{"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-tagging","name":"Audio Tagging","slug":"audio-tagging","description_markdown":"Audio tagging is a task to predict the tags of audio clips. Audio tagging tasks include music tagging, acoustic scene classification, audio event classification, etc.","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":81,"papers_with_code":49,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":10,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/audio-tagging-on-audioset","slug":"audio-tagging-on-audioset","dataset":"AudioSet","dataset_url":"/dataset/audioset","rows_in_archive":11,"metrics":["mean average precision"],"first_row_in_archive_order":{"model":"CAV-MAE (Audio-Visual)","paper_title":"Contrastive Audio-Visual Masked Autoencoder","paper_url":"/paper/contrastive-audio-visual-masked-autoencoder","paper_date":"2022-10-02","arxiv_id":"2210.07839","code_links":[{"title":"yuangongnd/cav-mae","url":"https://github.com/yuangongnd/cav-mae"}],"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/contrastive-audio-visual-masked-autoencoder#ran","syntology_url":"https://syntology.ai/paper/2210.07839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07839"}},"official":{"repos":["yuangongnd/cav-mae"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}}}],"datasets":[{"url":"/dataset/audioset","name":"AudioSet","full_name":"","num_papers_in_archive":744},{"url":"/dataset/vocalsound","name":"VocalSound","full_name":"","num_papers_in_archive":24},{"url":"/dataset/fsdkaggle2018","name":"FSDKaggle2018","full_name":"FSDKaggle2018","num_papers_in_archive":12},{"url":"/dataset/ssc","name":"SSC","full_name":"Spiking Speech Commands v0.2","num_papers_in_archive":7},{"url":"/dataset/chime-home","name":"CHiME-Home","full_name":"CHiME-Home","num_papers_in_archive":5},{"url":"/dataset/fsdkaggle2019","name":"FSDKaggle2019","full_name":"FSDKaggle2019","num_papers_in_archive":5},{"url":"/dataset/sonyc-ust-v2","name":"SONYC-UST-V2","full_name":"","num_papers_in_archive":4},{"url":"/dataset/singa-pura","name":"SINGA:PURA","full_name":"SINGApore: Polyphonic URban Audio","num_papers_in_archive":2},{"url":"/dataset/meerkat-meerkat-kalahari-audio-transcripts","name":"MeerKAT: Meerkat Kalahari Audio Transcripts","full_name":"","num_papers_in_archive":1},{"url":"/dataset/sound-of-water-50","name":"Sound of Water 50","full_name":"Sound of Water 50","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":81,"of":81,"of_with_code":49,"tagged_in_all":81,"counts":{"archive_papers_tagged":81,"with_a_code_link":49,"where_syntology_ran_a_sample":10,"not_listed_spam_title":0,"listed":81,"listed_where_code_ran":10,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":8,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/ast-audio-spectrogram-transformer","slug":"ast-audio-spectrogram-transformer","title":"AST: Audio Spectrogram Transformer","date":"2021-04-05","arxiv_id":"2104.01778","repositories_listed":5,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ast-audio-spectrogram-transformer#ran","syntology_url":"https://syntology.ai/paper/2104.01778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.01778"}},"official":{"repos":["YuanGongND/ast"],"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/speech-denoising-with-deep-feature-losses","slug":"speech-denoising-with-deep-feature-losses","title":"Speech Denoising with Deep Feature Losses","date":"2018-06-27","arxiv_id":"1806.10522","repositories_listed":5,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/speech-denoising-with-deep-feature-losses#ran","syntology_url":"https://syntology.ai/paper/1806.10522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.10522"}},"official":null}},{"url":"/paper/musicnn-pre-trained-convolutional-neural","slug":"musicnn-pre-trained-convolutional-neural","title":"musicnn: Pre-trained convolutional neural networks for music audio tagging","date":"2019-09-14","arxiv_id":"1909.06654","repositories_listed":4,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/musicnn-pre-trained-convolutional-neural#ran","syntology_url":"https://syntology.ai/paper/1909.06654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.06654"}},"official":{"repos":["jordipons/musicnn","jordipons/sklearn-audio-transfer-learning"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["named_in_paper","official"]}}},{"url":"/paper/general-purpose-tagging-of-freesound-audio","slug":"general-purpose-tagging-of-freesound-audio","title":"General-purpose Tagging of Freesound Audio