_kind":"official","path":"module/transforms.py","file_url":"https://github.com/hayeong0/Diff-HierVC/blob/HEAD/module/transforms.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ba6cafc4d658c14f"}},{"code_sha256_prefix":"e85d747983c4f5d8","entry":"searchsorted","repo":"hayeong0/Diff-HierVC","repo_kind":"official","path":"module/transforms.py","file_url":"https://github.com/hayeong0/Diff-HierVC/blob/HEAD/module/transforms.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e85d747983c4f5d8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}