{"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-classification","name":"Audio Classification","slug":"audio-classification","description_markdown":"**Audio Classification** is a machine learning task that involves identifying and tagging audio signals into different classes or categories. The goal of audio classification is to enable machines to automatically recognize and distinguish between different types of audio, such as music, speech, and environmental sounds.","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":361,"papers_with_code":183,"benchmarks":22,"benchmark_tables_in_archive":25,"benchmark_tables_shown":25,"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":43,"subtasks":4,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/audio-classification-on-audioset","slug":"audio-classification-on-audioset","dataset":"AudioSet","dataset_url":"/dataset/audioset","rows_in_archive":51,"metrics":["Test mAP","AUC","d-prime"],"first_row_in_archive_order":{"model":"OmniVec2","paper_title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","paper_url":"/paper/omnivec2-a-novel-transformer-based-network","paper_date":"2024-01-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/audio-classification-on-esc-50","slug":"audio-classification-on-esc-50","dataset":"ESC-50","dataset_url":"/dataset/esc-50","rows_in_archive":29,"metrics":["Top-1 Accuracy","PRE-TRAINING DATASET","Accuracy (5-fold)"],"first_row_in_archive_order":{"model":"OmniVec2","paper_title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","paper_url":"/paper/omnivec2-a-novel-transformer-based-network","paper_date":"2024-01-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/audio-classification-on-icbhi-respiratory","slug":"audio-classification-on-icbhi-respiratory","dataset":"ICBHI Respiratory Sound Database","dataset_url":"/dataset/icbhi-respiratory-sound-database","rows_in_archive":25,"metrics":["ICBHI Score","Sensitivity","Specificity"],"first_row_in_archive_order":{"model":"ADD","paper_title":"Adaptive Differential Denoising for Respiratory Sounds Classification","paper_url":"/paper/adaptive-differential-denoising-for","paper_date":"2025-06-03","arxiv_id":"2506.02505","code_links":[{"title":"deegy666/add-rsc","url":"https://github.com/deegy666/add-rsc"}],"syntology":null}},{"leaderboard":"/sota/audio-classification-on-vggsound","slug":"audio-classification-on-vggsound","dataset":"VGGSound","dataset_url":"/dataset/vgg-sound","rows_in_archive":23,"metrics":["Top 1 Accuracy","Top 5 Accuracy","Mean AP","AUC","d-prime"],"first_row_in_archive_order":{"model":"Mirasol3B","paper_title":"Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities","paper_url":"/paper/mirasol3b-a-multimodal-autoregressive-model","paper_date":"2023-11-09","arxiv_id":"2311.05698","code_links":[],"syntology":null}},{"leaderboard":"/sota/audio-classification-on-shd","slug":"audio-classification-on-shd","dataset":"SHD","dataset_url":"/dataset/shd","rows_in_archive":11,"metrics":["Percentage correct"],"first_row_in_archive_order":{"model":"Event-SSM","paper_title":"Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Models","paper_url":"/paper/scalable-event-by-event-processing-of","paper_date":"2024-04-29","arxiv_id":"2404.18508","code_links":[{"title":"Efficient-Scalable-Machine-Learning/event-ssm","url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm"}],"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":10,"n_instrument":5,"n_unverified":3,"n_honours":1,"n_violates":2,"n_no_contract":7,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 2 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/scalable-event-by-event-processing-of#ran","syntology_url":"https://syntology.ai/paper/2404.18508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18508"}},"official":{"repos":["Efficient-Scalable-Machine-Learning/event-ssm"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/audio-classification-on-fsd50k","slug":"audio-classification-on-fsd50k","dataset":"FSD50K","dataset_url":"/dataset/fsd50k","rows_in_archive":10,"metrics":["mAP","Mean AP"],"first_row_in_archive_order":{"model":"ONE-PEACE","paper_title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","paper_url":"/paper/one-peace-exploring-one-general","paper_date":"2023-05-18","arxiv_id":"2305.11172","code_links":[{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"OFA-Sys/ONE-PEACE","url":"https://github.com/OFA-Sys/ONE-PEACE"}],"syntology":{"n":7,"n_ran":5,"n_constructed":2,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/one-peace-exploring-one-general#ran","syntology_url":"https://syntology.ai/paper/2305.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11172"}},"official":{"repos":["OFA-Sys/ONE-PEACE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/audio-classification-on-balanced-audio-set","slug":"audio-classification-on-balanced-audio-set","dataset":"Balanced Audio Set","dataset_url":null,"rows_in_archive":8,"metrics":["Mean AP"],"first_row_in_archive_order":{"model":"EquiAV","paper_title":"EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning","paper_url":"/paper/equiav-leveraging-equivariance-for-audio","paper_date":"2024-03-14","arxiv_id":"2403.09502","code_links":[{"title":"jongsuk1/equiav","url":"https://github.com/jongsuk1/equiav"}],"syntology":{"n":13,"n_ran":6,"n_constructed":4,"n_ran_checked":5,"n_instrument":1,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/equiav-leveraging-equivariance-for-audio#ran","syntology_url":"https://syntology.ai/paper/2403.09502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09502"}},"official":{"repos":["jongsuk1/equiav"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/audio-classification-on-speech-commands-1","slug":"audio-classification-on-speech-commands-1","dataset":"Speech Commands","dataset_url":"/dataset/speech-commands","rows_in_archive":7,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"EAT","paper_title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer","paper_url":"/paper/eat-self-supervised-pre-training-with","paper_date":"2024-01-07","arxiv_id":"2401.03497","code_links":[{"title":"cwx-worst-one/eat","url":"https://github.com/cwx-worst-one/eat"}],"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/eat-self-supervised-pre-training-with#ran","syntology_url":"https://syntology.ai/paper/2401.03497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03497"}},"official":{"repos":["cwx-worst-one/eat"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/audio-classification-on-dcase","slug":"audio-classification-on-dcase","dataset":"DCASE","dataset_url":null,"rows_in_archive":5,"metrics":["Top-1 Accuracy","PRE-TRAINING DATASET"],"first_row_in_archive_order":{"model":"CrissCross (AudioSet)","paper_title":"Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity","paper_url":"/paper/self-supervised-audio-visual-representation","paper_date":"2021-11-09","arxiv_id":"2111.05329","code_links":[{"title":"pritamqu/CrissCross","url":"https://github.com/pritamqu/CrissCross"}],"syntology":null}},{"leaderboard":"/sota/audio-classification-on-ssc","slug":"audio-classification-on-ssc","dataset":"SSC","dataset_url":"/dataset/ssc","rows_in_archive":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Event-SSM","paper_title":"Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Models","paper_url":"/paper/scalable-event-by-event-processing-of","paper_date":"2024-04-29","arxiv_id":"2404.18508","code_links":[{"title":"Efficient-Scalable-Machine-Learning/event-ssm","url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm"}],"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":10,"n_instrument":5,"n_unverified":3,"n_honours":1,"n_violates":2,"n_no_contract":7,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 2 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/scalable-event-by-event-processing-of#ran","syntology_url":"https://syntology.ai/paper/2404.18508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18508"}},"official":{"repos":["Efficient-Scalable-Machine-Learning/event-ssm"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/audio-classification-on-birdclef-2021","slug":"audio-classification-on-birdclef-2021","dataset":"BirdCLEF 2021","dataset_url":null,"rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"EfficientLEAF (8s)","paper_title":"EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use","paper_url":"/paper/efficientleaf-a-faster-learnable-audio","paper_date":"2022-07-12","arxiv_id":"2207.05508","code_links":[{"title":"cpjku/efficientleaf","url":"https://github.com/cpjku/efficientleaf"}],"syntology":null}},{"leaderboard":"/sota/audio-classification-on-epic-kitchens-100","slug":"audio-classification-on-epic-kitchens-100","dataset":"EPIC-KITCHENS-100","dataset_url":"/dataset/epic-kitchens-100","rows_in_archive":4,"metrics":["Top-1 Action","Top-1 Noun","Top-1 Verb","Top-5 Action","Top-5 Noun","Top-5 Verb"],"first_row_in_archive_order":{"model":"Audiovisual Masked Autoencoder\n(Audiovisual, Single)","paper_title":"Audiovisual Masked Autoencoders","paper_url":"/paper/audiovisual-masked-autoencoders","paper_date":"2022-12-09","arxiv_id":"2212.05922","code_links":[{"title":"google-research/scenic","url":"https://github.com/google-research/scenic/tree/main/scenic/projects/av_mae"},{"title":"google-research/scenic","url":"https://github.com/google-research/scenic"}],"syntology":null}},{"leaderboard":"/sota/audio-classification-on-audio-set","slug":"audio-classification-on-audio-set","dataset":"Audio Set","dataset_url":null,"rows_in_archive":3,"metrics":["Mean AP"],"first_row_in_archive_order":{"model":"M2D-AS/0.7","paper_title":"Masked Modeling Duo: Towards a Universal Audio Pre-training Framework","paper_url":"/paper/masked-modeling-duo-towards-a-universal-audio","paper_date":"2024-04-09","arxiv_id":"2404.06095","code_links":[{"title":"nttcslab/m2d","url":"https://github.com/nttcslab/m2d"},{"title":"nttcslab/eval-audio-repr","url":"https://github.com/nttcslab/eval-audio-repr"}],"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/masked-modeling-duo-towards-a-universal-audio#ran","syntology_url":"https://syntology.ai/paper/2404.06095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.06095"}},"official":{"repos":["nttcslab/m2d","nttcslab/eval-audio-repr"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/audio-classification-on-crema-d","slug":"audio-classification-on-crema-d","dataset":"CREMA-D","dataset_url":"/dataset/crema-d","rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"EfficientLEAF","paper_title":"EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use","paper_url":"/paper/efficientleaf-a-faster-learnable-audio","paper_date":"2022-07-12","arxiv_id":"2207.05508","code_links":[{"title":"cpjku/efficientleaf","url":"https://github.com/cpjku/efficientleaf"}],"syntology":null}},{"leaderboard":"/sota/audio-classification-on-dicova","slug":"audio-classification-on-dicova","dataset":"DiCOVA","dataset_url":"/dataset/dicova","rows_in_archive":3,"metrics":["AUC"],"first_row_in_archive_order":{"model":"AUCO ResNet","paper_title":"AUCO ResNet: an end-to-end network for Covid-19 pre-screening from cough and breath","paper_url":"/paper/auco-resnet-an-end-to-end-network-for-covid","paper_date":"2022-03-15","arxiv_id":null,"code_links":[{"title":"vincenzodentamaro/aucoresnet","url":"https://github.com/vincenzodentamaro/aucoresnet"}],"syntology":null}},{"leaderboard":"/sota/audio-classification-on-epic-sounds","slug":"audio-classification-on-epic-sounds","dataset":"EPIC-SOUNDS","dataset_url":"/dataset/epic-sounds","rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Mirasol3B","paper_title":"Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities","paper_url":"/paper/mirasol3b-a-multimodal-autoregressive-model","paper_date":"2023-11-09","arxiv_id":"2311.05698","code_links":[],"syntology":null}},{"leaderboard":"/sota/audio-classification-on-ravdess","slug":"audio-classification-on-ravdess","dataset":"RAVDESS","dataset_url":"/dataset/ravdess","rows_in_archive":2,"metrics":["Top-1 Accuracy"],"first_row_in_archive_order":{"model":"ASM-RH-A","paper_title":"Mixer is more than just a model","paper_url":"/paper/mixer-is-more-than-just-a-model","paper_date":"2024-02-28","arxiv_id":"2402.18007","code_links":[],"syntology":null}},{"leaderboard":"/sota/audio-classification-on-vocalsound","slug":"audio-classification-on-vocalsound","dataset":"VocalSound","dataset_url":"/dataset/vocalsound","rows_in_archive":2,"metrics":["Accuracy "],"first_row_in_archive_order":{"model":"VocalSound Baseline","paper_title":"Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition","paper_url":"/paper/vocalsound-a-dataset-for-improving-human","paper_date":"2022-05-06","arxiv_id":"2205.03433","code_links":[{"title":"YuanGongND/vocalsound","url":"https://github.com/YuanGongND/vocalsound"}],"syntology":null}},{"leaderboard":"/sota/audio-classification-on-deep-voice-deepfake","slug":"audio-classification-on-deep-voice-deepfake","dataset":"DEEP-VOICE: DeepFake Voice Recognition","dataset_url":"/dataset/deep-voice-deepfake-voice-recognition","rows_in_archive":1,"metrics":["Accuracy (10-fold)"],"first_row_in_archive_order":{"model":"XGBoost (330)","paper_title":"Real-time Detection of AI-Generated Speech for DeepFake Voice Conversion","paper_url":"/paper/real-time-detection-of-ai-generated-speech","paper_date":"2023-08-24","arxiv_id":"2308.12734","code_links":[],"syntology":null}},{"leaderboard":"/sota/audio-classification-on-meerkat-meerkat","slug":"audio-classification-on-meerkat-meerkat","dataset":"MeerKAT: Meerkat Kalahari Audio Transcripts","dataset_url":"/dataset/meerkat-meerkat-kalahari-audio-transcripts","rows_in_archive":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"animal2vec","paper_title":"animal2vec and MeerKAT: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacoustics","paper_url":"/paper/animal2vec-and-meerkat-a-self-supervised","paper_date":"2024-06-03","arxiv_id":"2406.01253","code_links":[{"title":"livingingroups/animal2vec","url":"https://github.com/livingingroups/animal2vec"}],"syntology":null}},{"leaderboard":"/sota/audio-classification-on-multimodal-pisa","slug":"audio-classification-on-multimodal-pisa","dataset":"Multimodal PISA","dataset_url":"/dataset/multimodal-pisa","rows_in_archive":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"Audio","paper_title":"Piano Skills