{"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-generation","name":"Audio Generation","slug":"audio-generation","description_markdown":"Audio generation (synthesis) is the task of generating raw audio such as speech.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [MelNet](https://arxiv.org/pdf/1906.01083v1.pdf) )</span>","categories":[{"name":"Audio","url":"/area/audio"},{"name":"Music","url":"/area/music"},{"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":270,"papers_with_code":124,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"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":11,"subtasks":4,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/audio-generation-on-audiocaps","slug":"audio-generation-on-audiocaps","dataset":"AudioCaps","dataset_url":"/dataset/audiocaps","rows_in_archive":23,"metrics":["FD_openl3","FAD","FD","KL_passt","IS","CLAP_LAION","CLAP_MS"],"first_row_in_archive_order":{"model":"ETTA-FT-AC-100k","paper_title":"ETTA: Elucidating the Design Space of Text-to-Audio Models","paper_url":"/paper/etta-elucidating-the-design-space-of-text-to","paper_date":"2024-12-26","arxiv_id":"2412.19351","code_links":[{"title":"NVIDIA/elucidated-text-to-audio","url":"https://github.com/NVIDIA/elucidated-text-to-audio"}],"syntology":null}},{"leaderboard":"/sota/audio-generation-on-classical-music-5-seconds","slug":"audio-generation-on-classical-music-5-seconds","dataset":"Classical music, 5 seconds at 12 kHz","dataset_url":null,"rows_in_archive":2,"metrics":["Bits per byte"],"first_row_in_archive_order":{"model":"Sparse Transformer 152M (strided)","paper_title":"Generating Long Sequences with Sparse Transformers","paper_url":"/paper/190410509","paper_date":"2019-04-23","arxiv_id":"1904.10509","code_links":[{"title":"mistralai/mistral-src","url":"https://github.com/mistralai/mistral-src"},{"title":"openai/sparse_attention","url":"https://github.com/openai/sparse_attention"},{"title":"wilson1yan/VideoGPT","url":"https://github.com/wilson1yan/VideoGPT"},{"title":"ptillet/torch-blocksparse","url":"https://github.com/ptillet/torch-blocksparse"},{"title":"han-shi/SparseBERT","url":"https://github.com/han-shi/SparseBERT"},{"title":"jonahwinninghoff/Text-Summarization","url":"https://github.com/jonahwinninghoff/Text-Summarization"},{"title":"MindCode-4/code-11","url":"https://github.com/MindCode-4/code-11/tree/main/factorized-attention"}],"syntology":{"n":6,"n_ran":5,"n_constructed":4,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/190410509#ran","syntology_url":"https://syntology.ai/paper/1904.10509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.10509"}},"official":{"repos":["openai/sparse_attention"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/audio-generation-on-symphony-music","slug":"audio-generation-on-symphony-music","dataset":"Symphony music","dataset_url":"/dataset/symphonynet","rows_in_archive":1,"metrics":[" Human listening average results"],"first_row_in_archive_order":{"model":"SymphonyNet","paper_title":"Symphony Generation with Permutation Invariant Language Model","paper_url":"/paper/symphony-generation-with-permutation","paper_date":"2022-05-10","arxiv_id":"2205.05448","code_links":[{"title":"symphonynet/SymphonyNet","url":"https://github.com/symphonynet/SymphonyNet"}],"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/symphony-generation-with-permutation#ran","syntology_url":"https://syntology.ai/paper/2205.05448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.05448"}},"official":{"repos":["symphonynet/SymphonyNet"],"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"]}}}}],"datasets":[{"url":"/dataset/audiocaps","name":"AudioCaps","full_name":"","num_papers_in_archive":279},{"url":"/dataset/nsynth","name":"NSynth","full_name":"NSynth","num_papers_in_archive":138},{"url":"/dataset/maestro","name":"MAESTRO","full_name":"MAESTRO","num_papers_in_archive":118},{"url":"/dataset/movienet","name":"MovieNet","full_name":"MovieNet","num_papers_in_archive":54},{"url":"/dataset/symphonynet","name":"SymphonyNet","full_name":"SymphonyNet","num_papers_in_archive":10},{"url":"/dataset/nes-mdb","name":"NES-MDB","full_name":"Nintendo Entertainment System Music Database","num_papers_in_archive":7},{"url":"/dataset/adl-piano-midi","name":"ADL Piano MIDI","full_name":"","num_papers_in_archive":5},{"url":"/dataset/blizzard-challenge-2013","name":"Blizzard Challenge 2013","full_name":"Blizzard Challenge 2013 - English language tasks","num_papers_in_archive":5},{"url":"/dataset/dmelodies","name":"dMelodies","full_name":null,"num_papers_in_archive":4},{"url":"/dataset/audio-alpaca","name":"Audio-alpaca","full_name":"","num_papers_in_archive":2},{"url":"/dataset/medibeng","name":"MediBeng","full_name":"Synthetic Code-Switched Bengali-English Speech Conversations for Healthcare Applications","num_papers_in_archive":1}],"subtasks":[{"url":"/task/audio-super-resolution","name":"Audio Super-Resolution"},{"url":"/task/room-impulse-response-rir","name":"Room Impulse Response (RIR)"},{"url":"/task/video-to-sound-generation","name":"Video-to-Sound Generation"},{"url":"/task/voice-cloning","name":"Voice Cloning"}],"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":3,"rows_per_page":100,"shown":100,"of":270,"of_with_code":124,"tagged_in_all":270,"counts":{"archive_papers_tagged":270,"with_a_code_link":124,"where_syntology_ran_a_sample":57,"not_listed_spam_title":0,"listed":270,"listed_where_code_ran":57,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":49,"every_run_a_failure_of_syntologys_instrument":8,"listed_with_a_run_with_no_instrument_failure":49,"listed_every_run_a_failure_of_syntologys_instrument":8,"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/wavenet-a-generative-model-for-raw-audio","slug":"wavenet-a-generative-model-for-raw-audio","title":"WaveNet: A Generative Model for Raw Audio","date":"2016-09-12","arxiv_id":"1609.03499","repositories_listed":62,"syntology":{"n":103,"n_ran":65,"n_constructed":23,"n_ran_checked":52,"n_instrument":13,"n_unverified":38,"n_honours":2,"n_violates":1,"n_no_contract":49,"n_pointer_only":25,"phrase":"65 ran (of which 23 constructed an object rather than computing a result; 52 with no instrument failure: 2 honoured, 1 violated, 49 with no contract checked; 13 where Syntology's instrument failed) · 38 unverified","sample_list":"/paper/wavenet-a-generative-model-for-raw-audio#ran","syntology_url":"https://syntology.ai/paper/1609.03499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.03499"}},"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/audiolm-a-language-modeling-approach-to-audio","slug":"audiolm-a-language-modeling-approach-to-audio","title":"AudioLM: a Language Modeling Approach to Audio Generation","date":"2022-09-07","arxiv_id":"2209.03143","repositories_listed":6,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":2,"n_no_contract":8,"n_pointer_only":4,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 2 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/audiolm-a-language-modeling-approach-to-audio#ran","syntology_url":"https://syntology.ai/paper/2209.03143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.03143"}},"official":null}},{"url":"/paper/it-s-raw-audio-generation-with-state-space","slug":"it-s-raw-audio-generation-with-state-space","title":"It's Raw! Audio Generation with State-Space Models","date":"2022-02-20","arxiv_id":"2202.09729","repositories_listed":6,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"6 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; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/it-s-raw-audio-generation-with-state-space#ran","syntology_url":"https://syntology.ai/paper/2202.09729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.09729"}},"official":{"repos":["hazyresearch/state-spaces"],"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","unlocated"]}}},{"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/melnet-a-generative-model-for-audio-in-the","slug":"melnet-a-generative-model-for-audio-in-the","title":"MelNet: A Generative Model for Audio in the Frequency Domain","date":"2019-06-04","arxiv_id":"1906.01083","repositories_listed":5,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/melnet-a-generative-model-for-audio-in-the#ran","syntology_url":"https://syntology.ai/paper/1906.01083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.01083"}},"official":null}},{"url":"/paper/high-fidelity-audio-compression-with-improved","slug":"high-fidelity-audio-compression-with-improved","title":"High-Fidelity Audio Compression with Improved RVQGAN","date":"2023-06-11","arxiv_id":"2306.06546","repositories_listed":4,"syntology":{"n":38,"n_ran":27,"n_constructed":10,"n_ran_checked":17,"n_instrument":10,"n_unverified":11,"n_honours":3,"n_violates":3,"n_no_contract":11,"n_pointer_only":0,"phrase":"27 ran (of which 10 constructed an object rather than computing a result; 17 with no instrument failure: 3 honoured, 3 violated, 11 with no contract checked; 10 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/high-fidelity-audio-compression-with-improved#ran","syntology_url":"https://syntology.ai/paper/2306.06546","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.06546"}},"official":{"repos":["descriptinc/descript-audio-codec"],"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/audioldm-text-to-audio-generation-with-latent","slug":"audioldm-text-to-audio-generation-with-latent","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","date":"2023-01-29","arxiv_id":"2301.12503","repositories_listed":4,"syntology":{"n":21,"n_ran":16,"n_constructed":1,"n_ran_checked":11,"n_instrument":5,"n_unverified":5,"n_honours":1,"n_violates":1,"n_no_contract":9,"n_pointer_only":12,"phrase":"16 ran (of which 1 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/audioldm-text-to-audio-generation-with-latent#ran","syntology_url":"https://syntology.ai/paper/2301.12503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12503"}},"official":{"repos":["haoheliu/AudioLDM"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["named_in_paper","official"]}}},{"url":"/paper/audio-super-resolution-using-neural-networks","slug":"audio-super-resolution-using-neural-networks","title":"Audio Super Resolution using Neural Networks","date":"2017-08-02","arxiv_id":"1708.00853","repositories_listed":4,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/audio-super-resolution-using-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1708.00853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.00853"}},"official":null}},{"url":"/paper/samplernn-an-unconditional-end-to-end-neural","slug":"samplernn-an-unconditional-end-to-end-neural","title":"SampleRNN: An Unconditional End-to-End Neural Audio Generation Model","date":"2016-12-22","arxiv_id":"1612.07837","repositories_listed":4,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/samplernn-an-unconditional-end-to-end-neural#ran","syntology_url":"https://syntology.ai/paper/1612.07837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.07837"}},"official":{"repos":["soroushmehr/sampleRNN_ICLR2017"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/soundstorm-efficient-parallel-audio","slug":"soundstorm-efficient-parallel-audio","title":"SoundStorm: Efficient Parallel Audio Generation","date":"2023-05-16","arxiv_id":"2305.09636","repositories_listed":3,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":5,"n_no_contract":5,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 5 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/soundstorm-efficient-parallel-audio#ran","syntology_url":"https://syntology.ai/paper/2305.09636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.09636"}},"official":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/differentiable-time-frequency-scattering-in","slug":"differentiable-time-frequency-scattering-in","title":"Differentiable Time-Frequency Scattering on GPU","date":"2022-04-18","arxiv_id":"2204.08269","repositories_listed":3,"syntology":null},{"url":"/paper/hifi-a-unified-framework-for-neural-vocoding","slug":"hifi-a-unified-framework-for-neural-vocoding","title":"HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement","date":"2022-03-24","arxiv_id":"2203.13086","repositories_listed":3,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hifi-a-unified-framework-for-neural-vocoding#ran","syntology_url":"https://syntology.ai/paper/2203.13086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13086"}},"official":{"repos":["andreevp/wvmos"],"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":["listed","official"]}}},{"url":"/paper/taming-visually-guided-sound-generation","slug":"taming-visually-guided-sound-generation","title":"Taming Visually Guided Sound Generation","date":"2021-10-17","arxiv_id":"2110.08791","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/taming-visually-guided-sound-generation#ran","syntology_url":"https://syntology.ai/paper/2110.08791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08791"}},"official":{"repos":["v-iashin/SpecVQGAN"],"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":["listed","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/190600794","slug":"190600794","title":"Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion","date":"2019-06-03","arxiv_id":"1906.00794","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/190600794#ran","syntology_url":"https://syntology.ai/paper/1906.00794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.00794"}},"official":{"repos":["joansj/blow","liusongxiang/StarGAN-Voice-Conversion"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/assisted-sound-sample-generation-with-musical","slug":"assisted-sound-sample-generation-with-musical","title":"Assisted Sound Sample Generation with Musical Conditioning in Adversarial Auto-Encoders","date":"2019-04-12","arxiv_id":"1904.06215","repositories_listed":3,"syntology":null},{"url":"/paper/latent-swap-joint-diffusion-for-long-form","slug":"latent-swap-joint-diffusion-for-long-form","title":"Latent Swap Joint Diffusion for 2D Long-Form Latent Generation","date":"2025-02-07","arxiv_id":"2502.05130","repositories_listed":2,"syntology":null},{"url":"/paper/audio-deepfake-detection-with-self-supervised-1","slug":"audio-deepfake-detection-with-self-supervised-1","title":"Audio Deepfake Detection with Self-Supervised XLS-R and SLS Classifier","date":"2024-10-28","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/movie-gen-a-cast-of-media-foundation-models","slug":"movie-gen-a-cast-of-media-foundation-models","title":"Movie Gen: A Cast of Media Foundation Models","date":"2024-10-17","arxiv_id":"2410.13720","repositories_listed":2,"syntology":null},{"url":"/paper/espnet-codec-comprehensive-training-and","slug":"espnet-codec-comprehensive-training-and","title":"ESPnet-Codec: Comprehensive Training and Evaluation of Neural Codecs for Audio, Music, and Speech","date":"2024-09-24","arxiv_id":"2409.15897","repositories_listed":2,"syntology":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/fast-timing-conditioned-latent-audio","slug":"fast-timing-conditioned-latent-audio","title":"Fast Timing-Conditioned Latent Audio Diffusion","date":"2024-02-07","arxiv_id":"2402.04825","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"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, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fast-timing-conditioned-latent-audio#ran","syntology_url":"https://syntology.ai/paper/2402.04825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04825"}},"official":{"repos":["stability-ai/stable-audio-metrics","stability-ai/stable-audio-tools"],"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/invisible-watermarking-for-audio-generation","slug":"invisible-watermarking-for-audio-generation","title":"Invisible Watermarking for Audio Generation Diffusion Models","date":"2023-09-22","arxiv_id":"2309.13166","repositories_listed":2,"syntology":null},{"url":"/paper/audioldm-2-learning-holistic-audio-generation","slug":"audioldm-2-learning-holistic-audio-generation","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","date":"2023-08-10","arxiv_id":"2308.05734","repositories_listed":2,"syntology":{"n":27,"n_ran":16,"n_constructed":0,"n_ran_checked":13,"n_instrument":3,"n_unverified":11,"n_honours":4,"n_violates":4,"n_no_contract":5,"n_pointer_only":19,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 4 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/audioldm-2-learning-holistic-audio-generation#ran","syntology_url":"https://syntology.ai/paper/2308.05734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.05734"}},"official":{"repos":["haoheliu/AudioLDM2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/musecoco-generating-symbolic-music-from-text","slug":"musecoco-generating-symbolic-music-from-text","title":"MuseCoco: Generating Symbolic Music from Text","date":"2023-05-31","arxiv_id":"2306.00110","repositories_listed":2,"syntology":null},{"url":"/paper/any-to-any-generation-via-composable","slug":"any-to-any-generation-via-composable","title":"Any-to-Any Generation via Composable Diffusion","date":"2023-05-19","arxiv_id":"2305.11846","repositories_listed":2,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/any-to-any-generation-via-composable#ran","syntology_url":"https://syntology.ai/paper/2305.11846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11846"}},"official":{"repos":["microsoft/i-Code"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-singer-fast-multi-singer-singing-voice-1","slug":"multi-singer-fast-multi-singer-singing-voice-1","title":"Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus","date":"2021-12-20","arxiv_id":"2112.10358","repositories_listed":2,"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/multi-singer-fast-multi-singer-singing-voice-1#ran","syntology_url":"https://syntology.ai/paper/2112.10358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.10358"}},"official":{"repos":["Rongjiehuang/Multi-Singer"],"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/refinegan-universally-generating-waveform","slug":"refinegan-universally-generating-waveform","title":"RefineGAN: Universally Generating Waveform Better than Ground Truth with Highly Accurate Pitch and Intensity Responses","date":"2021-11-01","arxiv_id":"2111.00962","repositories_listed":2,"syntology":null},{"url":"/paper/gacela-a-generative-adversarial-context","slug":"gacela-a-generative-adversarial-context","title":"GACELA -- A generative adversarial context encoder for long audio inpainting","date":"2020-05-11","arxiv_id":"2005.05032","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/gacela-a-generative-adversarial-context#ran","syntology_url":"https://syntology.ai/paper/2005.05032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05032"}},"official":{"repos":["andimarafioti/GACELA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/thinksound-chain-of-thought-reasoning-in","slug":"thinksound-chain-of-thought-reasoning-in","title":"ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing","date":"2025-06-26","arxiv_id":"2506.21448","repositories_listed":1,"syntology":null},{"url":"/paper/bemaganv2-a-tutorial-and-comparative-survey","slug":"bemaganv2-a-tutorial-and-comparative-survey","title":"BemaGANv2: A Tutorial and Comparative Survey of GAN-based Vocoders for Long-Term Audio Generation","date":"2025-06-11","arxiv_id":"2506.09487","repositories_listed":1,"syntology":null},{"url":"/paper/xmad-bench-cross-domain-multilingual-audio","slug":"xmad-bench-cross-domain-multilingual-audio","title":"XMAD-Bench: Cross-Domain Multilingual Audio Deepfake Benchmark","date":"2025-05-31","arxiv_id":"2506.00462","repositories_listed":1,"syntology":null},{"url":"/paper/conditional-diffusion-models-with-classifier","slug":"conditional-diffusion-models-with-classifier","title":"Conditional Diffusion Models with Classifier-Free Gibbs-like Guidance","date":"2025-05-27","arxiv_id":"2505.21101","repositories_listed":1,"syntology":null},{"url":"/paper/fast-text-to-audio-generation-with","slug":"fast-text-to-audio-generation-with","title":"Fast Text-to-Audio Generation with Adversarial Post-Training","date":"2025-05-13","arxiv_id":"2505.08175","repositories_listed":1,"syntology":null},{"url":"/paper/omniaudio-generating-spatial-audio-from-360","slug":"omniaudio-generating-spatial-audio-from-360","title":"OmniAudio: Generating Spatial Audio from 360-Degree Video","date":"2025-04-21","arxiv_id":"2504.14906","repositories_listed":1,"syntology":null},{"url":"/paper/detect-all-type-deepfake-audio-wavelet-prompt","slug":"detect-all-type-deepfake-audio-wavelet-prompt","title":"Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perception","date":"2025-04-09","arxiv_id":"2504.06753","repositories_listed":1,"syntology":null},{"url":"/paper/enhance-generation-quality-of-flow-matching","slug":"enhance-generation-quality-of-flow-matching","title":"Enhance Generation Quality of Flow Matching V2A Model via Multi-Step CoT-Like Guidance and Combined Preference Optimization","date":"2025-03-28","arxiv_id":"2503.22200","repositories_listed":1,"syntology":null},{"url":"/paper/2503-00455","slug":"2503-00455","title":"PodAgent: A Comprehensive Framework for Podcast Generation","date":"2025-03-01","arxiv_id":"2503.00455","repositories_listed":1,"syntology":null},{"url":"/paper/2503-00084","slug":"2503-00084","title":"InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music Generation","date":"2025-02-28","arxiv_id":"2503.00084","repositories_listed":1,"syntology":null},{"url":"/paper/kad-no-more-fad-an-effective-and-efficient","slug":"kad-no-more-fad-an-effective-and-efficient","title":"KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio Generation","date":"2025-02-21","arxiv_id":"2502.15602","repositories_listed":1,"syntology":null},{"url":"/paper/tokensynth-a-token-based-neural-synthesizer","slug":"tokensynth-a-token-based-neural-synthesizer","title":"TokenSynth: A Token-based Neural Synthesizer for Instrument Cloning and Text-to-Instrument","date":"2025-02-13","arxiv_id":"2502.08939","repositories_listed":1,"syntology":null},{"url":"/paper/adiff-explaining-audio-difference-using","slug":"adiff-explaining-audio-difference-using","title":"ADIFF: Explaining audio difference using natural