{"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/audio-synthesis","name":"Audio Synthesis","slug":"audio-synthesis","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":127,"papers_with_code":55,"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":0},"benchmarks":[],"datasets":[{"url":"/dataset/https-trinityspeechgesture-scss-tcd-ie","name":"Trinity Speech-Gesture Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/mdrt","name":"mDRT","full_name":"Multilingual Diagnostic Rhyme Test","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":2,"rows_per_page":100,"shown":100,"of":127,"of_with_code":55,"tagged_in_all":127,"counts":{"archive_papers_tagged":127,"with_a_code_link":55,"where_syntology_ran_a_sample":24,"not_listed_spam_title":0,"listed":127,"listed_where_code_ran":24,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":18,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":18,"listed_every_run_a_failure_of_syntologys_instrument":6,"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/an-empirical-evaluation-of-generic","slug":"an-empirical-evaluation-of-generic","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","date":"2018-03-04","arxiv_id":"1803.01271","repositories_listed":35,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/an-empirical-evaluation-of-generic#ran","syntology_url":"https://syntology.ai/paper/1803.01271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.01271"}},"official":{"repos":["locuslab/TCN"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/tacotron-towards-end-to-end-speech-synthesis","slug":"tacotron-towards-end-to-end-speech-synthesis","title":"Tacotron: Towards End-to-End Speech Synthesis","date":"2017-03-29","arxiv_id":"1703.10135","repositories_listed":30,"syntology":{"n":25,"n_ran":16,"n_constructed":0,"n_ran_checked":13,"n_instrument":3,"n_unverified":9,"n_honours":3,"n_violates":1,"n_no_contract":9,"n_pointer_only":6,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 1 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/tacotron-towards-end-to-end-speech-synthesis#ran","syntology_url":"https://syntology.ai/paper/1703.10135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.10135"}},"official":null}},{"url":"/paper/adversarial-audio-synthesis","slug":"adversarial-audio-synthesis","title":"Adversarial Audio Synthesis","date":"2018-02-12","arxiv_id":"1802.04208","repositories_listed":22,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 2 unverified","sample_list":"/paper/adversarial-audio-synthesis#ran","syntology_url":"https://syntology.ai/paper/1802.04208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.04208"}},"official":{"repos":["chrisdonahue/wavegan"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/efficient-neural-audio-synthesis","slug":"efficient-neural-audio-synthesis","title":"Efficient Neural Audio Synthesis","date":"2018-02-23","arxiv_id":"1802.08435","repositories_listed":16,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-neural-audio-synthesis#ran","syntology_url":"https://syntology.ai/paper/1802.08435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.08435"}},"official":null}},{"url":"/paper/diffwave-a-versatile-diffusion-model-for","slug":"diffwave-a-versatile-diffusion-model-for","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","date":"2020-09-21","arxiv_id":"2009.09761","repositories_listed":11,"syntology":{"n":33,"n_ran":20,"n_constructed":11,"n_ran_checked":13,"n_instrument":7,"n_unverified":13,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"20 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 7 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/diffwave-a-versatile-diffusion-model-for#ran","syntology_url":"https://syntology.ai/paper/2009.09761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.09761"}},"official":null}},{"url":"/paper/differentiable-all-pole-filters-for-time","slug":"differentiable-all-pole-filters-for-time","title":"Differentiable All-pole Filters for Time-varying Audio