Assessment","paper_url":"/paper/piano-skills-assessment","paper_date":"2021-01-13","arxiv_id":"2101.04884","code_links":[{"title":"ParitoshParmar/Piano-Skills-Assessment","url":"https://github.com/ParitoshParmar/Piano-Skills-Assessment"}],"syntology":null}},{"leaderboard":"/sota/audio-classification-on-ucr-time-series","slug":"audio-classification-on-ucr-time-series","dataset":"UCR Time Series Classification Archive","dataset_url":"/dataset/ucr-time-series-classification-archive","rows_in_archive":1,"metrics":["FruitFlies","MosquitoSound","RightWhaleCalls"],"first_row_in_archive_order":{"model":"CDIL","paper_title":"Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks","paper_url":"/paper/classification-of-long-sequential-data-using","paper_date":"2022-01-06","arxiv_id":"2201.02143","code_links":[{"title":"leicheng-no/cdil-cnn","url":"https://github.com/leicheng-no/cdil-cnn"}],"syntology":null}},{"leaderboard":null,"slug":"audio-classification-on-audiofolder","dataset":"audiofolder","dataset_url":null,"rows_in_archive":0,"metrics":["Accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"audio-classification-on-common-voice-16-1","dataset":"Common Voice 16.1","dataset_url":"/dataset/common-voice","rows_in_archive":0,"metrics":["Test Accent Accuracy","Test Age Accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"audio-classification-on-gtzan","dataset":"GTZAN","dataset_url":"/dataset/gtzan","rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/audioset","name":"AudioSet","full_name":"","num_papers_in_archive":744},{"url":"/dataset/common-voice","name":"Common Voice","full_name":"Common Voice","num_papers_in_archive":449},{"url":"/dataset/speech-commands","name":"Speech Commands","full_name":"Speech Commands","num_papers_in_archive":392},{"url":"/dataset/esc-50","name":"ESC-50","full_name":"ESC-50","num_papers_in_archive":387},{"url":"/dataset/vgg-sound","name":"VGG-Sound","full_name":"","num_papers_in_archive":211},{"url":"/dataset/epic-kitchens-100","name":"EPIC-KITCHENS-100","full_name":"","num_papers_in_archive":162},{"url":"/dataset/fsd50k","name":"FSD50K","full_name":"Freesound Database 50K","num_papers_in_archive":155},{"url":"/dataset/urbansound8k-1","name":"UrbanSound8K","full_name":"UrbanSound8K","num_papers_in_archive":147},{"url":"/dataset/ucr-time-series-classification-archive","name":"UCR Time Series Classification Archive","full_name":"UCR Time Series Classification Archive","num_papers_in_archive":42},{"url":"/dataset/crema-d","name":"CREMA-D","full_name":"CREMA-D","num_papers_in_archive":28},{"url":"/dataset/ravdess","name":"RAVDESS","full_name":"Ryerson Audio-Visual Database of Emotional Speech and Song","num_papers_in_archive":27},{"url":"/dataset/vocalsound","name":"VocalSound","full_name":"","num_papers_in_archive":24},{"url":"/dataset/icbhi-respiratory-sound-database","name":"ICBHI Respiratory Sound Database","full_name":"The Respiratory Sound database -  ICBHI 2017 Challenge","num_papers_in_archive":21},{"url":"/dataset/dicova","name":"DiCOVA","full_name":"","num_papers_in_archive":20},{"url":"/dataset/fsdnoisy18k","name":"FSDnoisy18k","full_name":"FSDnoisy18k","num_papers_in_archive":19},{"url":"/dataset/shd","name":"SHD","full_name":"Spiking Heidelberg Digits","num_papers_in_archive":19},{"url":"/dataset/gtzan","name":"GTZAN","full_name":"","num_papers_in_archive":15},{"url":"/dataset/epic-sounds","name":"EPIC-SOUNDS","full_name":"","num_papers_in_archive":12},{"url":"/dataset/youtube-100m","name":"YouTube-100M","full_name":"YouTube-100m","num_papers_in_archive":8},{"url":"/dataset/ssc","name":"SSC","full_name":"Spiking Speech Commands v0.2","num_papers_in_archive":7},{"url":"/dataset/agender","name":"aGender","full_name":"aGender","num_papers_in_archive":5},{"url":"/dataset/vggsound-sparse","name":"VGGSound-Sparse","full_name":"","num_papers_in_archive":5},{"url":"/dataset/sonyc-ust-v2","name":"SONYC-UST-V2","full_name":"","num_papers_in_archive":4},{"url":"/dataset/tau-nigens-spatial-sound-events-2021","name":"TAU-NIGENS Spatial Sound Events 2021","full_name":"TAU-NIGENS Spatial Sound Events 2021","num_papers_in_archive":4},{"url":"/dataset/dcase-2014","name":"DCASE 2014","full_name":"DCASE 2014","num_papers_in_archive":3},{"url":"/dataset/hume-vb","name":"HUME-VB","full_name":"The Hume Vocal Bursts Dataset","num_papers_in_archive":3},{"url":"/dataset/infantmarmosetsvox","name":"InfantMarmosetsVox","full_name":"InfantMarmosetsVox","num_papers_in_archive":3},{"url":"/dataset/chest-wall-lung-sound-dataset","name":"Chest wall lung sound dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/nemo-1","name":"nEMO","full_name":"","num_papers_in_archive":2},{"url":"/dataset/singa-pura","name":"SINGA:PURA","full_name":"SINGApore: Polyphonic URban Audio","num_papers_in_archive":2},{"url":"/dataset/bgg-dataset","name":"BGG dataset","full_name":"PUBG Gun Sound Dataset","num_papers_in_archive":1},{"url":"/dataset/deep-voice-deepfake-voice-recognition","name":"DEEP-VOICE: DeepFake Voice Recognition","full_name":"Jordan Bird","num_papers_in_archive":1},{"url":"/dataset/medibeng","name":"MediBeng","full_name":"Synthetic Code-Switched Bengali-English Speech Conversations for Healthcare Applications","num_papers_in_archive":1},{"url":"/dataset/meerkat-meerkat-kalahari-audio-transcripts","name":"MeerKAT: Meerkat Kalahari Audio Transcripts","full_name":"","num_papers_in_archive":1},{"url":"/dataset/multimodal-pisa","name":"Multimodal PISA","full_name":"Multimodal Piano Skills Assessment","num_papers_in_archive":1},{"url":"/dataset/pc-gita","name":"PC-GITA","full_name":"PC-GITA","num_papers_in_archive":1},{"url":"/dataset/reefset","name":"ReefSet","full_name":"","num_papers_in_archive":1},{"url":"/dataset/respiratory-and-drug-actuation-dataset","name":"RESPIRATORY AND DRUG ACTUATION DATASET","full_name":"RESPIRATORY AND DRUG ACTUATION DATASET","num_papers_in_archive":1},{"url":"/dataset/k-drone","name":"Sound-based drone fault classification using multitask learning","full_name":"","num_papers_in_archive":1},{"url":"/dataset/zooniverse","name":"Zooniverse","full_name":"HumBug Zooniverse","num_papers_in_archive":1},{"url":"/dataset/dear","name":"DEAR","full_name":"","num_papers_in_archive":0},{"url":"/dataset/mudestreda","name":"Mudestreda","full_name":"Mudestreda Multimodal Device State Recognition Dataset","num_papers_in_archive":0}],"subtasks":[{"url":"/task/audio-multiple-target-classification","name":"Audio Multiple Target Classification"},{"url":"/task/environmental-sound-classification","name":"Environmental Sound Classification"},{"url":"/task/parkinson-detection-from-speech","name":"Parkinson Detection from Speech"},{"url":"/task/semi-supervised-audio-classification","name":"Semi-supervised Audio Classification"}],"parent_tasks":[{"url":"/task/classification-1","name":"Classification"}],"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":4,"rows_per_page":100,"shown":100,"of":361,"of_with_code":183,"tagged_in_all":361,"counts":{"archive_papers_tagged":361,"with_a_code_link":183,"where_syntology_ran_a_sample":46,"not_listed_spam_title":0,"listed":361,"listed_where_code_ran":46,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":41,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":41,"listed_every_run_a_failure_of_syntologys_instrument":5,"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/cnn-architectures-for-large-scale-audio","slug":"cnn-architectures-for-large-scale-audio","title":"CNN