{"url":"/task/zero-shot-multi-speaker-tts","name":"Zero-Shot Multi-Speaker TTS","slug":"zero-shot-multi-speaker-tts","description_markdown":null,"categories":[{"name":"Audio","url":"/area/audio"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":8,"papers_with_code":3,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/emilia-dataset","name":"Emilia Dataset","full_name":"An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation","num_papers_in_archive":8},{"url":"/dataset/arvoice","name":"ArVoice","full_name":"ArVoice: A Multi-Speaker Dataset for Arabic Speech Synthesis","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/text-to-speech-synthesis","name":"Text-To-Speech Synthesis"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":3,"of":3,"tagged_in_all":8,"items":[{"url":"/paper/yourtts-towards-zero-shot-multi-speaker-tts","title":"YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone","date":"2021-12-04","arxiv_id":"2112.02418","repositories_listed":3,"syntology":null},{"url":"/paper/xtts-a-massively-multilingual-zero-shot-text","title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","date":"2024-06-07","arxiv_id":"2406.04904","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/stochastic-pitch-prediction-improves-the","title":"Stochastic Pitch Prediction Improves the Diversity and Naturalness of Speech in Glow-TTS","date":"2023-05-28","arxiv_id":"2305.17724","repositories_listed":1,"syntology":null}],"syntology_records":1,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}