with AudioSet Labels: Task Description, Dataset, and Baseline","date":"2018-07-26","arxiv_id":"1807.09902","repositories_listed":3,"syntology":null},{"url":"/paper/m2d2-exploring-general-purpose-audio-language","slug":"m2d2-exploring-general-purpose-audio-language","title":"M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP","date":"2025-03-28","arxiv_id":"2503.22104","repositories_listed":2,"syntology":null},{"url":"/paper/audio-classification-with-dilated-convolution","slug":"audio-classification-with-dilated-convolution","title":"Audio classification with Dilated Convolution with Learnable Spacings","date":"2023-09-25","arxiv_id":"2309.13972","repositories_listed":2,"syntology":null},{"url":"/paper/self-supervised-audio-teacher-student","slug":"self-supervised-audio-teacher-student","title":"Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks","date":"2023-06-07","arxiv_id":"2306.04186","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-large-scale-audio-tagging-via","slug":"efficient-large-scale-audio-tagging-via","title":"Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation","date":"2022-11-09","arxiv_id":"2211.04772","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/efficient-large-scale-audio-tagging-via#ran","syntology_url":"https://syntology.ai/paper/2211.04772","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.04772"}},"official":{"repos":["fschmid56/efficientat"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/efficient-training-of-audio-transformers-with","slug":"efficient-training-of-audio-transformers-with","title":"Efficient Training of Audio Transformers with Patchout","date":"2021-10-11","arxiv_id":"2110.05069","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-training-of-audio-transformers-with#ran","syntology_url":"https://syntology.ai/paper/2110.05069","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.05069"}},"official":{"repos":["kkoutini/passt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/crnns-for-urban-sound-tagging-with","slug":"crnns-for-urban-sound-tagging-with","title":"CRNNs for Urban Sound Tagging with spatiotemporal context","date":"2020-08-24","arxiv_id":"2008.10413","repositories_listed":2,"syntology":null},{"url":"/paper/audio-tagging-with-noisy-labels-and-minimal","slug":"audio-tagging-with-noisy-labels-and-minimal","title":"Audio tagging with noisy labels and minimal supervision","date":"2019-06-07","arxiv_id":"1906.02975","repositories_listed":2,"syntology":null},{"url":"/paper/general-audio-tagging-with-ensembling","slug":"general-audio-tagging-with-ensembling","title":"General audio tagging with ensembling convolutional neural network and statistical features","date":"2018-10-30","arxiv_id":"1810.12832","repositories_listed":2,"syntology":null},{"url":"/paper/speech-denoising-convolutional-neural-network","slug":"speech-denoising-convolutional-neural-network","title":"Speech Denoising Convolutional Neural Network trained with Deep Feature Losses.","date":"2018-06-27","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/convolutional-gated-recurrent-neural-network","slug":"convolutional-gated-recurrent-neural-network","title":"Convolutional Gated Recurrent Neural Network Incorporating Spatial Features for Audio Tagging","date":"2017-02-24","arxiv_id":"1702.07787","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-feature-learning-based-on-deep","slug":"unsupervised-feature-learning-based-on-deep","title":"Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging","date":"2016-07-13","arxiv_id":"1607.03681","repositories_listed":2,"syntology":null},{"url":"/paper/baseline-systems-and-evaluation-metrics-for","slug":"baseline-systems-and-evaluation-metrics-for","title":"Baseline Systems and Evaluation Metrics for Spatial Semantic Segmentation of Sound Scenes","date":"2025-03-28","arxiv_id":"2503.22088","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-label-propagation-a-model-size","slug":"hierarchical-label-propagation-a-model-size","title":"Hierarchical Label Propagation: A Model-Size-Dependent Performance Booster for AudioSet Tagging","date":"2025-03-26","arxiv_id":"2503.21826","repositories_listed":1,"syntology":null},{"url":"/paper/solla-towards-a-speech-oriented-llm-that","slug":"solla-towards-a-speech-oriented-llm-that","title":"Solla: Towards a Speech-Oriented LLM That Hears Acoustic Context","date":"2025-03-19","arxiv_id":"2503.15338","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-performance-complexity-trade-offs","slug":"exploring-performance-complexity-trade-offs","title":"Exploring