Architectures for Large-Scale Audio Classification","date":"2016-09-29","arxiv_id":"1609.09430","repositories_listed":16,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/cnn-architectures-for-large-scale-audio#ran","syntology_url":"https://syntology.ai/paper/1609.09430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.09430"}},"official":null}},{"url":"/paper/perceiver-general-perception-with-iterative","slug":"perceiver-general-perception-with-iterative","title":"Perceiver: General Perception with Iterative Attention","date":"2021-03-04","arxiv_id":"2103.03206","repositories_listed":12,"syntology":{"n":55,"n_ran":41,"n_constructed":20,"n_ran_checked":30,"n_instrument":11,"n_unverified":14,"n_honours":0,"n_violates":2,"n_no_contract":28,"n_pointer_only":11,"phrase":"41 ran (of which 20 constructed an object rather than computing a result; 30 with no instrument failure: 0 honoured, 2 violated, 28 with no contract checked; 11 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/perceiver-general-perception-with-iterative#ran","syntology_url":"https://syntology.ai/paper/2103.03206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03206"}},"official":{"repos":["deepmind/deepmind-research"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["community","listed","unlocated"]}}},{"url":"/paper/languagebind-extending-video-language","slug":"languagebind-extending-video-language","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","date":"2023-10-03","arxiv_id":"2310.01852","repositories_listed":6,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":4,"n_honours":3,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/languagebind-extending-video-language#ran","syntology_url":"https://syntology.ai/paper/2310.01852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01852"}},"official":{"repos":["pku-yuangroup/languagebind"],"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":["listed","official"]}}},{"url":"/paper/vatt-transformers-for-multimodal-self","slug":"vatt-transformers-for-multimodal-self","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","date":"2021-04-22","arxiv_id":"2104.11178","repositories_listed":5,"syntology":{"n":8,"n_ran":5,"n_constructed":4,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"5 ran (of which 4 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/vatt-transformers-for-multimodal-self#ran","syntology_url":"https://syntology.ai/paper/2104.11178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11178"}},"official":{"repos":["google-research/google-research"],"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/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/multi-level-attention-model-for-weakly","slug":"multi-level-attention-model-for-weakly","title":"Multi-level Attention Model for Weakly Supervised Audio Classification","date":"2018-03-06","arxiv_id":"1803.02353","repositories_listed":5,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-level-attention-model-for-weakly#ran","syntology_url":"https://syntology.ai/paper/1803.02353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.02353"}},"official":null}},{"url":"/paper/beats-audio-pre-training-with-acoustic","slug":"beats-audio-pre-training-with-acoustic","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","date":"2022-12-18","arxiv_id":"2212.09058","repositories_listed":4,"syntology":{"n":18,"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":4,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/beats-audio-pre-training-with-acoustic#ran","syntology_url":"https://syntology.ai/paper/2212.09058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09058"}},"official":{"repos":["microsoft/unilm"],"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/masked-autoencoders-that-listen","slug":"masked-autoencoders-that-listen","title":"Masked Autoencoders that Listen","date":"2022-07-13","arxiv_id":"2207.06405","repositories_listed":4,"syntology":{"n":32,"n_ran":17,"n_constructed":12,"n_ran_checked":16,"n_instrument":1,"n_unverified":15,"n_honours":1,"n_violates":1,"n_no_contract":14,"n_pointer_only":10,"phrase":"17 ran (of which 12 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 15 unverified","sample_list":"/paper/masked-autoencoders-that-listen#ran","syntology_url":"https://syntology.ai/paper/2207.06405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06405"}},"official":{"repos":["facebookresearch/audiomae"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/atst-audio-representation-learning-with","slug":"atst-audio-representation-learning-with","title":"ATST: Audio Representation Learning with Teacher-Student Transformer","date":"2022-04-26","arxiv_id":"2204.12076","repositories_listed":4,"syntology":null},{"url":"/paper/leaf-a-learnable-frontend-for-audio","slug":"leaf-a-learnable-frontend-for-audio","title":"LEAF: A Learnable Frontend for Audio Classification","date":"2021-01-21","arxiv_id":"2101.08596","repositories_listed":4,"syntology":{"n":26,"n_ran":14,"n_constructed":1,"n_ran_checked":7,"n_instrument":7,"n_unverified":12,"n_honours":1,"n_violates":2,"n_no_contract":4,"n_pointer_only":2,"phrase":"14 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/leaf-a-learnable-frontend-for-audio#ran","syntology_url":"https://syntology.ai/paper/2101.08596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.08596"}},"official":{"repos":["google-research/leaf-audio"],"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/slowing-down-the-weight-norm-increase-in","slug":"slowing-down-the-weight-norm-increase-in","title":"AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights","date":"2020-06-15","arxiv_id":"2006.08217","repositories_listed":4,"syntology":{"n":4,"n_ran":4,"n_constructed":1,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/slowing-down-the-weight-norm-increase-in#ran","syntology_url":"https://syntology.ai/paper/2006.08217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.08217"}},"official":{"repos":["clovaai/AdamP"],"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":["named_in_paper"]}}},{"url":"/paper/leveraging-tropical-reef-bird-and-unrelated","slug":"leveraging-tropical-reef-bird-and-unrelated","title":"Leveraging tropical reef, bird and unrelated sounds for superior transfer learning in marine bioacoustics","date":"2024-04-25","arxiv_id":"2404.16436","repositories_listed":3,"syntology":null},{"url":"/paper/ssast-self-supervised-audio-spectrogram","slug":"ssast-self-supervised-audio-spectrogram","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","date":"2021-10-19","arxiv_id":"2110.09784","repositories_listed":3,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/ssast-self-supervised-audio-spectrogram#ran","syntology_url":"https://syntology.ai/paper/2110.09784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.09784"}},"official":{"repos":["YuanGongND/ssast"],"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":["listed","official"]}}},{"url":"/paper/rethinking-cnn-models-for-audio","slug":"rethinking-cnn-models-for-audio","title":"Rethinking