{"url":"/task/emotional-speech-synthesis","name":"Emotional Speech Synthesis","slug":"emotional-speech-synthesis","description_markdown":null,"categories":[{"name":"Audio","url":"/area/audio"},{"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":26,"papers_with_code":7,"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/emodb-dataset","name":"EmoDB Dataset","full_name":"Berlin Database of Emotional Speech","num_papers_in_archive":6},{"url":"/dataset/emovie","name":"EMOVIE","full_name":"","num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[{"url":"/task/speech-synthesis","name":"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":7,"of":7,"tagged_in_all":26,"items":[{"url":"/paper/exploring-transfer-learning-for-low-resource","title":"Exploring Transfer Learning for Low Resource Emotional TTS","date":"2019-01-14","arxiv_id":"1901.04276","repositories_listed":5,"syntology":null},{"url":"/paper/openomni-large-language-models-pivot-zero","title":"OpenOmni: Large Language Models Pivot Zero-shot Omnimodal Alignment across Language with Real-time Self-Aware Emotional Speech Synthesis","date":"2025-01-08","arxiv_id":"2501.04561","repositories_listed":1,"syntology":null},{"url":"/paper/emosphere-emotion-controllable-zero-shot-text","title":"EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector","date":"2024-11-04","arxiv_id":"2411.02625","repositories_listed":1,"syntology":null},{"url":"/paper/emoknob-enhance-voice-cloning-with-fine","title":"EmoKnob: Enhance Voice Cloning with Fine-Grained Emotion Control","date":"2024-10-01","arxiv_id":"2410.00316","repositories_listed":1,"syntology":null},{"url":"/paper/emosphere-tts-emotional-style-and-intensity","title":"EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speech","date":"2024-06-12","arxiv_id":"2406.07803","repositories_listed":1,"syntology":null},{"url":"/paper/strengthnet-deep-learning-based-emotion","title":"StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis","date":"2021-10-07","arxiv_id":"2110.03156","repositories_listed":1,"syntology":null},{"url":"/paper/visualization-and-interpretation-of-latent","title":"Visualization and Interpretation of Latent Spaces for Controlling Expressive Speech Synthesis through Audio Analysis","date":"2019-03-27","arxiv_id":"1903.11570","repositories_listed":1,"syntology":null}],"syntology_records":0,"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"}}