{"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/styletts-vc-one-shot-voice-conversion-by","title":"StyleTTS-VC: One-Shot Voice Conversion by Knowledge Transfer from Style-Based TTS Models","arxiv_id":"2212.14227","date":"2022-12-29","proceeding":null,"authors":["Yinghao Aaron Li","Cong Han","Nima Mesgarani"],"abstract":"One-shot voice conversion (VC) aims to convert speech from any source speaker to an arbitrary target speaker with only a few seconds of reference speech from the target speaker. This relies heavily on disentangling the speaker's identity and speech content, a task that still remains challenging. Here, we propose a novel approach to learning disentangled speech representation by transfer learning from style-based text-to-speech (TTS) models. With cycle consistent and adversarial training, the style-based TTS models can perform transcription-guided one-shot VC with high fidelity and similarity. By learning an additional mel-spectrogram encoder through a teacher-student knowledge transfer and novel data augmentation scheme, our approach results in disentangled speech representation without needing the input text. The subjective evaluation shows that our approach can significantly outperform the previous state-of-the-art one-shot voice conversion models in both naturalness and similarity.","url_abs":"https://arxiv.org/abs/2212.14227v1","url_pdf":"https://arxiv.org/pdf/2212.14227v1.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":"styletts-vc-one-shot-voice-conversion-by","repo_url":"https://github.com/yl4579/StyleTTS-VC","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"voice-conversion","task_name":"Voice Conversion"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2212.14227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.14227"}},"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/yl4579/StyleTTS-VC","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"ran_honours":1,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":11,"ran":7,"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":"yl4579/StyleTTS-VC","repo_kind":"official","path":"optimizers.py","file_url":"https://github.com/yl4579/StyleTTS-VC/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":"yl4579/StyleTTS-VC","repo_kind":"official","path":"optimizers.py","file_url":"https://github.com/yl4579/StyleTTS-VC/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":"7137577cbef51217","entry":"discriminator_loss","repo":"yl4579/StyleTTS-VC","repo_kind":"official","path":"Demo/hifi-gan/vocoder.py","file_url":"https://github.com/yl4579/StyleTTS-VC/blob/HEAD/Demo/hifi-gan/vocoder.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":"7137577cbef51217"}},{"code_sha256_prefix":"e453b51f0ed5fb28","entry":"feature_loss","repo":"yl4579/StyleTTS-VC","repo_kind":"official","path":"Demo/hifi-gan/vocoder.py","file_url":"https://github.com/yl4579/StyleTTS-VC/blob/HEAD/Demo/hifi-gan/vocoder.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":"e453b51f0ed5fb28"}},{"code_sha256_prefix":"1a9d74439d969cfd","entry":"generator_loss","repo":"yl4579/StyleTTS-VC","repo_kind":"official","path":"Demo/hifi-gan/vocoder.py","file_url":"https://github.com/yl4579/StyleTTS-VC/blob/HEAD/Demo/hifi-gan/vocoder.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":"1a9d74439d969cfd"}},{"code_sha256_prefix":"a26f85d7c72ef39a","entry":"get_padding","repo":"yl4579/StyleTTS-VC","repo_kind":"official","path":"Demo/hifi-gan/vocoder_utils.py","file_url":"https://github.com/yl4579/StyleTTS-VC/blob/HEAD/Demo/hifi-gan/vocoder_utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"code_sha256_prefix":"19c9fe23dc000c61","entry":"load_checkpoint","repo":"yl4579/StyleTTS-VC","repo_kind":"official","path":"Demo/hifi-gan/vocoder_utils.py","file_url":"https://github.com/yl4579/StyleTTS-VC/blob/HEAD/Demo/hifi-gan/vocoder_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"19c9fe23dc000c61"}},{"code_sha256_prefix":"32cbf209eb837cfc","entry":"build_model","repo":"yl4579/StyleTTS-VC","repo_kind":"official","path":"models.py","file_url":"https://github.com/yl4579/StyleTTS-VC/blob/HEAD/models.py","link_basis":"harvester_set","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":"32cbf209eb837cfc"}},{"code_sha256_prefix":"c6ec720d4ab00513","entry":"get_data_path_list","repo":"yl4579/StyleTTS-VC","repo_kind":"official","path":"utils.py","file_url":"https://github.com/yl4579/StyleTTS-VC/blob/HEAD/utils.py","link_basis":"harvester_set","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":"c6ec720d4ab00513"}},{"code_sha256_prefix":"c992f7522596af60","entry":"length_to_mask","repo":"yl4579/StyleTTS-VC","repo_kind":"official","path":"utils.py","file_url":"https://github.com/yl4579/StyleTTS-VC/blob/HEAD/utils.py","link_basis":"harvester_set","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":"c992f7522596af60"}},{"code_sha256_prefix":"8520e6e61b8bf789","entry":"plot_spectrogram","repo":"yl4579/StyleTTS-VC","repo_kind":"official","path":"Demo/hifi-gan/vocoder_utils.py","file_url":"https://github.com/yl4579/StyleTTS-VC/blob/HEAD/Demo/hifi-gan/vocoder_utils.py","link_basis":"harvester_set","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":"8520e6e61b8bf789"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}