CNN Models for Audio Classification","date":"2020-07-22","arxiv_id":"2007.11154","repositories_listed":3,"syntology":null},{"url":"/paper/unified-probabilistic-deep-continual-learning","slug":"unified-probabilistic-deep-continual-learning","title":"Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition","date":"2019-05-28","arxiv_id":"1905.12019","repositories_listed":3,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/unified-probabilistic-deep-continual-learning#ran","syntology_url":"https://syntology.ai/paper/1905.12019","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.12019"}},"official":{"repos":["MrtnMndt/OCDVAE_ContinualLearning","MrtnMndt/OCDVAEContinualLearning"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/interpreting-and-explaining-deep-neural","slug":"interpreting-and-explaining-deep-neural","title":"AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmark","date":"2018-07-09","arxiv_id":"1807.03418","repositories_listed":3,"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":0,"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/interpreting-and-explaining-deep-neural#ran","syntology_url":"https://syntology.ai/paper/1807.03418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.03418"}},"official":{"repos":["soerenab/AudioMNIST"],"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/convolutional-rnn-an-enhanced-model-for","slug":"convolutional-rnn-an-enhanced-model-for","title":"Convolutional RNN: an Enhanced Model for Extracting Features from Sequential Data","date":"2016-02-18","arxiv_id":"1602.05875","repositories_listed":3,"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/convolutional-rnn-an-enhanced-model-for#ran","syntology_url":"https://syntology.ai/paper/1602.05875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.05875"}},"official":{"repos":["cruvadom/Convolutional-RNN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"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/m2d-clap-masked-modeling-duo-meets-clap-for","slug":"m2d-clap-masked-modeling-duo-meets-clap-for","title":"M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation","date":"2024-06-04","arxiv_id":"2406.02032","repositories_listed":2,"syntology":null},{"url":"/paper/masked-modeling-duo-towards-a-universal-audio","slug":"masked-modeling-duo-towards-a-universal-audio","title":"Masked Modeling Duo: Towards a Universal Audio Pre-training Framework","date":"2024-04-09","arxiv_id":"2404.06095","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/masked-modeling-duo-towards-a-universal-audio#ran","syntology_url":"https://syntology.ai/paper/2404.06095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.06095"}},"official":{"repos":["nttcslab/m2d","nttcslab/eval-audio-repr"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/internvideo2-scaling-video-foundation-models","slug":"internvideo2-scaling-video-foundation-models","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","date":"2024-03-22","arxiv_id":"2403.15377","repositories_listed":2,"syntology":null},{"url":"/paper/acoustic-prompt-tuning-empowering-large","slug":"acoustic-prompt-tuning-empowering-large","title":"Acoustic Prompt Tuning: Empowering Large Language Models with Audition Capabilities","date":"2023-11-30","arxiv_id":"2312.00249","repositories_listed":2,"syntology":null},{"url":"/paper/qwen-audio-advancing-universal-audio","slug":"qwen-audio-advancing-universal-audio","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","date":"2023-11-14","arxiv_id":"2311.07919","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/qwen-audio-advancing-universal-audio#ran","syntology_url":"https://syntology.ai/paper/2311.07919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07919"}},"official":{"repos":["qwenlm/qwen-audio"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"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/feature-embeddings-from-large-scale-acoustic","slug":"feature-embeddings-from-large-scale-acoustic","title":"Global birdsong embeddings enable superior transfer learning for bioacoustic classification","date":"2023-07-12","arxiv_id":"2307.06292","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/feature-embeddings-from-large-scale-acoustic#ran","syntology_url":"https://syntology.ai/paper/2307.06292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.06292"}},"official":{"repos":["google-research/chirp","google-research/perch"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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/bytes-are-all-you-need-transformers-operating","slug":"bytes-are-all-you-need-transformers-operating","title":"Bytes Are All You Need: Transformers Operating Directly On File Bytes","date":"2023-05-31","arxiv_id":"2306.00238","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bytes-are-all-you-need-transformers-operating#ran","syntology_url":"https://syntology.ai/paper/2306.00238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00238"}},"official":{"repos":["apple/corenet","apple/ml-cvnets"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/one-peace-exploring-one-general","slug":"one-peace-exploring-one-general","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","date":"2023-05-18","arxiv_id":"2305.11172","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":2,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/one-peace-exploring-one-general#ran","syntology_url":"https://syntology.ai/paper/2305.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11172"}},"official":{"repos":["OFA-Sys/ONE-PEACE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/audiovisual-masked-autoencoders","slug":"audiovisual-masked-autoencoders","title":"Audiovisual Masked Autoencoders","date":"2022-12-09","arxiv_id":"2212.05922","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/mae-ast-masked-autoencoding-audio-spectrogram","slug":"mae-ast-masked-autoencoding-audio-spectrogram","title":"MAE-AST: Masked Autoencoding Audio Spectrogram Transformer","date":"2022-03-30","arxiv_id":"2203.16691","repositories_listed":2,"syntology":null},{"url":"/paper/cmkd-cnn-transformer-based-cross-model","slug":"cmkd-cnn-transformer-based-cross-model","title":"CMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for Audio Classification","date":"2022-03-13","arxiv_id":"2203.06760","repositories_listed":2,"syntology":null},{"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/polynomial-networks-in-deep-classifiers","slug":"polynomial-networks-in-deep-classifiers","title":"Augmenting Deep Classifiers with Polynomial Neural Networks","date":"2021-04-16","arxiv_id":"2104.07916","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"4 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/polynomial-networks-in-deep-classifiers#ran","syntology_url":"https://syntology.ai/paper/2104.07916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07916"}},"official":{"repos":["grigorisg9gr/polynomials-for-augmenting-nns"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/slow-fast-auditory-streams-for-audio","slug":"slow-fast-auditory-streams-for-audio","title":"Slow-Fast Auditory Streams For Audio