{"url":"/task/expressive-speech-synthesis","name":"Expressive Speech Synthesis","slug":"expressive-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":"derived"},"counts":{"papers_tagged":47,"papers_with_code":13,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"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":13,"of":13,"tagged_in_all":47,"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/enhancing-suno-s-bark-text-to-speech-model","title":"Enhancing Suno's Bark Text-to-Speech Model: Addressing Limitations Through Meta's Encodec and Pre-Trained Hubert","date":"2023-04-18","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/towards-end-to-end-prosody-transfer-for","title":"Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron","date":"2018-03-24","arxiv_id":"1803.09047","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/rasa-building-expressive-speech-synthesis","title":"Rasa: Building Expressive Speech Synthesis Systems for Indian Languages in Low-resource Settings","date":"2024-07-19","arxiv_id":"2407.14056","repositories_listed":1,"syntology":null},{"url":"/paper/articulatory-phonetics-informed-controllable","title":"Articulatory Phonetics Informed Controllable Expressive Speech Synthesis","date":"2024-06-15","arxiv_id":"2406.10514","repositories_listed":1,"syntology":null},{"url":"/paper/diffprosody-diffusion-based-latent-prosody","title":"DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training","date":"2023-07-31","arxiv_id":"2307.16549","repositories_listed":1,"syntology":null},{"url":"/paper/sc-vall-e-style-controllable-zero-shot-text","title":"SC VALL-E: Style-Controllable Zero-Shot Text to Speech Synthesizer","date":"2023-07-20","arxiv_id":"2307.10550","repositories_listed":1,"syntology":null},{"url":"/paper/emns-imz-corpus-an-emotive-single-speaker","title":"EMNS /Imz/ Corpus: An emotive single-speaker dataset for narrative storytelling in games, television and graphic novels","date":"2023-05-22","arxiv_id":"2305.13137","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/cross-speaker-emotion-transfer-based-on","title":"Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech","date":"2021-10-08","arxiv_id":"2110.04153","repositories_listed":1,"syntology":null},{"url":"/paper/laughter-synthesis-combining-seq2seq-modeling","title":"Laughter Synthesis: Combining Seq2seq modeling with Transfer Learning","date":"2020-08-20","arxiv_id":"2008.09483","repositories_listed":1,"syntology":null},{"url":"/paper/effective-use-of-variational-embedding","title":"Effective Use of Variational Embedding Capacity in Expressive End-to-End Speech Synthesis","date":"2019-06-08","arxiv_id":"1906.03402","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},{"url":"/paper/robust-and-fine-grained-prosody-control-of","title":"Robust and fine-grained prosody control of end-to-end speech synthesis","date":"2018-11-06","arxiv_id":"1811.02122","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}}],"syntology_records":3,"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"}}