Systems","date":"2024-04-11","arxiv_id":"2404.07970","repositories_listed":8,"syntology":null},{"url":"/paper/neural-audio-synthesis-of-musical-notes-with","slug":"neural-audio-synthesis-of-musical-notes-with","title":"Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders","date":"2017-04-05","arxiv_id":"1704.01279","repositories_listed":8,"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/neural-audio-synthesis-of-musical-notes-with#ran","syntology_url":"https://syntology.ai/paper/1704.01279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.01279"}},"official":null}},{"url":"/paper/gansynth-adversarial-neural-audio-synthesis","slug":"gansynth-adversarial-neural-audio-synthesis","title":"GANSynth: Adversarial Neural Audio Synthesis","date":"2019-02-23","arxiv_id":"1902.08710","repositories_listed":6,"syntology":null},{"url":"/paper/bigvgan-a-universal-neural-vocoder-with-large","slug":"bigvgan-a-universal-neural-vocoder-with-large","title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","date":"2022-06-09","arxiv_id":"2206.04658","repositories_listed":5,"syntology":{"n":17,"n_ran":15,"n_constructed":2,"n_ran_checked":12,"n_instrument":3,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":9,"n_pointer_only":9,"phrase":"15 ran (of which 2 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/bigvgan-a-universal-neural-vocoder-with-large#ran","syntology_url":"https://syntology.ai/paper/2206.04658","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.04658"}},"official":{"repos":["nvidia/bigvgan"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","listed"]}}},{"url":"/paper/csdi-conditional-score-based-diffusion-models","slug":"csdi-conditional-score-based-diffusion-models","title":"CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation","date":"2021-07-07","arxiv_id":"2107.03502","repositories_listed":5,"syntology":{"n":19,"n_ran":12,"n_constructed":4,"n_ran_checked":10,"n_instrument":2,"n_unverified":7,"n_honours":2,"n_violates":0,"n_no_contract":8,"n_pointer_only":3,"phrase":"12 ran (of which 4 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/csdi-conditional-score-based-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2107.03502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.03502"}},"official":{"repos":["WenjieDu/PyPOTS"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","named_in_paper"]}}},{"url":"/paper/differentiable-time-varying-linear-prediction","slug":"differentiable-time-varying-linear-prediction","title":"Differentiable Time-Varying Linear Prediction in the Context of End-to-End Analysis-by-Synthesis","date":"2024-06-07","arxiv_id":"2406.05128","repositories_listed":4,"syntology":null},{"url":"/paper/vocos-closing-the-gap-between-time-domain-and","slug":"vocos-closing-the-gap-between-time-domain-and","title":"Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis","date":"2023-06-01","arxiv_id":"2306.00814","repositories_listed":4,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/vocos-closing-the-gap-between-time-domain-and#ran","syntology_url":"https://syntology.ai/paper/2306.00814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00814"}},"official":{"repos":["gemelo-ai/vocos"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/rave-a-variational-autoencoder-for-fast-and-1","slug":"rave-a-variational-autoencoder-for-fast-and-1","title":"RAVE: A variational autoencoder for fast and high-quality neural audio synthesis","date":"2021-11-09","arxiv_id":"2111.05011","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rave-a-variational-autoencoder-for-fast-and-1#ran","syntology_url":"https://syntology.ai/paper/2111.05011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.05011"}},"official":{"repos":["caillonantoine/RAVE"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/speedyspeech-efficient-neural-speech","slug":"speedyspeech-efficient-neural-speech","title":"SpeedySpeech: Efficient Neural Speech Synthesis","date":"2020-08-09","arxiv_id":"2008.03802","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":0,"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/speedyspeech-efficient-neural-speech#ran","syntology_url":"https://syntology.ai/paper/2008.03802","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.03802"}},"official":{"repos":["janvainer/speedyspeech"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ddsp-differentiable-digital-signal-processing-1","slug":"ddsp-differentiable-digital-signal-processing-1","title":"DDSP: Differentiable Digital Signal Processing","date":"2020-01-14","arxiv_id":"2001.04643","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ddsp-differentiable-digital-signal-processing-1#ran","syntology_url":"https://syntology.ai/paper/2001.04643","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.04643"}},"official":{"repos":["magenta/ddsp"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-voice-real-time-neural-text-to-speech","slug":"deep-voice-real-time-neural-text-to-speech","title":"Deep Voice: Real-time Neural Text-to-Speech","date":"2017-02-25","arxiv_id":"1702.07825","repositories_listed":3,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deep-voice-real-time-neural-text-to-speech#ran","syntology_url":"https://syntology.ai/paper/1702.07825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.07825"}},"official":null}},{"url":"/paper/audiolcm-text-to-audio-generation-with-latent","slug":"audiolcm-text-to-audio-generation-with-latent","title":"AudioLCM: Text-to-Audio Generation with Latent Consistency Models","date":"2024-06-01","arxiv_id":"2406.00356","repositories_listed":2,"syntology":null},{"url":"/paper/fre-gan-adversarial-frequency-consistent","slug":"fre-gan-adversarial-frequency-consistent","title":"Fre-GAN: Adversarial Frequency-consistent Audio Synthesis","date":"2021-06-04","arxiv_id":"2106.02297","repositories_listed":2,"syntology":null},{"url":"/paper/real-time-timbre-transfer-and-sound-synthesis","slug":"real-time-timbre-transfer-and-sound-synthesis","title":"Real-time Timbre Transfer and Sound Synthesis using DDSP","date":"2021-03-12","arxiv_id":"2103.07220","repositories_listed":2,"syntology":null},{"url":"/paper/waveglow-a-flow-based-generative-network-for","slug":"waveglow-a-flow-based-generative-network-for","title":"WaveGlow: A Flow-based Generative Network for Speech Synthesis","date":"2018-10-31","arxiv_id":"1811.00002","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/waveglow-a-flow-based-generative-network-for#ran","syntology_url":"https://syntology.ai/paper/1811.00002","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.00002"}},"official":null}},{"url":"/paper/fast-differentiable-modal-simulation-of-non","slug":"fast-differentiable-modal-simulation-of-non","title":"Fast Differentiable Modal Simulation of Non-linear Strings, Membranes, and Plates","date":"2025-05-09","arxiv_id":"2505.05940","repositories_listed":1,"syntology":null},{"url":"/paper/generative-diffusion-model-with-inverse","slug":"generative-diffusion-model-with-inverse","title":"Generative diffusion model with inverse renormalization group flows","date":"2025-01-15","arxiv_id":"2501.09064","repositories_listed":1,"syntology":null},{"url":"/paper/taming-multimodal-joint-training-for-high","slug":"taming-multimodal-joint-training-for-high","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","date":"2024-12-19","arxiv_id":"2412.15322","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/taming-multimodal-joint-training-for-high#ran","syntology_url":"https://syntology.ai/paper/2412.15322","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15322"}},"official":{"repos":["hkchengrex/MMAudio"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/omniflow-any-to-any-generation-with-multi","slug":"omniflow-any-to-any-generation-with-multi","title":"OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows","date":"2024-12-02","arxiv_id":"2412.01169","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/omniflow-any-to-any-generation-with-multi#ran","syntology_url":"https://syntology.ai/paper/2412.01169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01169"}},"official":{"repos":["jacklishufan/omniflows"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sonar-a-synthetic-ai-audio-detection","slug":"sonar-a-synthetic-ai-audio-detection","title":"Where are we in audio deepfake detection? A systematic analysis over generative and detection models","date":"2024-10-06","arxiv_id":"2410.04324","repositories_listed":1,"syntology":null},{"url":"/paper/violindiff-enhancing-expressive-violin","slug":"violindiff-enhancing-expressive-violin","title":"ViolinDiff: Enhancing Expressive Violin Synthesis with Pitch Bend Conditioning","date":"2024-09-19","arxiv_id":"2409.12477","repositories_listed":1,"syntology":null},{"url":"/paper/litefocus-accelerated-diffusion-inference-for","slug":"litefocus-accelerated-diffusion-inference-for","title":"LiteFocus: Accelerated Diffusion Inference for Long Audio Synthesis","date":"2024-07-15","arxiv_id":"2407.10468","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/litefocus-accelerated-diffusion-inference-for#ran","syntology_url":"https://syntology.ai/paper/2407.10468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.10468"}},"official":{"repos":["yuanshi9815/litefocus"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/taming-data-and-transformers-for-audio-1","slug":"taming-data-and-transformers-for-audio-1","title":"Taming Data and Transformers for Audio Generation","date":"2024-06-27","arxiv_id":"2406.19388","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-ts-interpretable-diffusion-for","slug":"diffusion-ts-interpretable-diffusion-for","title":"Diffusion-TS: Interpretable Diffusion for General Time Series Generation","date":"2024-03-04","arxiv_id":"2403.01742","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/diffusion-ts-interpretable-diffusion-for#ran","syntology_url":"https://syntology.ai/paper/2403.01742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01742"}},"official":{"repos":["y-debug-sys/diffusion-ts"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/diffmoog-a-differentiable-modular-synthesizer","slug":"diffmoog-a-differentiable-modular-synthesizer","title":"DiffMoog: a Differentiable Modular Synthesizer for Sound Matching","date":"2024-01-23","arxiv_id":"2401.12570","repositories_listed":1,"syntology":null},{"url":"/paper/t-foley-a-controllable-waveform-domain","slug":"t-foley-a-controllable-waveform-domain","title":"T-FOLEY: A Controllable Waveform-Domain Diffusion Model for Temporal-Event-Guided Foley Sound Synthesis","date":"2024-01-17","arxiv_id":"2401.09294","repositories_listed":1,"syntology":null},{"url":"/paper/facetalk-audio-driven-motion-diffusion-for","slug":"facetalk-audio-driven-motion-diffusion-for","title":"FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models","date":"2023-12-13","arxiv_id":"2312.08459","repositories_listed":1,"syntology":null},{"url":"/paper/diff-foley-synchronized-video-to-audio-1","slug":"diff-foley-synchronized-video-to-audio-1","title":"Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models","date":"2023-06-29","arxiv_id":"2306.17203","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diff-foley-synchronized-video-to-audio-1#ran","syntology_url":"https://syntology.ai/paper/2306.17203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.17203"}},"official":null}},{"url":"/paper/continuous-descriptor-based-control-for-deep","slug":"continuous-descriptor-based-control-for-deep","title":"Continuous descriptor-based control for deep audio synthesis","date":"2023-02-27","arxiv_id":"2302.13542","repositories_listed":1,"syntology":null},{"url":"/paper/perceptual-neural-physical-sound-matching","slug":"perceptual-neural-physical-sound-matching","title":"Perceptual-Neural-Physical Sound Matching","date":"2023-01-07","arxiv_id":"2301.02886","repositories_listed":1,"syntology":null},{"url":"/paper/score-based-generative-modeling-secretly","slug":"score-based-generative-modeling-secretly","title":"Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance","date":"2022-12-13","arxiv_id":"2212.06359","repositories_listed":1,"syntology":null},{"url":"/paper/from-words-to-sound-neural-audio-synthesis-of","slug":"from-words-to-sound-neural-audio-synthesis-of","title":"From Words to Sound: Neural Audio Synthesis of Guitar Sounds with Timbral Descriptors","date":"2022-09-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/realistic-gramophone-noise-synthesis-using-a","slug":"realistic-gramophone-noise-synthesis-using-a","title":"Realistic Gramophone Noise Synthesis using a Diffusion