Recognition","date":"2021-03-05","arxiv_id":"2103.03516","repositories_listed":2,"syntology":null},{"url":"/paper/artificially-synthesising-data-for-audio","slug":"artificially-synthesising-data-for-audio","title":"Artificially Synthesising Data for Audio Classification and Segmentation to Improve Speech and Music Detection in Radio Broadcast","date":"2021-02-19","arxiv_id":"2102.09959","repositories_listed":2,"syntology":null},{"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/generalised-interpretable-shapelets-for","slug":"generalised-interpretable-shapelets-for","title":"Generalised Interpretable Shapelets for Irregular Time Series","date":"2020-05-28","arxiv_id":"2005.13948","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/generalised-interpretable-shapelets-for#ran","syntology_url":"https://syntology.ai/paper/2005.13948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.13948"}},"official":{"repos":["patrick-kidger/generalised_shapelets","jambo6/generalised_shapelets"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/-nets-deep-polynomial-neural-networks","slug":"-nets-deep-polynomial-neural-networks","title":"$Π-$nets: Deep Polynomial Neural Networks","date":"2020-03-08","arxiv_id":"2003.03828","repositories_listed":2,"syntology":null},{"url":"/paper/moped-efficient-priors-for-scalable","slug":"moped-efficient-priors-for-scalable","title":"Specifying Weight Priors in Bayesian Deep Neural Networks with Empirical Bayes","date":"2019-06-12","arxiv_id":"1906.05323","repositories_listed":2,"syntology":null},{"url":"/paper/fully-few-shot-class-incremental-audio-1","slug":"fully-few-shot-class-incremental-audio-1","title":"Fully Few-shot Class-incremental Audio Classification Using Multi-level Embedding Extractor and Ridge Regression Classifier","date":"2025-06-23","arxiv_id":"2506.18406","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-differential-denoising-for","slug":"adaptive-differential-denoising-for","title":"Adaptive Differential Denoising for Respiratory Sounds Classification","date":"2025-06-03","arxiv_id":"2506.02505","repositories_listed":1,"syntology":null},{"url":"/paper/spectrotemporal-modulation-efficient-and","slug":"spectrotemporal-modulation-efficient-and","title":"Spectrotemporal Modulation: Efficient and Interpretable Feature Representation for Classifying Speech, Music, and Environmental Sounds","date":"2025-05-29","arxiv_id":"2505.23509","repositories_listed":1,"syntology":null},{"url":"/paper/patient-aware-feature-alignment-for-robust","slug":"patient-aware-feature-alignment-for-robust","title":"Patient-Aware Feature Alignment for Robust Lung Sound Classification:Cohesion-Separation and Global Alignment Losses","date":"2025-05-28","arxiv_id":"2505.23834","repositories_listed":1,"syntology":null},{"url":"/paper/15500-seconds-lean-uav-classification","slug":"15500-seconds-lean-uav-classification","title":"15,500 Seconds: Lean UAV Classification Leveraging PEFT and Pre-Trained Networks","date":"2025-05-21","arxiv_id":"2506.11049","repositories_listed":1,"syntology":null},{"url":"/paper/4500-seconds-small-data-training-approaches","slug":"4500-seconds-small-data-training-approaches","title":"4,500 Seconds: Small Data Training Approaches for Deep UAV Audio Classification","date":"2025-05-21","arxiv_id":"2505.23782","repositories_listed":1,"syntology":null},{"url":"/paper/a-training-framework-for-optimal-and-stable","slug":"a-training-framework-for-optimal-and-stable","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","date":"2025-05-16","arxiv_id":"2505.11589","repositories_listed":1,"syntology":null},{"url":"/paper/token-pruning-in-audio-transformers","slug":"token-pruning-in-audio-transformers","title":"Token Pruning in Audio Transformers: Optimizing Performance and Decoding Patch Importance","date":"2025-04-02","arxiv_id":"2504.01690","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/cycleguardian-a-framework-for-automatic","slug":"cycleguardian-a-framework-for-automatic","title":"CycleGuardian: A Framework for Automatic RespiratorySound classification Based on Improved Deep clustering and Contrastive Learning","date":"2025-02-02","arxiv_id":"2502.00734","repositories_listed":1,"syntology":null},{"url":"/paper/performance-analysis-of-hybrid-quantum","slug":"performance-analysis-of-hybrid-quantum","title":"Performance Analysis of Hybrid Quantum-Classical Convolutional Neural Networks for Audio Classification","date":"2024-11-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/taxabind-a-unified-embedding-space-for","slug":"taxabind-a-unified-embedding-space-for","title":"TaxaBind: A Unified Embedding Space for Ecological Applications","date":"2024-11-01","arxiv_id":"2411.00683","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/taxabind-a-unified-embedding-space-for#ran","syntology_url":"https://syntology.ai/paper/2411.00683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00683"}},"official":{"repos":["mvrl/taxabind"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/episodic-fine-tuning-prototypical-networks","slug":"episodic-fine-tuning-prototypical-networks","title":"Episodic fine-tuning prototypical networks for optimization-based few-shot learning: Application to audio classification","date":"2024-10-04","arxiv_id":"2410.05302","repositories_listed":1,"syntology":null},{"url":"/paper/synthio-augmenting-small-scale-audio","slug":"synthio-augmenting-small-scale-audio","title":"Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data","date":"2024-10-02","arxiv_id":"2410.02056","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/synthio-augmenting-small-scale-audio#ran","syntology_url":"https://syntology.ai/paper/2410.02056","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02056"}},"official":{"repos":["sreyan88/synthio"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/reclap-improving-zero-shot-audio","slug":"reclap-improving-zero-shot-audio","title":"ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds","date":"2024-09-13","arxiv_id":"2409.09213","repositories_listed":1,"syntology":null},{"url":"/paper/ildnet-a-novel-deep-learning-framework-for","slug":"ildnet-a-novel-deep-learning-framework-for","title":"ILDNet: A Novel Deep Learning Framework for Interstitial Lung Disease Identification Using Respiratory Sounds","date":"2024-08-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-audio-language-models-through-self","slug":"enhancing-audio-language-models-through-self","title":"Enhancing Audio-Language Models through Self-Supervised Post-Training with Text-Audio Pairs","date":"2024-08-17","arxiv_id":"2408.09269","repositories_listed":1,"syntology":null},{"url":"/paper/multi-label-audio-classification-with-a-noisy","slug":"multi-label-audio-classification-with-a-noisy","title":"Multi-label audio classification with a noisy zero-shot teacher","date":"2024-07-20","arxiv_id":"2407.14712","repositories_listed":1,"syntology":null},{"url":"/paper/elasticast-an-audio-spectrogram-transformer","slug":"elasticast-an-audio-spectrogram-transformer","title":"ElasticAST: An Audio Spectrogram Transformer for All Length and Resolutions","date":"2024-07-11","arxiv_id":"2407.08691","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/exploiting-foundation-models-and-speech","slug":"exploiting-foundation-models-and-speech","title":"Exploiting