language","date":"2025-02-06","arxiv_id":"2502.04476","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/adiff-explaining-audio-difference-using#ran","syntology_url":"https://syntology.ai/paper/2502.04476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.04476"}},"official":{"repos":["soham97/adiff"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/audiogenx-explainability-on-text-to-audio","slug":"audiogenx-explainability-on-text-to-audio","title":"AudioGenX: Explainability on Text-to-Audio Generative Models","date":"2025-02-01","arxiv_id":"2502.00459","repositories_listed":1,"syntology":null},{"url":"/paper/baichuan-omni-1-5-technical-report","slug":"baichuan-omni-1-5-technical-report","title":"Baichuan-Omni-1.5 Technical Report","date":"2025-01-26","arxiv_id":"2501.15368","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/baichuan-omni-1-5-technical-report#ran","syntology_url":"https://syntology.ai/paper/2501.15368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.15368"}},"official":{"repos":["baichuan-inc/Baichuan-Omni-1.5"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/retrieval-augmented-neural-field-for-hrtf","slug":"retrieval-augmented-neural-field-for-hrtf","title":"Retrieval-Augmented Neural Field for HRTF Upsampling and Personalization","date":"2025-01-22","arxiv_id":"2501.13017","repositories_listed":1,"syntology":null},{"url":"/paper/ringformer-a-neural-vocoder-with-ring","slug":"ringformer-a-neural-vocoder-with-ring","title":"RingFormer: A Neural Vocoder with Ring Attention and Convolution-Augmented Transformer","date":"2025-01-02","arxiv_id":"2501.01182","repositories_listed":1,"syntology":null},{"url":"/paper/tangoflux-super-fast-and-faithful-text-to","slug":"tangoflux-super-fast-and-faithful-text-to","title":"TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization","date":"2024-12-30","arxiv_id":"2412.21037","repositories_listed":1,"syntology":null},{"url":"/paper/etta-elucidating-the-design-space-of-text-to","slug":"etta-elucidating-the-design-space-of-text-to","title":"ETTA: Elucidating the Design Space of Text-to-Audio Models","date":"2024-12-26","arxiv_id":"2412.19351","repositories_listed":1,"syntology":null},{"url":"/paper/ritta-modeling-event-relations-in-text-to","slug":"ritta-modeling-event-relations-in-text-to","title":"RiTTA: Modeling Event Relations in Text-to-Audio Generation","date":"2024-12-20","arxiv_id":"2412.15922","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/gotta-hear-them-all-sound-source-aware-vision","slug":"gotta-hear-them-all-sound-source-aware-vision","title":"Gotta Hear Them All: Sound Source Aware Vision to Audio Generation","date":"2024-11-23","arxiv_id":"2411.15447","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gotta-hear-them-all-sound-source-aware-vision#ran","syntology_url":"https://syntology.ai/paper/2411.15447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15447"}},"official":{"repos":["wguo86/ssv2a"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tell-what-you-hear-from-what-you-see-video-to","slug":"tell-what-you-hear-from-what-you-see-video-to","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","date":"2024-11-08","arxiv_id":"2411.05679","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tell-what-you-hear-from-what-you-see-video-to#ran","syntology_url":"https://syntology.ai/paper/2411.05679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05679"}},"official":{"repos":["DragonLiu1995/multimodal-llm-for-audio-gen"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/challenge-on-sound-scene-synthesis-evaluating","slug":"challenge-on-sound-scene-synthesis-evaluating","title":"Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio Generation","date":"2024-10-23","arxiv_id":"2410.17589","repositories_listed":1,"syntology":null},{"url":"/paper/snac-multi-scale-neural-audio-codec","slug":"snac-multi-scale-neural-audio-codec","title":"SNAC: Multi-Scale Neural Audio Codec","date":"2024-10-18","arxiv_id":"2410.14411","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/snac-multi-scale-neural-audio-codec#ran","syntology_url":"https://syntology.ai/paper/2410.14411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14411"}},"official":{"repos":["hubertsiuzdak/snac"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/flashaudio-rectified-flows-for-fast-and-high","slug":"flashaudio-rectified-flows-for-fast-and-high","title":"FlashAudio: Rectified Flows for Fast and High-Fidelity Text-to-Audio Generation","date":"2024-10-16","arxiv_id":"2410.12266","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":3,"n_no_contract":1,"n_pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 3 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/flashaudio-rectified-flows-for-fast-and-high#ran","syntology_url":"https://syntology.ai/paper/2410.12266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12266"}},"official":null}},{"url":"/paper/from-vision-to-audio-and-beyond-a-unified","slug":"from-vision-to-audio-and-beyond-a-unified","title":"From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation","date":"2024-09-27","arxiv_id":"2409.19132","repositories_listed":1,"syntology":null},{"url":"/paper/temporally-aligned-audio-for-video-with","slug":"temporally-aligned-audio-for-video-with","title":"Temporally Aligned Audio for Video with Autoregression","date":"2024-09-20","arxiv_id":"2409.13689","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/temporally-aligned-audio-for-video-with#ran","syntology_url":"https://syntology.ai/paper/2409.13689","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13689"}},"official":{"repos":["ilpoviertola/V-AURA"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/tselm-target-speaker-extraction-using","slug":"tselm-target-speaker-extraction-using","title":"TSELM: Target Speaker Extraction using Discrete Tokens and Language Models","date":"2024-09-12","arxiv_id":"2409.07841","repositories_listed":1,"syntology":null},{"url":"/paper/codec-does-matter-exploring-the-semantic","slug":"codec-does-matter-exploring-the-semantic","title":"Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model","date":"2024-08-30","arxiv_id":"2408.17175","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/codec-does-matter-exploring-the-semantic#ran","syntology_url":"https://syntology.ai/paper/2408.17175","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.17175"}},"official":{"repos":["zhenye234/xcodec"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/efficient-autoregressive-audio-modeling-via","slug":"efficient-autoregressive-audio-modeling-via","title":"Efficient Autoregressive Audio Modeling via Next-Scale Prediction","date":"2024-08-16","arxiv_id":"2408.09027","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"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: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-autoregressive-audio-modeling-via#ran","syntology_url":"https://syntology.ai/paper/2408.09027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.09027"}},"official":{"repos":["qiuk2/aar"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-01180","slug":"2408-01180","title":"Nested Music Transformer: Sequentially Decoding Compound Tokens in Symbolic Music and Audio Generation","date":"2024-08-02","arxiv_id":"2408.01180","repositories_listed":1,"syntology":null},{"url":"/paper/mmtrail-a-multimodal-trailer-video-dataset","slug":"mmtrail-a-multimodal-trailer-video-dataset","title":"MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions","date":"2024-07-30","arxiv_id":"2407.20962","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":1,"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/mmtrail-a-multimodal-trailer-video-dataset#ran","syntology_url":"https://syntology.ai/paper/2407.20962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.20962"}},"official":{"repos":["litwellchi/mmtrail"],"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/stable-audio-open","slug":"stable-audio-open","title":"Stable Audio Open","date":"2024-07-19","arxiv_id":"2407.14358","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":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/stable-audio-open#ran","syntology_url":"https://syntology.ai/paper/2407.14358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14358"}},"official":{"repos":["stability-ai/stable-audio-tools"],"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/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/read-watch-and-scream-sound-generation-from","slug":"read-watch-and-scream-sound-generation-from","title":"Read, Watch and Scream! Sound Generation from Text and Video","date":"2024-07-08","arxiv_id":"2407.05551","repositories_listed":1,"syntology":{"n":22,"n_ran":18,"n_constructed":0,"n_ran_checked":3,"n_instrument":15,"n_unverified":4,"n_honours":0,"n_violates":2,"n_no_contract":1,"n_pointer_only":22,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 15 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/read-watch-and-scream-sound-generation-from#ran","syntology_url":"https://syntology.ai/paper/2407.05551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05551"}},"official":{"repos":["naver-ai/rewas"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/foleycrafter-bring-silent-videos-to-life-with","slug":"foleycrafter-bring-silent-videos-to-life-with","title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","date":"2024-07-01","arxiv_id":"2407.01494","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/foleycrafter-bring-silent-videos-to-life-with#ran","syntology_url":"https://syntology.ai/paper/2407.01494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01494"}},"official":{"repos":["open-mmlab/foleycrafter"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"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/2406-15487","slug":"2406-15487","title":"Improving Text-To-Audio Models with Synthetic Captions","date":"2024-06-18","arxiv_id":"2406.15487","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/2406-15487#ran","syntology_url":"https://syntology.ai/paper/2406.15487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15487"}},"official":null}},{"url":"/paper/can-synthetic-audio-from-generative","slug":"can-synthetic-audio-from-generative","title":"Can Synthetic Audio From Generative Foundation Models Assist Audio Recognition and Speech Modeling?","date":"2024-06-13","arxiv_id":"2406.08800","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/can-synthetic-audio-from-generative#ran","syntology_url":"https://syntology.ai/paper/2406.08800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08800"}},"official":{"repos":["usc-sail/synthaudio"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/lafma-a-latent-flow-matching-model-for-text","slug":"lafma-a-latent-flow-matching-model-for-text","title":"LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation","date":"2024-06-12","arxiv_id":"2406.08203","repositories_listed":1,"syntology":null},{"url":"/paper/see-2-sound-zero-shot-spatial-environment-to","slug":"see-2-sound-zero-shot-spatial-environment-to","title":"SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound","date":"2024-06-06","arxiv_id":"2406.06612","repositories_listed":1,"syntology":null},{"url":"/paper/stochastic-diffusion-a-diffusion","slug":"stochastic-diffusion-a-diffusion","title":"Stochastic