Performance-Complexity Trade-Offs in Sound Event Detection Models","date":"2025-03-14","arxiv_id":"2503.11373","repositories_listed":1,"syntology":null},{"url":"/paper/masked-latent-prediction-and-classification","slug":"masked-latent-prediction-and-classification","title":"Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning","date":"2025-02-17","arxiv_id":"2502.12031","repositories_listed":1,"syntology":null},{"url":"/paper/lc-protonets-multi-label-few-shot-learning","slug":"lc-protonets-multi-label-few-shot-learning","title":"LC-Protonets: Multi-Label Few-Shot Learning for World Music Audio Tagging","date":"2024-09-17","arxiv_id":"2409.11264","repositories_listed":1,"syntology":null},{"url":"/paper/integrating-ip-broadcasting-with-audio-tags","slug":"integrating-ip-broadcasting-with-audio-tags","title":"Integrating IP Broadcasting with Audio Tags: Workflow and Challenges","date":"2024-07-22","arxiv_id":"2407.15423","repositories_listed":1,"syntology":null},{"url":"/paper/dass-distilled-audio-state-space-models-are","slug":"dass-distilled-audio-state-space-models-are","title":"DASS: Distilled Audio State Space Models Are Stronger and More Duration-Scalable Learners","date":"2024-07-04","arxiv_id":"2407.04082","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/dass-distilled-audio-state-space-models-are#ran","syntology_url":"https://syntology.ai/paper/2407.04082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04082"}},"official":{"repos":["Saurabhbhati/DASS"],"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/perceptual-musical-features-for-interpretable","slug":"perceptual-musical-features-for-interpretable","title":"Perceptual Musical Features for Interpretable Audio Tagging","date":"2023-12-18","arxiv_id":"2312.11234","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-convolutional-neural-networks-as","slug":"dynamic-convolutional-neural-networks-as","title":"Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models","date":"2023-10-24","arxiv_id":"2310.15648","repositories_listed":1,"syntology":null},{"url":"/paper/audio-tagging-on-an-embedded-hardware","slug":"audio-tagging-on-an-embedded-hardware","title":"Audio Tagging on an Embedded Hardware Platform","date":"2023-06-15","arxiv_id":"2306.09106","repositories_listed":1,"syntology":null},{"url":"/paper/e-panns-sound-recognition-using-efficient-pre","slug":"e-panns-sound-recognition-using-efficient-pre","title":"E-PANNs: Sound Recognition Using Efficient Pre-trained Audio Neural Networks","date":"2023-05-30","arxiv_id":"2305.18665","repositories_listed":1,"syntology":null},{"url":"/paper/robust-cross-modal-knowledge-distillation-for","slug":"robust-cross-modal-knowledge-distillation-for","title":"Robust Cross-Modal Knowledge Distillation for Unconstrained Videos","date":"2023-04-16","arxiv_id":"2304.07775","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-cross-modal-knowledge-distillation-for#ran","syntology_url":"https://syntology.ai/paper/2304.07775","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.07775"}},"official":{"repos":["gewu-lab/cross-modal-distillation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/zorro-the-masked-multimodal-transformer","slug":"zorro-the-masked-multimodal-transformer","title":"Zorro: the masked multimodal transformer","date":"2023-01-23","arxiv_id":"2301.09595","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/zorro-the-masked-multimodal-transformer#ran","syntology_url":"https://syntology.ai/paper/2301.09595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.09595"}},"official":null}},{"url":"/paper/ontology-aware-learning-and-evaluation-for","slug":"ontology-aware-learning-and-evaluation-for","title":"Ontology-aware Learning and Evaluation for Audio Tagging","date":"2022-11-22","arxiv_id":"2211.12195","repositories_listed":1,"syntology":null},{"url":"/paper/masked-modeling-duo-learning-representations","slug":"masked-modeling-duo-learning-representations","title":"Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input","date":"2022-10-26","arxiv_id":"2210.14648","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":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/masked-modeling-duo-learning-representations#ran","syntology_url":"https://syntology.ai/paper/2210.14648","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.14648"}},"official":{"repos":["nttcslab/m2d"],"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/contrastive-audio-visual-masked-autoencoder","slug":"contrastive-audio-visual-masked-autoencoder","title":"Contrastive