{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":47,"of":47,"of_with_code":13,"tagged_in_all":47,"counts":{"archive_papers_tagged":47,"with_a_code_link":13,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":47,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/exploring-transfer-learning-for-low-resource","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-end-to-end-prosody-transfer-for#ran","syntology_url":"https://syntology.ai/paper/1803.09047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.09047"}},"official":null}},{"url":"/paper/rasa-building-expressive-speech-synthesis","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/emns-imz-corpus-an-emotive-single-speaker#ran","syntology_url":"https://syntology.ai/paper/2305.13137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13137"}},"official":{"repos":["knoriy/emns-dct"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-speaker-emotion-transfer-based-on","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-and-fine-grained-prosody-control-of#ran","syntology_url":"https://syntology.ai/paper/1811.02122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.02122"}},"official":null}},{"url":null,"slug":"nonverbaltts-a-public-english-corpus-of-text","title":"NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech","date":"2025-07-17","arxiv_id":"2507.13155","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-unseen-emotion-zero-shot-expressive","title":"Prompt-Unseen-Emotion: Zero-shot Expressive Speech Synthesis with Prompt-LLM Contextual Knowledge for Mixed Emotions","date":"2025-06-03","arxiv_id":"2506.02742","repositories_listed":0,"syntology":null},{"url":null,"slug":"rasmalai-resources-for-adaptive-speech","title":"RASMALAI: Resources for Adaptive Speech Modeling in Indian Languages with Accents and Intonations","date":"2025-05-24","arxiv_id":"2505.18609","repositories_listed":0,"syntology":null},{"url":null,"slug":"gender-bias-in-instruction-guided-speech","title":"Gender Bias in Instruction-Guided Speech Synthesis Models","date":"2025-02-08","arxiv_id":"2502.05649","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-synthesis-along-perceptual-voice","title":"Speech Synthesis along Perceptual Voice Quality Dimensions","date":"2025-01-15","arxiv_id":"2501.08791","repositories_listed":0,"syntology":null},{"url":null,"slug":"mscenespeech-a-multi-scene-speech-dataset-for","title":"MSceneSpeech: A Multi-Scene Speech Dataset For Expressive Speech Synthesis","date":"2024-07-19","arxiv_id":"2407.14006","repositories_listed":0,"syntology":null},{"url":null,"slug":"expressivity-and-speech-synthesis","title":"Expressivity and Speech Synthesis","date":"2024-04-30","arxiv_id":"2404.19363","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-speaker-expressive-speech-synthesis-via-1","title":"Boosting Multi-Speaker Expressive Speech Synthesis with Semi-supervised Contrastive Learning","date":"2023-10-26","arxiv_id":"2310.17101","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-spontaneous-style-modeling-with-semi","title":"Towards Spontaneous Style Modeling with Semi-supervised Pre-training for Conversational Text-to-Speech Synthesis","date":"2023-08-31","arxiv_id":"2308.16593","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-prosody-transfer-for-expressive","title":"Cross-lingual Prosody Transfer for Expressive Machine Dubbing","date":"2023-06-20","arxiv_id":"2306.11658","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensemble-prosody-prediction-for-expressive","title":"Ensemble prosody prediction for expressive speech synthesis","date":"2023-04-03","arxiv_id":"2304.00714","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-granularity-of-prosodic-representations-in","title":"On granularity of prosodic representations in expressive text-to-speech","date":"2023-01-26","arxiv_id":"2301.11446","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-speaker-expressive-speech-synthesis-via","title":"Multi-Speaker Expressive Speech Synthesis via Multiple Factors Decoupling","date":"2022-11-19","arxiv_id":"2211.10568","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-phoneme-level-prosody-latents","title":"Predicting phoneme-level prosody latents using AR and flow-based Prior Networks for expressive speech synthesis","date":"2022-11-02","arxiv_id":"2211.01327","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-utterance-level-representations","title":"Learning utterance-level representations through token-level acoustic latents prediction for Expressive Speech