Diffusion: A Diffusion Probabilistic Model for Stochastic Time Series Forecasting","date":"2024-06-05","arxiv_id":"2406.02827","repositories_listed":1,"syntology":null},{"url":"/paper/generative-pre-trained-speech-language-model","slug":"generative-pre-trained-speech-language-model","title":"Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer","date":"2024-06-03","arxiv_id":"2406.00976","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"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) · 1 unverified","sample_list":"/paper/generative-pre-trained-speech-language-model#ran","syntology_url":"https://syntology.ai/paper/2406.00976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00976"}},"official":{"repos":["youngsheen/gpst"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/frieren-efficient-video-to-audio-generation","slug":"frieren-efficient-video-to-audio-generation","title":"Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching","date":"2024-06-01","arxiv_id":"2406.00320","repositories_listed":1,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":7,"n_instrument":8,"n_unverified":2,"n_honours":1,"n_violates":4,"n_no_contract":2,"n_pointer_only":6,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 4 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/frieren-efficient-video-to-audio-generation#ran","syntology_url":"https://syntology.ai/paper/2406.00320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00320"}},"official":{"repos":["cyanbx/Frieren-V2A"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/soundctm-uniting-score-based-and-consistency","slug":"soundctm-uniting-score-based-and-consistency","title":"SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation","date":"2024-05-28","arxiv_id":"2405.18503","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/soundctm-uniting-score-based-and-consistency#ran","syntology_url":"https://syntology.ai/paper/2405.18503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18503"}},"official":{"repos":["sony/soundctm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/the-codecfake-dataset-and-countermeasures-for","slug":"the-codecfake-dataset-and-countermeasures-for","title":"The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio","date":"2024-05-08","arxiv_id":"2405.04880","repositories_listed":1,"syntology":null},{"url":"/paper/lvns-rave-diversified-audio-generation-with","slug":"lvns-rave-diversified-audio-generation-with","title":"LVNS-RAVE: Diversified audio generation with RAVE and Latent Vector Novelty Search","date":"2024-04-22","arxiv_id":"2404.14063","repositories_listed":1,"syntology":null},{"url":"/paper/long-form-music-generation-with-latent","slug":"long-form-music-generation-with-latent","title":"Long-form music generation with latent diffusion","date":"2024-04-16","arxiv_id":"2404.10301","repositories_listed":1,"syntology":null},{"url":"/paper/tango-2-aligning-diffusion-based-text-to","slug":"tango-2-aligning-diffusion-based-text-to","title":"Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization","date":"2024-04-15","arxiv_id":"2404.09956","repositories_listed":1,"syntology":null},{"url":"/paper/rfwave-multi-band-rectified-flow-for-audio","slug":"rfwave-multi-band-rectified-flow-for-audio","title":"RFWave: Multi-band Rectified Flow for Audio Waveform Reconstruction","date":"2024-03-08","arxiv_id":"2403.05010","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/rfwave-multi-band-rectified-flow-for-audio#ran","syntology_url":"https://syntology.ai/paper/2403.05010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05010"}},"official":{"repos":["bfs18/rfwave"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/llmbind-a-unified-modality-task-integration","slug":"llmbind-a-unified-modality-task-integration","title":"LLMBind: A Unified Modality-Task Integration Framework","date":"2024-02-22","arxiv_id":"2402.14891","repositories_listed":1,"syntology":null},{"url":"/paper/language-codec-reducing-the-gaps-between","slug":"language-codec-reducing-the-gaps-between","title":"Language-Codec: Bridging Discrete Codec Representations and Speech Language Models","date":"2024-02-19","arxiv_id":"2402.12208","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/language-codec-reducing-the-gaps-between#ran","syntology_url":"https://syntology.ai/paper/2402.12208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12208"}},"official":{"repos":["jishengpeng/languagecodec"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/arrange-inpaint-and-refine-steerable-long","slug":"arrange-inpaint-and-refine-steerable-long","title":"Arrange, Inpaint, and Refine: Steerable Long-term Music Audio Generation and Editing via Content-based Controls","date":"2024-02-14","arxiv_id":"2402.09508","repositories_listed":1,"syntology":null},{"url":"/paper/eva-gan-enhanced-various-audio-generation-via","slug":"eva-gan-enhanced-various-audio-generation-via","title":"EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks","date":"2024-01-31","arxiv_id":"2402.00892","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/auffusion-leveraging-the-power-of-diffusion","slug":"auffusion-leveraging-the-power-of-diffusion","title":"Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation","date":"2024-01-02","arxiv_id":"2401.01044","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":2,"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/auffusion-leveraging-the-power-of-diffusion#ran","syntology_url":"https://syntology.ai/paper/2401.01044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01044"}},"official":{"repos":["happylittlecat2333/Auffusion"],"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","unlocated"]}}},{"url":"/paper/speech-collage-code-switched-audio-generation","slug":"speech-collage-code-switched-audio-generation","title":"Speech