Audio-Visual Masked Autoencoder","date":"2022-10-02","arxiv_id":"2210.07839","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/contrastive-audio-visual-masked-autoencoder#ran","syntology_url":"https://syntology.ai/paper/2210.07839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07839"}},"official":{"repos":["yuangongnd/cav-mae"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/connecting-the-dots-between-audio-and-text","slug":"connecting-the-dots-between-audio-and-text","title":"Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer","date":"2021-12-16","arxiv_id":"2112.08995","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-audio-source-separation-through","slug":"zero-shot-audio-source-separation-through","title":"Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data","date":"2021-12-15","arxiv_id":"2112.07891","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":4,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/zero-shot-audio-source-separation-through#ran","syntology_url":"https://syntology.ai/paper/2112.07891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.07891"}},"official":{"repos":["RetroCirce/Zero_Shot_Audio_Source_Separation"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sound-event-detection-transformer-an-event","slug":"sound-event-detection-transformer-an-event","title":"Sound Event Detection Transformer: An Event-based End-to-End Model for Sound Event Detection","date":"2021-10-05","arxiv_id":"2110.02011","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-classification-and-1","slug":"weakly-supervised-classification-and-1","title":"Weakly-Supervised Classification and Detection of Bird Sounds in the Wild.","date":"2021-07-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/the-sjtu-system-for-dcase2021-challenge-task","slug":"the-sjtu-system-for-dcase2021-challenge-task","title":"THE SJTU SYSTEM FOR DCASE2021 CHALLENGE TASK 6: AUDIO CAPTIONING BASED ON ENCODER PRE-TRAINING AND REINFORCEMENT LEARNING","date":"2021-07-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cross-referencing-self-training-network-for","slug":"cross-referencing-self-training-network-for","title":"Cross-Referencing Self-Training Network for Sound Event Detection in Audio Mixtures","date":"2021-05-27","arxiv_id":"2105.13392","repositories_listed":1,"syntology":null},{"url":"/paper/a-modulation-front-end-for-music-audio","slug":"a-modulation-front-end-for-music-audio","title":"A Modulation Front-End for Music Audio Tagging","date":"2021-05-25","arxiv_id":"2105.11836","repositories_listed":1,"syntology":null},{"url":"/paper/distilling-audio-visual-knowledge-by","slug":"distilling-audio-visual-knowledge-by","title":"Distilling Audio-Visual Knowledge by Compositional Contrastive Learning","date":"2021-04-22","arxiv_id":"2104.10955","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/distilling-audio-visual-knowledge-by#ran","syntology_url":"https://syntology.ai/paper/2104.10955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.10955"}},"official":{"repos":["yanbeic/CCL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/fast-threshold-optimization-for-multi-label","slug":"fast-threshold-optimization-for-multi-label","title":"Fast threshold optimization for multi-label audio tagging using Surrogate gradient learning","date":"2021-03-01","arxiv_id":"2103.00833","repositories_listed":1,"syntology":null},{"url":"/paper/improving-deep-learning-based-semi-supervised","slug":"improving-deep-learning-based-semi-supervised","title":"Comparison of semi-supervised deep learning algorithms for audio classification","date":"2021-02-16","arxiv_id":"2102.08183","repositories_listed":1,"syntology":null},{"url":"/paper/psla-improving-audio-event-classification","slug":"psla-improving-audio-event-classification","title":"PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation","date":"2021-02-02","arxiv_id":"2102.01243","repositories_listed":1,"syntology":null},{"url":"/paper/urban-sound-classification-striving-towards-a","slug":"urban-sound-classification-striving-towards-a","title":"Urban Sound Classification : striving towards a fair comparison","date":"2020-10-22","arxiv_id":"2010.11805","repositories_listed":1,"syntology":null},{"url":"/paper/dcasenet-a-joint-pre-trained-deep-neural","slug":"dcasenet-a-joint-pre-trained-deep-neural","title":"DCASENET: A joint pre-trained deep neural network for detecting and classifying acoustic scenes and