Model","date":"2022-06-13","arxiv_id":"2206.06259","repositories_listed":1,"syntology":null},{"url":"/paper/binauralgrad-a-two-stage-conditional","slug":"binauralgrad-a-two-stage-conditional","title":"BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesis","date":"2022-05-30","arxiv_id":"2205.14807","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/binauralgrad-a-two-stage-conditional#ran","syntology_url":"https://syntology.ai/paper/2205.14807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14807"}},"official":{"repos":["microsoft/NeuralSpeech"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/midi-ddsp-detailed-control-of-musical-1","slug":"midi-ddsp-detailed-control-of-musical-1","title":"MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling","date":"2021-12-17","arxiv_id":"2112.09312","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/midi-ddsp-detailed-control-of-musical-1#ran","syntology_url":"https://syntology.ai/paper/2112.09312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.09312"}},"official":{"repos":["magenta/midi-ddsp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/differentiable-wavetable-synthesis","slug":"differentiable-wavetable-synthesis","title":"Differentiable Wavetable Synthesis","date":"2021-11-19","arxiv_id":"2111.10003","repositories_listed":1,"syntology":null},{"url":"/paper/caesynth-real-time-timbre-interpolation-and","slug":"caesynth-real-time-timbre-interpolation-and","title":"CAESynth: Real-Time Timbre Interpolation and Pitch Control with Conditional Autoencoders","date":"2021-11-09","arxiv_id":"2111.05174","repositories_listed":1,"syntology":null},{"url":"/paper/neural-waveshaping-synthesis","slug":"neural-waveshaping-synthesis","title":"Neural Waveshaping Synthesis","date":"2021-07-11","arxiv_id":"2107.05050","repositories_listed":1,"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/neural-waveshaping-synthesis#ran","syntology_url":"https://syntology.ai/paper/2107.05050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.05050"}},"official":{"repos":["ben-hayes/neural-waveshaping-synthesis"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vqcpc-gan-variable-length-adversarial-audio","slug":"vqcpc-gan-variable-length-adversarial-audio","title":"VQCPC-GAN: Variable-Length Adversarial Audio Synthesis Using Vector-Quantized Contrastive Predictive Coding","date":"2021-05-04","arxiv_id":"2105.01531","repositories_listed":1,"syntology":null},{"url":"/paper/points2sound-from-mono-to-binaural-audio","slug":"points2sound-from-mono-to-binaural-audio","title":"Points2Sound: From mono to binaural audio using 3D point cloud scenes","date":"2021-04-26","arxiv_id":"2104.12462","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/points2sound-from-mono-to-binaural-audio#ran","syntology_url":"https://syntology.ai/paper/2104.12462","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12462"}},"official":{"repos":["francesclluis/points2sound"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/upsampling-artifacts-in-neural-audio","slug":"upsampling-artifacts-in-neural-audio","title":"Upsampling artifacts in neural audio synthesis","date":"2020-10-27","arxiv_id":"2010.14356","repositories_listed":1,"syntology":null},{"url":"/paper/drumgan-synthesis-of-drum-sounds-with-timbral","slug":"drumgan-synthesis-of-drum-sounds-with-timbral","title":"DrumGAN: Synthesis of Drum Sounds With Timbral Feature Conditioning Using Generative Adversarial Networks","date":"2020-08-27","arxiv_id":"2008.12073","repositories_listed":1,"syntology":null},{"url":"/paper/audeo-audio-generation-for-a-silent","slug":"audeo-audio-generation-for-a-silent","title":"Audeo: Audio Generation for a Silent Performance Video","date":"2020-06-23","arxiv_id":"2006.14348","repositories_listed":1,"syntology":null},{"url":"/paper/generative-modelling-for-controllable-audio","slug":"generative-modelling-for-controllable-audio","title":"Generative Modelling for Controllable Audio Synthesis of Expressive Piano Performance","date":"2020-06-16","arxiv_id":"2006.09833","repositories_listed":1,"syntology":null},{"url":"/paper/introducing-latent-timbre-synthesis","slug":"introducing-latent-timbre-synthesis","title":"Introducing Latent Timbre