{"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-a-style-based-generative-model-for","title":"StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesis","arxiv_id":"2205.15439","date":"2022-05-30","proceeding":null,"authors":["Yinghao Aaron Li","Cong Han","Nima Mesgarani"],"abstract":"Text-to-Speech (TTS) has recently seen great progress in synthesizing high-quality speech owing to the rapid development of parallel TTS systems, but producing speech with naturalistic prosodic variations, speaking styles and emotional tones remains challenging. Moreover, since duration and speech are generated separately, parallel TTS models still have problems finding the best monotonic alignments that are crucial for naturalistic speech synthesis. Here, we propose StyleTTS, a style-based generative model for parallel TTS that can synthesize diverse speech with natural prosody from a reference speech utterance. With novel Transferable Monotonic Aligner (TMA) and duration-invariant data augmentation schemes, our method significantly outperforms state-of-the-art models on both single and multi-speaker datasets in subjective tests of speech naturalness and speaker similarity. Through self-supervised learning of the speaking styles, our model can synthesize speech with the same prosodic and emotional tone as any given reference speech without the need for explicitly labeling these categories.","url_abs":"https://arxiv.org/abs/2205.15439v2","url_pdf":"https://arxiv.org/pdf/2205.15439v2.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-a-style-based-generative-model-for","repo_url":"https://github.com/yl4579/StyleTTS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-synthesis","task_name":"Text-To-Speech Synthesis"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.15439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.15439"}},"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","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","repo_kind":"official","path":"optimizers.py","file_url":"https://github.com/yl4579/StyleTTS/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","repo_kind":"official","path":"optimizers.py","file_url":"https://github.com/yl4579/StyleTTS/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","repo_kind":"official","path":"Demo/hifi-gan/vocoder.py","file_url":"https://github.com/yl4579/StyleTTS/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","repo_kind":"official","path":"Demo/hifi-gan/vocoder.py","file_url":"https://github.com/yl4579/StyleTTS/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","repo_kind":"official","path":"Demo/hifi-gan/vocoder.py","file_url":"https://github.com/yl4579/StyleTTS/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","repo_kind":"official","path":"Demo/hifi-gan/vocoder_utils.py","file_url":"https://github.com/yl4579/StyleTTS/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","repo_kind":"official","path":"Demo/hifi-gan/vocoder_utils.py","file_url":"https://github.com/yl4579/StyleTTS/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":"c7a858f0649cb08a","entry":"build_model","repo":"yl4579/StyleTTS","repo_kind":"official","path":"models.py","file_url":"https://github.com/yl4579/StyleTTS/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":"c7a858f0649cb08a"}},{"code_sha256_prefix":"ce873dd11c39f49d","entry":"get_data_path_list","repo":"yl4579/StyleTTS","repo_kind":"official","path":"utils.py","file_url":"https://github.com/yl4579/StyleTTS/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":"ce873dd11c39f49d"}},{"code_sha256_prefix":"c992f7522596af60","entry":"length_to_mask","repo":"yl4579/StyleTTS","repo_kind":"official","path":"utils.py","file_url":"https://github.com/yl4579/StyleTTS/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","repo_kind":"official","path":"Demo/hifi-gan/vocoder_utils.py","file_url":"https://github.com/yl4579/StyleTTS/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}