Foundation Models and Speech Enhancement for Parkinson's Disease Detection from Speech in Real-World Operative Conditions","date":"2024-06-23","arxiv_id":"2406.16128","repositories_listed":1,"syntology":null},{"url":"/paper/fully-few-shot-class-incremental-audio","slug":"fully-few-shot-class-incremental-audio","title":"Fully Few-shot Class-incremental Audio Classification Using Expandable Dual-embedding Extractor","date":"2024-06-12","arxiv_id":"2406.08122","repositories_listed":1,"syntology":null},{"url":"/paper/fastast-accelerating-audio-spectrogram","slug":"fastast-accelerating-audio-spectrogram","title":"FastAST: Accelerating Audio Spectrogram Transformer via Token Merging and Cross-Model Knowledge Distillation","date":"2024-06-11","arxiv_id":"2406.07676","repositories_listed":1,"syntology":null},{"url":"/paper/bts-bridging-text-and-sound-modalities-for","slug":"bts-bridging-text-and-sound-modalities-for","title":"BTS: Bridging Text and Sound Modalities for Metadata-Aided Respiratory Sound Classification","date":"2024-06-10","arxiv_id":"2406.06786","repositories_listed":1,"syntology":null},{"url":"/paper/audio-mamba-bidirectional-state-space-model","slug":"audio-mamba-bidirectional-state-space-model","title":"Audio Mamba: Bidirectional State Space Model for Audio Representation Learning","date":"2024-06-05","arxiv_id":"2406.03344","repositories_listed":1,"syntology":{"n":17,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":6,"phrase":"11 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; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/audio-mamba-bidirectional-state-space-model#ran","syntology_url":"https://syntology.ai/paper/2406.03344","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03344"}},"official":{"repos":["mhamzaerol/audio-mamba-aum"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/animal2vec-and-meerkat-a-self-supervised","slug":"animal2vec-and-meerkat-a-self-supervised","title":"animal2vec and MeerKAT: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacoustics","date":"2024-06-03","arxiv_id":"2406.01253","repositories_listed":1,"syntology":null},{"url":"/paper/ssamba-self-supervised-audio-representation","slug":"ssamba-self-supervised-audio-representation","title":"SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model","date":"2024-05-20","arxiv_id":"2405.11831","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/ssamba-self-supervised-audio-representation#ran","syntology_url":"https://syntology.ai/paper/2405.11831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11831"}},"official":{"repos":["siavashshams/ssamba"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/investigating-design-choices-in-joint","slug":"investigating-design-choices-in-joint","title":"Investigating Design Choices in Joint-Embedding Predictive Architectures for General Audio Representation Learning","date":"2024-05-14","arxiv_id":"2405.08679","repositories_listed":1,"syntology":null},{"url":"/paper/on-device-online-learning-and-semantic","slug":"on-device-online-learning-and-semantic","title":"On-device Online Learning and Semantic Management of TinyML Systems","date":"2024-05-13","arxiv_id":"2405.07601","repositories_listed":1,"syntology":null},{"url":"/paper/rene-a-pre-trained-multi-modal-architecture","slug":"rene-a-pre-trained-multi-modal-architecture","title":"Rene: A Pre-trained Multi-modal Architecture for Auscultation of Respiratory Diseases","date":"2024-05-13","arxiv_id":"2405.07442","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-representations-for-speech-music","slug":"benchmarking-representations-for-speech-music","title":"Benchmarking Representations for Speech, Music, and Acoustic Events","date":"2024-05-02","arxiv_id":"2405.00934","repositories_listed":1,"syntology":null},{"url":"/paper/scalable-event-by-event-processing-of","slug":"scalable-event-by-event-processing-of","title":"Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Models","date":"2024-04-29","arxiv_id":"2404.18508","repositories_listed":1,"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":10,"n_instrument":5,"n_unverified":3,"n_honours":1,"n_violates":2,"n_no_contract":7,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 2 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/scalable-event-by-event-processing-of#ran","syntology_url":"https://syntology.ai/paper/2404.18508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18508"}},"official":{"repos":["Efficient-Scalable-Machine-Learning/event-ssm"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/max-ast-combining-convolution-local-and","slug":"max-ast-combining-convolution-local-and","title":"MAX-AST: COMBINING CONVOLUTION, LOCAL AND GLOBAL SELF-ATTENTIONS FOR AUDIO EVENT CLASSIFICATION","date":"2024-04-14","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/audio-visual-generalized-zero-shot-learning","slug":"audio-visual-generalized-zero-shot-learning","title":"Audio-Visual Generalized Zero-Shot Learning using Pre-Trained Large Multi-Modal Models","date":"2024-04-09","arxiv_id":"2404.06309","repositories_listed":1,"syntology":null},{"url":"/paper/nemo-dataset-of-emotional-speech-in-polish","slug":"nemo-dataset-of-emotional-speech-in-polish","title":"nEMO: Dataset of Emotional Speech in Polish","date":"2024-04-09","arxiv_id":"2404.06292","repositories_listed":1,"syntology":null},{"url":"/paper/dtf-at-decoupled-time-frequency-audio","slug":"dtf-at-decoupled-time-frequency-audio","title":"DTF-AT: Decoupled Time-Frequency Audio Transformer for Event Classification","date":"2024-03-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/birdset-a-multi-task-benchmark-for","slug":"birdset-a-multi-task-benchmark-for","title":"BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics","date":"2024-03-15","arxiv_id":"2403.10380","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/birdset-a-multi-task-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2403.10380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10380"}},"official":{"repos":["dbd-research-group/birdset"],"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/equiav-leveraging-equivariance-for-audio","slug":"equiav-leveraging-equivariance-for-audio","title":"EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning","date":"2024-03-14","arxiv_id":"2403.09502","repositories_listed":1,"syntology":{"n":13,"n_ran":6,"n_constructed":4,"n_ran_checked":5,"n_instrument":1,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/equiav-leveraging-equivariance-for-audio#ran","syntology_url":"https://syntology.ai/paper/2403.09502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09502"}},"official":{"repos":["jongsuk1/equiav"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/leveraging-pre-trained-autoencoders-for","slug":"leveraging-pre-trained-autoencoders-for","title":"Leveraging Pre-Trained Autoencoders for Interpretable Prototype Learning of Music Audio","date":"2024-02-14","arxiv_id":"2402.09318","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-transferability-of-large-scale-self","slug":"on-the-transferability-of-large-scale-self","title":"On the Transferability of Large-Scale