Synthesis","date":"2020-05-31","arxiv_id":"2006.00408","repositories_listed":1,"syntology":null},{"url":"/paper/vapar-synth-a-variational-parametric-model","slug":"vapar-synth-a-variational-parametric-model","title":"VaPar Synth -- A Variational Parametric Model for Audio Synthesis","date":"2020-03-30","arxiv_id":"2004.00001","repositories_listed":1,"syntology":null},{"url":"/paper/music-source-separation-in-the-waveform-1","slug":"music-source-separation-in-the-waveform-1","title":"Music Source Separation in the Waveform Domain","date":"2019-11-27","arxiv_id":"1911.13254","repositories_listed":1,"syntology":null},{"url":"/paper/a-prior-of-a-googol-gaussians-a-tensor-ring","slug":"a-prior-of-a-googol-gaussians-a-tensor-ring","title":"A Prior of a Googol Gaussians: a Tensor Ring Induced Prior for Generative Models","date":"2019-10-29","arxiv_id":"1910.13148","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-generation-of-time-frequency","slug":"adversarial-generation-of-time-frequency","title":"Adversarial Generation of Time-Frequency Features with application in audio synthesis","date":"2019-02-11","arxiv_id":"1902.04072","repositories_listed":1,"syntology":null},{"url":"/paper/sing-symbol-to-instrument-neural-generator","slug":"sing-symbol-to-instrument-neural-generator","title":"SING: Symbol-to-Instrument Neural Generator","date":"2018-10-23","arxiv_id":"1810.09785","repositories_listed":1,"syntology":null},{"url":null,"slug":"midi-valle-improving-expressive-piano","title":"MIDI-VALLE: Improving Expressive Piano Performance Synthesis Through Neural Codec Language Modelling","date":"2025-07-11","arxiv_id":"2507.08530","repositories_listed":0,"syntology":null},{"url":null,"slug":"step-by-step-video-to-audio-synthesis-via","title":"Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidance","date":"2025-06-26","arxiv_id":"2506.20995","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-based-symbolic-regression","title":"Diffusion-Based Symbolic Regression","date":"2025-05-30","arxiv_id":"2505.24776","repositories_listed":0,"syntology":null},{"url":null,"slug":"specmaskfoley-steering-pretrained-spectral","title":"SpecMaskFoley: Steering Pretrained Spectral Masked Generative Transformer Toward Synchronized Video-to-audio Synthesis via ControlNet","date":"2025-05-22","arxiv_id":"2505.16195","repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-efficient-diffusion-denoising","title":"Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism","date":"2025-05-20","arxiv_id":"2505.14741","repositories_listed":0,"syntology":null},{"url":null,"slug":"dpn-gan-inducing-periodic-activations-in","title":"DPN-GAN: Inducing Periodic Activations in Generative Adversarial Networks for High-Fidelity Audio Synthesis","date":"2025-05-14","arxiv_id":"2505.09091","repositories_listed":0,"syntology":null},{"url":null,"slug":"supervising-3d-talking-head-avatars-with","title":"Supervising 3D Talking Head Avatars with Analysis-by-Audio-Synthesis","date":"2025-04-18","arxiv_id":"2504.13386","repositories_listed":0,"syntology":null},{"url":null,"slug":"taro-timestep-adaptive-representation","title":"TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis","date":"2025-04-08","arxiv_id":"2504.05684","repositories_listed":0,"syntology":null},{"url":null,"slug":"designing-neural-synthesizers-for-low-latency","title":"Designing Neural Synthesizers for Low-Latency Interaction","date":"2025-03-14","arxiv_id":"2503.11562","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-video-audio-synthesis-with-multi-agent","title":"Long-Video Audio Synthesis with Multi-Agent Collaboration","date":"2025-03-13","arxiv_id":"2503.10719","repositories_listed":0,"syntology":null},{"url":null,"slug":"nexus-o-an-omni-perceptive-and-interactive","title":"Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision","date":"2025-02-26","arxiv_id":"2503.01879","repositories_listed":0,"syntology":null},{"url":null,"slug":"xattnmark-learning-robust-audio-watermarking","title":"XAttnMark: Learning Robust Audio Watermarking with Cross-Attention","date":"2025-02-06","arxiv_id":"2502.04230","repositories_listed":0,"syntology":null},{"url":null,"slug":"customized-condition-controllable-generation","title":"Customized