{"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/stargan-vc-towards-emotion-preserving-voice","title":"StarGAN-VC++: Towards Emotion Preserving Voice Conversion Using Deep Embeddings","arxiv_id":"2309.07592","date":"2023-09-14","proceeding":null,"authors":["Arnab Das","Suhita Ghosh","Tim Polzehl","Sebastian Stober"],"abstract":"Voice conversion (VC) transforms an utterance to sound like another person without changing the linguistic content. A recently proposed generative adversarial network-based VC method, StarGANv2-VC is very successful in generating natural-sounding conversions. However, the method fails to preserve the emotion of the source speaker in the converted samples. Emotion preservation is necessary for natural human-computer interaction. In this paper, we show that StarGANv2-VC fails to disentangle the speaker and emotion representations, pertinent to preserve emotion. Specifically, there is an emotion leakage from the reference audio used to capture the speaker embeddings while training. To counter the problem, we propose novel emotion-aware losses and an unsupervised method which exploits emotion supervision through latent emotion representations. The objective and subjective evaluations prove the efficacy of the proposed strategy over diverse datasets, emotions, gender, etc.","url_abs":"https://arxiv.org/abs/2309.07592v1","url_pdf":"https://arxiv.org/pdf/2309.07592v1.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":"stargan-vc-towards-emotion-preserving-voice","repo_url":"https://github.com/arnabdas8901/StarGAN-VC_PlusPlus","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"voice-conversion","task_name":"Voice Conversion"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.07592","atlas_url":"https://app.syntology.ai/?focus=2309.07592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07592"}},"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/arnabdas8901/StarGAN-VC_PlusPlus","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":7,"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":0,"samples":[{"code_sha256_prefix":"f5f1bd6b9f51a9f0","entry":"build_optimizer","repo":"arnabdas8901/StarGAN-VC_PlusPlus","repo_kind":"official","path":"optimizers.py","file_url":"https://github.com/arnabdas8901/StarGAN-VC_PlusPlus/blob/HEAD/optimizers.py","link_basis":"first_harvest_node","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":"arnabdas8901/StarGAN-VC_PlusPlus","repo_kind":"official","path":"optimizers.py","file_url":"https://github.com/arnabdas8901/StarGAN-VC_PlusPlus/blob/HEAD/optimizers.py","link_basis":"first_harvest_node","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":"arnabdas8901/StarGAN-VC_PlusPlus","repo_kind":"official","path":"features.py","file_url":"https://github.com/arnabdas8901/StarGAN-VC_PlusPlus/blob/HEAD/features.py","link_basis":"first_harvest_node","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":"0ca619f78d86b72f","entry":"get_index","repo":"arnabdas8901/StarGAN-VC_PlusPlus","repo_kind":"official","path":"emo_preserve_evaluation.py","file_url":"https://github.com/arnabdas8901/StarGAN-VC_PlusPlus/blob/HEAD/emo_preserve_evaluation.py","link_basis":"first_harvest_node","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":"0ca619f78d86b72f"}},{"code_sha256_prefix":"62618bc8a2fb233e","entry":"log_norm","repo":"arnabdas8901/StarGAN-VC_PlusPlus","repo_kind":"official","path":"losses.py","file_url":"https://github.com/arnabdas8901/StarGAN-VC_PlusPlus/blob/HEAD/losses.py","link_basis":"first_harvest_node","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":"arnabdas8901/StarGAN-VC_PlusPlus","repo_kind":"official","path":"features.py","file_url":"https://github.com/arnabdas8901/StarGAN-VC_PlusPlus/blob/HEAD/features.py","link_basis":"first_harvest_node","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":"bc5e4dd0bd00b725","entry":"compute_g_loss","repo":"arnabdas8901/StarGAN-VC_PlusPlus","repo_kind":"official","path":"losses.py","file_url":"https://github.com/arnabdas8901/StarGAN-VC_PlusPlus/blob/HEAD/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":"bc5e4dd0bd00b725"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}