events","date":"2020-09-21","arxiv_id":"2009.09642","repositories_listed":1,"syntology":null},{"url":"/paper/evaluation-of-post-processing-algorithms-for","slug":"evaluation-of-post-processing-algorithms-for","title":"Evaluation of post-processing algorithms for polyphonic sound event detection","date":"2019-06-17","arxiv_id":"1906.06909","repositories_listed":1,"syntology":null},{"url":"/paper/what-you-need-is-a-more-professional-teacher","slug":"what-you-need-is-a-more-professional-teacher","title":"Guided learning for weakly-labeled semi-supervised sound event detection","date":"2019-06-06","arxiv_id":"1906.02517","repositories_listed":1,"syntology":null},{"url":"/paper/audio-tagging-with-connectionist-temporal","slug":"audio-tagging-with-connectionist-temporal","title":"Audio Tagging With Connectionist Temporal Classification Model Using Sequential Labelled Data","date":"2018-08-06","arxiv_id":"1808.01935","repositories_listed":1,"syntology":null},{"url":"/paper/classifying-variable-length-audio-files-with","slug":"classifying-variable-length-audio-files-with","title":"Classifying Variable-Length Audio Files with All-Convolutional Networks and Masked Global Pooling","date":"2016-07-11","arxiv_id":"1607.02857","repositories_listed":1,"syntology":null},{"url":null,"slug":"performance-improvement-of-spatial-semantic","title":"Performance improvement of spatial semantic segmentation with enriched audio features and agent-based error correction for DCASE 2025 Challenge Task 4","date":"2025-06-26","arxiv_id":"2506.21174","repositories_listed":0,"syntology":null},{"url":null,"slug":"usad-universal-speech-and-audio","title":"USAD: Universal Speech and Audio Representation via Distillation","date":"2025-06-23","arxiv_id":"2506.18843","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-speech-emotion-recognition-with","title":"Enhancing Speech Emotion Recognition with Graph-Based Multimodal Fusion and Prosodic Features for the Speech Emotion Recognition in Naturalistic Conditions Challenge at Interspeech 2025","date":"2025-06-02","arxiv_id":"2506.02088","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-real-time","title":"Knowledge Distillation for Real-Time Classification of Early Media in Voice Communications","date":"2024-10-28","arxiv_id":"2410.21478","repositories_listed":0,"syntology":null},{"url":null,"slug":"mt2kd-towards-a-general-purpose-encoder-for","title":"MT2KD: Towards A General-Purpose Encoder for Speech, Speaker, and Audio Events","date":"2024-09-25","arxiv_id":"2409.17010","repositories_listed":0,"syntology":null},{"url":null,"slug":"normalizing-energy-consumption-for-hardware","title":"Normalizing Energy Consumption for Hardware-Independent Evaluation","date":"2024-09-09","arxiv_id":"2409.05602","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-computation-to-consumption-exploring-the","title":"From Computation to Consumption: Exploring the Compute-Energy Link for Training and Testing Neural Networks for SED Systems","date":"2024-09-08","arxiv_id":"2409.05080","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-framework-for-synthetic-audio-conversations","title":"A Framework for Synthetic Audio Conversations Generation using Large Language Models","date":"2024-09-02","arxiv_id":"2409.00946","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-mamba-pretrained-audio-state-space","title":"Audio Mamba: Pretrained Audio State Space Model For Audio Tagging","date":"2024-05-22","arxiv_id":"2405.13636","repositories_listed":0,"syntology":null},{"url":null,"slug":"atgnn-audio-tagging-graph-neural-network","title":"ATGNN: Audio Tagging Graph Neural Network","date":"2023-11-02","arxiv_id":"2311.01526","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-music-and-language-attention-models-for","title":"Joint Music and Language Attention Models for Zero-shot Music Tagging","date":"2023-10-16","arxiv_id":"2310.10159","repositories_listed":0,"syntology":null},{"url":null,"slug":"killing-two-birds-with-one-stone-can-an-audio","title":"Killing two birds with one stone: Can an audio captioning system also be used for audio-text retrieval?","date":"2023-08-29","arxiv_id":"2308.15090","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-audio-cnns-with-graph-centrality","title":"Compressing audio CNNs with graph centrality based filter pruning","date":"2023-05-05","arxiv_id":"2305.03391","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-audio-tagging-assisted-sound-event","title":"Leveraging Audio-Tagging Assisted Sound Event Detection