Condition Controllable Generation for Video Soundtrack","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tri-ergon-fine-grained-video-to-audio","title":"Tri-Ergon: Fine-grained Video-to-Audio Generation with Multi-modal Conditions and LUFS Control","date":"2024-12-29","arxiv_id":"2412.20378","repositories_listed":0,"syntology":null},{"url":null,"slug":"cssinger-end-to-end-chunkwise-streaming","title":"CSSinger: End-to-End Chunkwise Streaming Singing Voice Synthesis System Based on Conditional Variational Autoencoder","date":"2024-12-12","arxiv_id":"2412.08918","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-mono-to-binaural-speech-synthesis","title":"Zero-Shot Mono-to-Binaural Speech Synthesis","date":"2024-12-11","arxiv_id":"2412.08356","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-diffusion-model-with-adjusted","title":"Generalized Diffusion Model with Adjusted Offset Noise","date":"2024-12-04","arxiv_id":"2412.03134","repositories_listed":0,"syntology":null},{"url":null,"slug":"vqalattent-a-transparent-speech-generation","title":"VQalAttent: a Transparent Speech Generation Pipeline based on Transformer-learned VQ-VAE Latent Space","date":"2024-11-22","arxiv_id":"2411.14642","repositories_listed":0,"syntology":null},{"url":null,"slug":"annotation-free-midi-to-audio-synthesis-via","title":"Annotation-Free MIDI-to-Audio Synthesis via Concatenative Synthesis and Generative Refinement","date":"2024-10-22","arxiv_id":"2410.16785","repositories_listed":0,"syntology":null},{"url":null,"slug":"array2br-an-end-to-end-noise-immune-binaural","title":"Array2BR: An End-to-End Noise-immune Binaural Audio Synthesis from Microphone-array Signals","date":"2024-10-08","arxiv_id":"2410.05739","repositories_listed":0,"syntology":null},{"url":null,"slug":"ptq4adm-post-training-quantization-for","title":"PTQ4ADM: Post-Training Quantization for Efficient Text Conditional Audio Diffusion Models","date":"2024-09-20","arxiv_id":"2409.13894","repositories_listed":0,"syntology":null},{"url":null,"slug":"d-captcha-a-study-of-resilience-of-deepfake","title":"D-CAPTCHA++: A Study of Resilience of Deepfake CAPTCHA under Transferable Imperceptible Adversarial Attack","date":"2024-09-11","arxiv_id":"2409.07390","repositories_listed":0,"syntology":null},{"url":null,"slug":"draw-an-audio-leveraging-multi-instruction","title":"Draw an Audio: Leveraging Multi-Instruction for Video-to-Audio Synthesis","date":"2024-09-10","arxiv_id":"2409.06135","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-high-quality-and-parameter-efficient","title":"Fast, High-Quality and Parameter-Efficient Articulatory Synthesis using Differentiable DSP","date":"2024-09-04","arxiv_id":"2409.02451","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-generative-modeling-of-melodic","title":"Hierarchical Generative Modeling of Melodic Vocal Contours in Hindustani Classical Music","date":"2024-08-22","arxiv_id":"2408.12658","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-foley-two-stage-video-to-sound","title":"Video-Foley: Two-Stage Video-To-Sound Generation via Temporal Event Condition For Foley Sound","date":"2024-08-21","arxiv_id":"2408.11915","repositories_listed":0,"syntology":null},{"url":null,"slug":"egosonics-generating-synchronized-audio-for","title":"EgoSonics: Generating Synchronized Audio for Silent Egocentric Videos","date":"2024-07-30","arxiv_id":"2407.20592","repositories_listed":0,"syntology":null},{"url":null,"slug":"braille-to-speech-generator-audio-generation","title":"Braille-to-Speech Generator: Audio Generation Based on Joint Fine-Tuning of CLIP and Fastspeech2","date":"2024-07-19","arxiv_id":"2407.14212","repositories_listed":0,"syntology":null},{"url":null,"slug":"groot-generating-robust-watermark-for","title":"GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio Synthesis","date":"2024-07-15","arxiv_id":"2407.10471","repositories_listed":0,"syntology":null},{"url":null,"slug":"av-gs-learning-material-and-geometry-aware","title":"AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis","date":"2024-06-13","arxiv_id":"2406.08920","repositories_listed":0,"syntology":null},{"url":null,"slug":"codecfake-enhancing-anti-spoofing-models","title":"CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems","date":"2024-06-11","arxiv_id":"2406.07237","repositories_listed":0,"syntology":null},{"url":null,"slug":"creative-text-to-audio-generation-via","title":"Creative