Synthesis","date":"2022-11-01","arxiv_id":"2211.00523","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-context-aware-style","title":"Self-supervised Context-aware Style Representation for Expressive Speech Synthesis","date":"2022-06-25","arxiv_id":"2206.12559","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-noise-control-for-multispeaker","title":"Fine-grained Noise Control for Multispeaker Speech Synthesis","date":"2022-04-11","arxiv_id":"2204.05070","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-expressive-speaking-style-modelling","title":"Towards Expressive Speaking Style Modelling with Hierarchical Context Information for Mandarin Speech Synthesis","date":"2022-03-23","arxiv_id":"2203.12201","repositories_listed":0,"syntology":null},{"url":null,"slug":"word-level-style-control-for-expressive-non","title":"Word-Level Style Control for Expressive, Non-attentive Speech Synthesis","date":"2021-11-19","arxiv_id":"2111.10173","repositories_listed":0,"syntology":null},{"url":null,"slug":"referee-towards-reference-free-cross-speaker","title":"Referee: Towards reference-free cross-speaker style transfer with low-quality data for expressive speech synthesis","date":"2021-09-08","arxiv_id":"2109.03439","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-speaker-style-transfer-with-prosody","title":"Cross-speaker Style Transfer with Prosody Bottleneck in Neural Speech Synthesis","date":"2021-07-27","arxiv_id":"2107.12562","repositories_listed":0,"syntology":null},{"url":null,"slug":"unitts-residual-learning-of-unified-embedding","title":"UniTTS: Residual Learning of Unified Embedding Space for Speech Style Control","date":"2021-06-21","arxiv_id":"2106.11171","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-multi-scale-style-control-for","title":"Towards Multi-Scale Style Control for Expressive Speech Synthesis","date":"2021-04-08","arxiv_id":"2104.03521","repositories_listed":0,"syntology":null},{"url":null,"slug":"sentiment-analysis-for-emotional-speech","title":"Sentiment Analysis for Emotional Speech Synthesis in a News Dialogue System","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-multi-grained-generative-model","title":"Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis","date":"2020-09-17","arxiv_id":"2009.08474","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-vaes-and-normalizing-flows-for-one-shot","title":"Using VAEs and Normalizing Flows for One-shot Text-To-Speech Synthesis of Expressive Speech","date":"2019-11-28","arxiv_id":"1911.12760","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-theory-behind-controllable-expressive","title":"The Theory behind Controllable Expressive Speech Synthesis: a Cross-disciplinary Approach","date":"2019-10-14","arxiv_id":"1910.06234","repositories_listed":0,"syntology":null},{"url":null,"slug":"synpaflex-corpus-an-expressive-french","title":"SynPaFlex-Corpus: An Expressive French Audiobooks Corpus dedicated to expressive speech synthesis.","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"expressive-speech-synthesis-via-modeling","title":"Expressive Speech Synthesis via Modeling Expressions with Variational Autoencoder","date":"2018-04-06","arxiv_id":"1804.02135","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncovering-latent-style-factors-for","title":"Uncovering Latent Style Factors for Expressive Speech Synthesis","date":"2017-11-01","arxiv_id":"1711.00520","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-expressive-speaking-styles","title":"Continuous Expressive Speaking Styles Synthesis based on CVSM and MR-HMM","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-manual-and-automatic-prosodic","title":"Combining Manual and Automatic Prosodic Annotation for Expressive Speech Synthesis","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"alert-calm-down-there-is-nothing-to-worry","title":"Alert!... Calm Down, There is Nothing to Worry About. Warning and Soothing Speech Synthesis.","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-expressive-speech-synthesis-from","title":"Evaluating expressive speech synthesis from audiobook corpora for conversational phrases","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/task/expressive-speech-synthesis/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/expressive-speech-synthesis/papers/ran/1","json":"/task/expressive-speech-synthesis/papers/ran/1.json","rows":3}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"24b6e653eaba713f41375f933141f000865b8dd7a8f792b73515af51a9d97c49","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}