using Weakified Strong Labels and Frequency Dynamic Convolutions","date":"2023-04-25","arxiv_id":"2304.12688","repositories_listed":0,"syntology":null},{"url":null,"slug":"ast-sed-an-effective-sound-event-detection","title":"AST-SED: An Effective Sound Event Detection Method Based on Audio Spectrogram Transformer","date":"2023-03-07","arxiv_id":"2303.03689","repositories_listed":0,"syntology":null},{"url":null,"slug":"incremental-learning-of-acoustic-scenes-and","title":"Incremental Learning of Acoustic Scenes and Sound Events","date":"2023-02-28","arxiv_id":"2302.14815","repositories_listed":0,"syntology":null},{"url":null,"slug":"tackling-the-cocktail-fork-problem-for","title":"Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks","date":"2022-12-14","arxiv_id":"2212.07327","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-learning-based-classification-of-3","title":"Machine Learning-based Classification of Birds through Birdsong","date":"2022-12-09","arxiv_id":"2212.04684","repositories_listed":0,"syntology":null},{"url":null,"slug":"spectnet-end-to-end-audio-signal","title":"SpectNet : End-to-End Audio Signal Classification Using Learnable Spectrograms","date":"2022-11-17","arxiv_id":"2211.09352","repositories_listed":0,"syntology":null},{"url":null,"slug":"impact-of-temporal-resolution-on","title":"Impact of temporal resolution on convolutional recurrent networks for audio tagging and sound event detection","date":"2022-09-26","arxiv_id":"2209.12843","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-encoder-attention-based-architectures","title":"Multi-encoder attention-based architectures for sound recognition with partial visual assistance","date":"2022-09-26","arxiv_id":"2209.12826","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-zero-shot-audio-tagging","title":"Improved Zero-Shot Audio Tagging & Classification with Patchout Spectrogram Transformers","date":"2022-08-24","arxiv_id":"2208.11402","repositories_listed":0,"syntology":null},{"url":null,"slug":"connecting-the-dots-between-audio-and-text-1","title":"Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"audiovisual-transfer-learning-for-audio","title":"Audiovisual transfer learning for audio tagging and sound event detection","date":"2021-06-09","arxiv_id":"2106.05408","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-the-ground-truth-reliability-of-multi","title":"What is the ground truth? Reliability of multi-annotator data for audio tagging","date":"2021-04-09","arxiv_id":"2104.04214","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-weakly-supervised-at-and-aed-using-deep","title":"Joint framework with deep feature distillation and adaptive focal loss for weakly supervised audio tagging and acoustic event detection","date":"2021-03-23","arxiv_id":"2103.12388","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-audio-augmentation-methods-with","title":"Enhancing Audio Augmentation Methods with Consistency Learning","date":"2021-02-09","arxiv_id":"2102.05151","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-tagging-by-cross-filtering-noisy-labels","title":"Audio Tagging by Cross Filtering Noisy Labels","date":"2020-07-16","arxiv_id":"2007.08165","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-scene-classification-using-audio","title":"Acoustic Scene Classification using Audio Tagging","date":"2020-04-19","arxiv_id":"2003.09164","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-branch-learning-for-weakly-labeled","title":"Multi-Branch Learning for Weakly-Labeled Sound Event Detection","date":"2020-02-22","arxiv_id":"2002.09661","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-high-level-features-of-raw-audio","title":"Combining High-Level Features of Raw Audio Waves and Mel-Spectrograms for Audio Tagging","date":"2018-11-26","arxiv_id":"1811.10708","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-dnn-based-multi-label-regression-for","title":"Fully DNN-based Multi-label regression for audio tagging","date":"2016-06-24","arxiv_id":"1606.07695","repositories_listed":0,"syntology":null}],"syntology_records":12,"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":10,"papers_where_code_ran_first_page":"/task/audio-tagging/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-tagging/papers/ran/1","json":"/task/audio-tagging/papers/ran/1.json","rows":10}],"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":"6665c4f5876b7b6a266c4b83533d5adb2ffdd92b4589f3eef716a0229a8b7e15","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}