Text-to-Audio Generation via Synthesizer Programming","date":"2024-06-01","arxiv_id":"2406.00294","repositories_listed":0,"syntology":null},{"url":null,"slug":"fill-in-the-gap-combining-self-supervised","title":"Fill in the Gap! Combining Self-supervised Representation Learning with Neural Audio Synthesis for Speech Inpainting","date":"2024-05-30","arxiv_id":"2405.20101","repositories_listed":0,"syntology":null},{"url":null,"slug":"text2data-low-resource-data-generation-with","title":"Text2Data: Low-Resource Data Generation with Textual Control","date":"2024-02-08","arxiv_id":"2402.10941","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-diffusion-gan-model-for-symbolic-music","title":"Fast Diffusion GAN Model for Symbolic Music Generation Controlled by Emotions","date":"2023-10-21","arxiv_id":"2310.14040","repositories_listed":0,"syntology":null},{"url":"/paper/unified-speech-and-gesture-synthesis-using","slug":"unified-speech-and-gesture-synthesis-using","title":"Unified speech and gesture synthesis using flow matching","date":"2023-10-08","arxiv_id":"2310.05181","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-audio-synthesis-from-tagged-mri-and","title":"Speech Audio Synthesis from Tagged MRI and Non-Negative Matrix Factorization via Plastic Transformer","date":"2023-09-26","arxiv_id":"2309.14586","repositories_listed":0,"syntology":null},{"url":null,"slug":"ddsp-sfx-acoustically-guided-sound-effects","title":"DDSP-SFX: Acoustically-guided sound effects generation with differentiable digital signal processing","date":"2023-09-14","arxiv_id":"2309.08060","repositories_listed":0,"syntology":null},{"url":null,"slug":"snakegan-a-universal-vocoder-leveraging-ddsp","title":"SnakeGAN: A Universal Vocoder Leveraging DDSP Prior Knowledge and Periodic Inductive Bias","date":"2023-09-14","arxiv_id":"2309.07803","repositories_listed":0,"syntology":null},{"url":null,"slug":"clipsonic-text-to-audio-synthesis-with","title":"CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models","date":"2023-06-16","arxiv_id":"2306.09635","repositories_listed":0,"syntology":null},{"url":null,"slug":"ecgan-self-supervised-generative-adversarial","title":"ECGAN: Self-supervised generative adversarial network for electrocardiography","date":"2023-01-23","arxiv_id":"2301.09496","repositories_listed":0,"syntology":null},{"url":null,"slug":"dopplerbas-binaural-audio-synthesis","title":"DopplerBAS: Binaural Audio Synthesis Addressing Doppler Effect","date":"2022-12-14","arxiv_id":"2212.07000","repositories_listed":0,"syntology":null},{"url":null,"slug":"conditional-variational-autoencoder-to","title":"Conditional variational autoencoder to improve neural audio synthesis for polyphonic music sound","date":"2022-11-16","arxiv_id":"2211.08715","repositories_listed":0,"syntology":null},{"url":null,"slug":"anisotropic-multiresolution-analyses-for-deep","title":"Anisotropic multiresolution analyses for deepfake detection","date":"2022-10-26","arxiv_id":"2210.14874","repositories_listed":0,"syntology":null},{"url":null,"slug":"full-band-general-audio-synthesis-with-score","title":"Full-band General Audio Synthesis with Score-based Diffusion","date":"2022-10-26","arxiv_id":"2210.14661","repositories_listed":0,"syntology":null}],"syntology_records":23,"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":24,"papers_where_code_ran_first_page":"/task/audio-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":"archive","page":2,"of":2,"url":"/task/audio-synthesis/papers/2","json":"/task/audio-synthesis/papers/2.json","rows":27},{"order":"ran","page":1,"of":1,"url":"/task/audio-synthesis/papers/ran/1","json":"/task/audio-synthesis/papers/ran/1.json","rows":24}],"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":"8255f99cf1db6c190908fd57f1d056719e0f729ddf996676d1539c6d564ac83d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}