{"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/emo-stargan-a-semi-supervised-any-to-many-non","title":"Emo-StarGAN: A Semi-Supervised Any-to-Many Non-Parallel Emotion-Preserving Voice Conversion","arxiv_id":"2309.07586","date":"2023-09-14","proceeding":null,"authors":["Suhita Ghosh","Arnab Das","Yamini Sinha","Ingo Siegert","Tim Polzehl","Sebastian Stober"],"abstract":"Speech anonymisation prevents misuse of spoken data by removing any personal identifier while preserving at least linguistic content. However, emotion preservation is crucial for natural human-computer interaction. The well-known voice conversion technique StarGANv2-VC achieves anonymisation but fails to preserve emotion. This work presents an any-to-many semi-supervised StarGANv2-VC variant trained on partially emotion-labelled non-parallel data. We propose emotion-aware losses computed on the emotion embeddings and acoustic features correlated to emotion. Additionally, we use an emotion classifier to provide direct emotion supervision. Objective and subjective evaluations show that the proposed approach significantly improves emotion preservation over the vanilla StarGANv2-VC. This considerable improvement is seen over diverse datasets, emotions, target speakers, and inter-group conversions without compromising intelligibility and anonymisation.","url_abs":"https://arxiv.org/abs/2309.07586v1","url_pdf":"https://arxiv.org/pdf/2309.07586v1.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":"emo-stargan-a-semi-supervised-any-to-many-non","repo_url":"https://github.com/suhitaghosh10/emo-stargan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"voice-conversion","task_name":"Voice Conversion"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.07586","atlas_url":"https://app.syntology.ai/?focus=2309.07586","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07586"}},"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/suhitaghosh10/emo-stargan","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":"f5f1bd6b9f51a9f0","entry":"build_optimizer","repo":"suhitaghosh10/emo-stargan","repo_kind":"official","path":"optimizers.py","file_url":"https://github.com/suhitaghosh10/emo-stargan/blob/HEAD/optimizers.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":"f5f1bd6b9f51a9f0"}},{"code_sha256_prefix":"6e710fd26220eb49","entry":"define_scheduler","repo":"suhitaghosh10/emo-stargan","repo_kind":"official","path":"optimizers.py","file_url":"https://github.com/suhitaghosh10/emo-stargan/blob/HEAD/optimizers.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":"6e710fd26220eb49"}},{"code_sha256_prefix":"4e97257128ddcb72","entry":"frame","repo":"suhitaghosh10/emo-stargan","repo_kind":"official","path":"Models/features.py","file_url":"https://github.com/suhitaghosh10/emo-stargan/blob/HEAD/Models/features.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":"4e97257128ddcb72"}},{"code_sha256_prefix":"62618bc8a2fb233e","entry":"log_norm","repo":"suhitaghosh10/emo-stargan","repo_kind":"official","path":"Models/losses.py","file_url":"https://github.com/suhitaghosh10/emo-stargan/blob/HEAD/Models/losses.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":"62618bc8a2fb233e"}},{"code_sha256_prefix":"3891e8e3b55b7362","entry":"torch_like_frame","repo":"suhitaghosh10/emo-stargan","repo_kind":"official","path":"Models/features.py","file_url":"https://github.com/suhitaghosh10/emo-stargan/blob/HEAD/Models/features.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":"3891e8e3b55b7362"}},{"code_sha256_prefix":"a1d80df697161cd2","entry":"compute_coding_loss","repo":"suhitaghosh10/emo-stargan","repo_kind":"official","path":"Utils/emotion_encoder/losses.py","file_url":"https://github.com/suhitaghosh10/emo-stargan/blob/HEAD/Utils/emotion_encoder/losses.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":"a1d80df697161cd2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}