Self-Supervision to Few-Shot Audio Classification","date":"2024-02-02","arxiv_id":"2402.01274","repositories_listed":1,"syntology":null},{"url":"/paper/learning-audio-concepts-from-counterfactual","slug":"learning-audio-concepts-from-counterfactual","title":"Learning Audio Concepts from Counterfactual Natural Language","date":"2024-01-10","arxiv_id":"2401.04935","repositories_listed":1,"syntology":null},{"url":"/paper/eat-self-supervised-pre-training-with","slug":"eat-self-supervised-pre-training-with","title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer","date":"2024-01-07","arxiv_id":"2401.03497","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/eat-self-supervised-pre-training-with#ran","syntology_url":"https://syntology.ai/paper/2401.03497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03497"}},"official":{"repos":["cwx-worst-one/eat"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/clapp-contrastive-language-audio-pre-training","slug":"clapp-contrastive-language-audio-pre-training","title":"Oceanship: A Large-Scale Dataset for Underwater Audio Target Recognition","date":"2024-01-04","arxiv_id":"2401.02099","repositories_listed":1,"syntology":null},{"url":"/paper/stethoscope-guided-supervised-contrastive","slug":"stethoscope-guided-supervised-contrastive","title":"Stethoscope-guided Supervised Contrastive Learning for Cross-domain Adaptation on Respiratory Sound Classification","date":"2023-12-15","arxiv_id":"2312.09603","repositories_listed":1,"syntology":null},{"url":"/paper/parameter-efficient-transfer-learning-of","slug":"parameter-efficient-transfer-learning-of","title":"Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers","date":"2023-12-06","arxiv_id":"2312.03694","repositories_listed":1,"syntology":null},{"url":"/paper/formal-verification-of-long-short-term-memory","slug":"formal-verification-of-long-short-term-memory","title":"Formal Verification of Long Short-Term Memory based Audio Classifiers: A Star based Approach","date":"2023-11-16","arxiv_id":"2311.12130","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-the-emergent-audio","slug":"investigating-the-emergent-audio","title":"Investigating the Emergent Audio Classification Ability of ASR Foundation Models","date":"2023-11-15","arxiv_id":"2311.09363","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-fine-tuning-using-generated","slug":"adversarial-fine-tuning-using-generated","title":"Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalance","date":"2023-11-11","arxiv_id":"2311.06480","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 3 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) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/adversarial-fine-tuning-using-generated#ran","syntology_url":"https://syntology.ai/paper/2311.06480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.06480"}},"official":{"repos":["kaen2891/adversarial_fine-tuning_using_generated_respiratory_sound"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/auto-deep-learning-for-bioacoustic-signals","slug":"auto-deep-learning-for-bioacoustic-signals","title":"Auto deep learning for bioacoustic signals","date":"2023-11-08","arxiv_id":"2311.04945","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/clara-multilingual-contrastive-learning-for","slug":"clara-multilingual-contrastive-learning-for","title":"CLARA: Multilingual Contrastive Learning for Audio Representation Acquisition","date":"2023-10-18","arxiv_id":"2310.11830","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-meta-information-for-audio-based","slug":"exploring-meta-information-for-audio-based","title":"Exploring Meta Information for Audio-based Zero-shot Bird Classification","date":"2023-09-15","arxiv_id":"2309.08398","repositories_listed":1,"syntology":null},{"url":"/paper/edac-efficient-deployment-of-audio","slug":"edac-efficient-deployment-of-audio","title":"EDAC: Efficient Deployment of Audio Classification Models For COVID-19 Detection","date":"2023-09-11","arxiv_id":"2309.05357","repositories_listed":1,"syntology":null},{"url":"/paper/audrandaug-random-image-augmentations-for","slug":"audrandaug-random-image-augmentations-for","title":"AudRandAug: Random Image Augmentations for Audio Classification","date":"2023-09-09","arxiv_id":"2309.04762","repositories_listed":1,"syntology":null},{"url":"/paper/asthmascelnet-a-lightweight-supervised","slug":"asthmascelnet-a-lightweight-supervised","title":"AsthmaSCELNet: A Lightweight Supervised Contrastive Embedding Learning Framework For Asthma Classification Using Lung Sounds","date":"2023-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/astfsonn-a-unified-framework-based-on-time","slug":"astfsonn-a-unified-framework-based-on-time","title":"AsTFSONN: A Unified Framework Based on Time-Frequency Domain Self-Operational Neural Network for Asthmatic Lung Sound Classification","date":"2023-07-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/rdlinet-a-novel-lightweight-inception-network","slug":"rdlinet-a-novel-lightweight-inception-network","title":"RDLINet: A Novel Lightweight Inception Network for Respiratory Disease Classification Using Lung Sounds","date":"2023-07-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-delays-in-spiking-neural-networks","slug":"learning-delays-in-spiking-neural-networks","title":"Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings","date":"2023-06-30","arxiv_id":"2306.17670","repositories_listed":1,"syntology":null},{"url":"/paper/s-tllr-stdp-inspired-temporal-local-learning","slug":"s-tllr-stdp-inspired-temporal-local-learning","title":"S-TLLR: STDP-inspired Temporal Local Learning Rule for Spiking Neural Networks","date":"2023-06-27","arxiv_id":"2306.15220","repositories_listed":1,"syntology":null}],"syntology_records":33,"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-classification-on-esc-50","since_archive":"/sota/audio-classification-on-esc-50#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/audio-classification-on-shd","since_archive":"/sota/audio-classification-on-shd#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/audio-classification-on-fsd50k","since_archive":"/sota/audio-classification-on-fsd50k#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/audio-classification-on-speech-commands-1","since_archive":"/sota/audio-classification-on-speech-commands-1#since-judged","papers_judged":2,"placed":0}]},"papers_where_code_ran":46,"papers_where_code_ran_first_page":"/task/audio-classification/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":4,"url":"/task/audio-classification/papers/2","json":"/task/audio-classification/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/audio-classification/papers/3","json":"/task/audio-classification/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/audio-classification/papers/4","json":"/task/audio-classification/papers/4.json","rows":61},{"order":"ran","page":1,"of":1,"url":"/task/audio-classification/papers/ran/1","json":"/task/audio-classification/papers/ran/1.json","rows":46}],"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":"7690a726bed8b6ebbb031ef9b03eccb1a63d0783cf8a126372f55499757d2a2c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}