collage: code-switched audio generation by collaging monolingual corpora","date":"2023-09-27","arxiv_id":"2309.15674","repositories_listed":1,"syntology":null},{"url":"/paper/accelerating-diffusion-based-text-to-audio","slug":"accelerating-diffusion-based-text-to-audio","title":"ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation","date":"2023-09-19","arxiv_id":"2309.10740","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":1,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/accelerating-diffusion-based-text-to-audio#ran","syntology_url":"https://syntology.ai/paper/2309.10740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.10740"}},"official":{"repos":["Bai-YT/ConsistencyTTA"],"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/wavmark-watermarking-for-audio-generation","slug":"wavmark-watermarking-for-audio-generation","title":"WavMark: Watermarking for Audio Generation","date":"2023-08-24","arxiv_id":"2308.12770","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/wavmark-watermarking-for-audio-generation#ran","syntology_url":"https://syntology.ai/paper/2308.12770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12770"}},"official":null}},{"url":"/paper/an-initial-exploration-learning-to-generate","slug":"an-initial-exploration-learning-to-generate","title":"An Initial Exploration: Learning to Generate Realistic Audio for Silent Video","date":"2023-08-23","arxiv_id":"2308.12408","repositories_listed":1,"syntology":null},{"url":"/paper/v2a-mapper-a-lightweight-solution-for-vision","slug":"v2a-mapper-a-lightweight-solution-for-vision","title":"V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models","date":"2023-08-18","arxiv_id":"2308.09300","repositories_listed":1,"syntology":null},{"url":"/paper/musicldm-enhancing-novelty-in-text-to-music","slug":"musicldm-enhancing-novelty-in-text-to-music","title":"MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies","date":"2023-08-03","arxiv_id":"2308.01546","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":4,"n_honours":2,"n_violates":3,"n_no_contract":1,"n_pointer_only":14,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 3 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/musicldm-enhancing-novelty-in-text-to-music#ran","syntology_url":"https://syntology.ai/paper/2308.01546","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.01546"}},"official":{"repos":["retrocirce/musicldm"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/wavjourney-compositional-audio-creation-with","slug":"wavjourney-compositional-audio-creation-with","title":"WavJourney: Compositional Audio Creation with Large Language Models","date":"2023-07-26","arxiv_id":"2307.14335","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/wavjourney-compositional-audio-creation-with#ran","syntology_url":"https://syntology.ai/paper/2307.14335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.14335"}},"official":{"repos":["audio-agi/wavjourney"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/make-an-audio-2-temporal-enhanced-text-to","slug":"make-an-audio-2-temporal-enhanced-text-to","title":"Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation","date":"2023-05-29","arxiv_id":"2305.18474","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":5,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/make-an-audio-2-temporal-enhanced-text-to#ran","syntology_url":"https://syntology.ai/paper/2305.18474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18474"}},"official":null}},{"url":"/paper/an-efficient-membership-inference-attack-for","slug":"an-efficient-membership-inference-attack-for","title":"An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization","date":"2023-05-26","arxiv_id":"2305.18355","repositories_listed":1,"syntology":null},{"url":"/paper/loopy-a-research-friendly-mix-framework-for","slug":"loopy-a-research-friendly-mix-framework-for","title":"LooPy: A Research-Friendly Mix Framework for Music Information Retrieval on Electronic Dance Music","date":"2023-05-01","arxiv_id":"2305.01051","repositories_listed":1,"syntology":null},{"url":"/paper/text-to-audio-generation-using-instruction","slug":"text-to-audio-generation-using-instruction","title":"Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model","date":"2023-04-24","arxiv_id":"2304.13731","repositories_listed":1,"syntology":null}],"syntology_records":48,"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":5,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/audio-generation-on-audiocaps","since_archive":"/sota/audio-generation-on-audiocaps#since-judged","papers_judged":5,"placed":0}]},"papers_where_code_ran":57,"papers_where_code_ran_first_page":"/task/audio-generation/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":3,"url":"/task/audio-generation/papers/2","json":"/task/audio-generation/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/audio-generation/papers/3","json":"/task/audio-generation/papers/3.json","rows":70},{"order":"ran","page":1,"of":1,"url":"/task/audio-generation/papers/ran/1","json":"/task/audio-generation/papers/ran/1.json","rows":57}],"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":"848a482d33b702e4ada828301cb4dbdef604f490854a22ced2a628b82b67a92c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}