{"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-super-resolution","name":"Audio Super-Resolution","slug":"audio-super-resolution","description_markdown":"Audio super-resolution, especially speech, refers to the process of reconstructing high-resolution music signals from their low-resolution counterparts. Essentially, it enhances the quality of a speech signal by increasing its sampling rate or bandwidth while preserving naturalness and intelligibility. A representative Github project for speech super-resolution is [ClearerVoice-Studio](https://github.com/modelscope/ClearerVoice-Studio).","categories":[{"name":"Audio","url":"/area/audio"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":22,"papers_with_code":16,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":3,"subtasks":0,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/audio-super-resolution-on-vctk-multi-speaker-1","slug":"audio-super-resolution-on-vctk-multi-speaker-1","dataset":"VCTK Multi-Speaker","dataset_url":"/dataset/vctk","rows_in_archive":7,"metrics":["Log-Spectral Distance"],"first_row_in_archive_order":{"model":"CMGAN","paper_title":"CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement","paper_url":"/paper/cmgan-conformer-based-metric-gan-for-monaural","paper_date":"2022-09-22","arxiv_id":"2209.11112","code_links":[{"title":"ruizhecao96/cmgan","url":"https://github.com/ruizhecao96/cmgan"},{"title":"SherifAbdulatif/CMGAN","url":"https://github.com/SherifAbdulatif/CMGAN"}],"syntology":null}},{"leaderboard":"/sota/audio-super-resolution-on-piano-1","slug":"audio-super-resolution-on-piano-1","dataset":"Piano","dataset_url":null,"rows_in_archive":3,"metrics":["Log-Spectral Distance"],"first_row_in_archive_order":{"model":"U-Net + AFiLM","paper_title":"Self-Attention for Audio Super-Resolution","paper_url":"/paper/self-attention-for-audio-super-resolution","paper_date":"2021-08-26","arxiv_id":"2108.11637","code_links":[{"title":"ncarraz/AFILM","url":"https://github.com/ncarraz/AFILM"}],"syntology":null}},{"leaderboard":"/sota/audio-super-resolution-on-voice-bank-corpus-1","slug":"audio-super-resolution-on-voice-bank-corpus-1","dataset":"Voice Bank corpus (VCTK)","dataset_url":"/dataset/vctk","rows_in_archive":3,"metrics":["Log-Spectral Distance"],"first_row_in_archive_order":{"model":"U-Net + AFiLM","paper_title":"Self-Attention for Audio Super-Resolution","paper_url":"/paper/self-attention-for-audio-super-resolution","paper_date":"2021-08-26","arxiv_id":"2108.11637","code_links":[{"title":"ncarraz/AFILM","url":"https://github.com/ncarraz/AFILM"}],"syntology":null}},{"leaderboard":"/sota/audio-super-resolution-on-dsd100","slug":"audio-super-resolution-on-dsd100","dataset":"DSD100","dataset_url":"/dataset/dsd100","rows_in_archive":1,"metrics":["SNR"],"first_row_in_archive_order":{"model":"U-Net and ResNet","paper_title":"On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks","paper_url":"/paper/on-filter-generalization-for-music-bandwidth","paper_date":"2020-11-14","arxiv_id":"2011.07274","code_links":[{"title":"serkansulun/deep-music-enhancer","url":"https://github.com/serkansulun/deep-music-enhancer"},{"title":"serkansulun/deep-music-enhancement","url":"https://github.com/serkansulun/deep-music-enhancement"}],"syntology":null}}],"datasets":[{"url":"/dataset/vctk","name":"VCTK","full_name":"CSTR VCTK Corpus","num_papers_in_archive":476},{"url":"/dataset/dsd100","name":"DSD100","full_name":"","num_papers_in_archive":2},{"url":"/dataset/medleydb-2-0","name":"MedleyDB 2.0","full_name":null,"num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/10-shot-image-generation","name":"10-shot image generation"},{"url":"/task/audio-generation","name":"Audio Generation"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":22,"of":22,"of_with_code":16,"tagged_in_all":22,"counts":{"archive_papers_tagged":22,"with_a_code_link":16,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":22,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/nu-wave-2-a-general-neural-audio-upsampling","slug":"nu-wave-2-a-general-neural-audio-upsampling","title":"NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates","date":"2022-06-17","arxiv_id":"2206.08545","repositories_listed":5,"syntology":{"n":18,"n_ran":13,"n_constructed":6,"n_ran_checked":11,"n_instrument":2,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"13 ran (of which 6 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/nu-wave-2-a-general-neural-audio-upsampling#ran","syntology_url":"https://syntology.ai/paper/2206.08545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.08545"}},"official":{"repos":["mindslab-ai/nuwave2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":6,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["listed","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/nu-wave-a-diffusion-probabilistic-model-for","slug":"nu-wave-a-diffusion-probabilistic-model-for","title":"NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling","date":"2021-04-06","arxiv_id":"2104.02321","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/nu-wave-a-diffusion-probabilistic-model-for#ran","syntology_url":"https://syntology.ai/paper/2104.02321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.02321"}},"official":{"repos":["mindslab-ai/nuwave"],"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/cmgan-conformer-based-metric-gan-for-monaural","slug":"cmgan-conformer-based-metric-gan-for-monaural","title":"CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement","date":"2022-09-22","arxiv_id":"2209.11112","repositories_listed":2,"syntology":null},{"url":"/paper/on-filter-generalization-for-music-bandwidth","slug":"on-filter-generalization-for-music-bandwidth","title":"On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks","date":"2020-11-14","arxiv_id":"2011.07274","repositories_listed":2,"syntology":null},{"url":"/paper/flowhigh-towards-efficient-and-high-quality","slug":"flowhigh-towards-efficient-and-high-quality","title":"FLowHigh: Towards Efficient and High-Quality Audio Super-Resolution with Single-Step Flow Matching","date":"2025-01-09","arxiv_id":"2501.04926","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":2,"n_honours":2,"n_violates":3,"n_no_contract":5,"n_pointer_only":6,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 3 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/flowhigh-towards-efficient-and-high-quality#ran","syntology_url":"https://syntology.ai/paper/2501.04926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.04926"}},"official":{"repos":["jjunak-yun/FLowHigh_code"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/aeromamba-an-efficient-architecture-for-audio","slug":"aeromamba-an-efficient-architecture-for-audio","title":"AEROMamba: An efficient architecture for audio super-resolution using generative adversarial networks and state space models","date":"2024-11-11","arxiv_id":"2411.07364","repositories_listed":1,"syntology":null},{"url":"/paper/audiosr-versatile-audio-super-resolution-at","slug":"audiosr-versatile-audio-super-resolution-at","title":"AudioSR: Versatile Audio Super-resolution at Scale","date":"2023-09-13","arxiv_id":"2309.07314","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/audiosr-versatile-audio-super-resolution-at#ran","syntology_url":"https://syntology.ai/paper/2309.07314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07314"}},"official":null}},{"url":"/paper/aero-audio-super-resolution-in-the-spectral","slug":"aero-audio-super-resolution-in-the-spectral","title":"AERO: Audio Super Resolution in the Spectral Domain","date":"2022-11-22","arxiv_id":"2211.12232","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/aero-audio-super-resolution-in-the-spectral#ran","syntology_url":"https://syntology.ai/paper/2211.12232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12232"}},"official":{"repos":["slp-rl/aero"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/nonparallel-high-quality-audio-super","slug":"nonparallel-high-quality-audio-super","title":"Nonparallel High-Quality Audio Super Resolution with Domain Adaptation and Resampling CycleGANs","date":"2022-10-28","arxiv_id":"2210.15887","repositories_listed":1,"syntology":null},{"url":"/paper/neural-vocoder-is-all-you-need-for-speech","slug":"neural-vocoder-is-all-you-need-for-speech","title":"Neural Vocoder is All You Need for Speech Super-resolution","date":"2022-03-28","arxiv_id":"2203.14941","repositories_listed":1,"syntology":null},{"url":"/paper/learning-continuous-representation-of-audio","slug":"learning-continuous-representation-of-audio","title":"Learning Continuous Representation of Audio for Arbitrary Scale Super Resolution","date":"2021-10-30","arxiv_id":"2111.00195","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/learning-continuous-representation-of-audio#ran","syntology_url":"https://syntology.ai/paper/2111.00195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.00195"}},"official":{"repos":["ml-postech/lisa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/tunet-a-block-online-bandwidth-extension","slug":"tunet-a-block-online-bandwidth-extension","title":"TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining","date":"2021-10-26","arxiv_id":"2110.13492","repositories_listed":1,"syntology":null},{"url":"/paper/self-attention-for-audio-super-resolution","slug":"self-attention-for-audio-super-resolution","title":"Self-Attention for Audio Super-Resolution","date":"2021-08-26","arxiv_id":"2108.11637","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-film-capturing-long-range-sequence-1","slug":"temporal-film-capturing-long-range-sequence-1","title":"Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations.","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/temporal-film-capturing-long-range-sequence","slug":"temporal-film-capturing-long-range-sequence","title":"Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations","date":"2019-09-14","arxiv_id":"1909.06628","repositories_listed":1,"syntology":null},{"url":null,"slug":"flashsr-one-step-versatile-audio-super","title":"FlashSR: One-step Versatile Audio Super-resolution via Diffusion Distillation","date":"2025-01-18","arxiv_id":"2501.10807","repositories_listed":0,"syntology":null},{"url":null,"slug":"gull-a-generative-multifunctional-audio-codec","title":"Gull: A Generative Multifunctional Audio Codec","date":"2024-04-07","arxiv_id":"2404.04947","repositories_listed":0,"syntology":null},{"url":null,"slug":"edge-storage-management-recipe-with-zero-shot","title":"Edge Storage Management Recipe with Zero-Shot Data Compression for Road Anomaly Detection","date":"2023-07-10","arxiv_id":"2307.04298","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-investigation-of-pre-upsampling-generative","title":"An investigation of pre-upsampling generative modelling and Generative Adversarial Networks in audio super resolution","date":"2021-09-30","arxiv_id":"2109.14994","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-have-an-ear-for-face-super","title":"Learning to Have an Ear for Face Super-Resolution","date":"2019-09-27","arxiv_id":"1909.12780","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-audio-super-resolution-with","title":"Adversarial Audio Super-Resolution with Unsupervised Feature Losses","date":"2018-09-27","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":7,"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":7,"papers_where_code_ran_first_page":"/task/audio-super-resolution/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/audio-super-resolution/papers/ran/1","json":"/task/audio-super-resolution/papers/ran/1.json","rows":7}],"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":"573f3fdc71249e7246cd1e35ef17e16679c57f6b5459437968ef96d981d81279","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}