{"url":"/sota/audio-classification-on-icbhi-respiratory","task":{"name":"Audio Classification","url":"/task/audio-classification","note":null},"dataset":{"name":"ICBHI Respiratory Sound Database","url":"/dataset/icbhi-respiratory-sound-database"},"category":"Audio","categories":["Audio"],"category_note":null,"description":"**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.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["ICBHI Score","Sensitivity","Specificity"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"ICBHI Score":"higher","Sensitivity":null,"Specificity":null}},"counts":{"rows":25,"rows_with_code":21,"rows_with_paper_page":25,"rows_dated":25,"rows_using_additional_data":14},"rows":[{"rank_in_archive_order":1,"model":"ADD","metrics":{"ICBHI Score":"65.53","Sensitivity":"45.94","Specificity":"85.13"},"uses_additional_data":false,"paper_date":"2025-06-03","paper":"/paper/adaptive-differential-denoising-for","paper_url":"https://arxiv.org/abs/2506.02505v1","paper_title":"Adaptive Differential Denoising for Respiratory Sounds Classification","code":"https://github.com/deegy666/add-rsc","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"BEATs (PAFA)","metrics":{"ICBHI Score":"64.84","Sensitivity":"47.63","Specificity":"82.05"},"uses_additional_data":true,"paper_date":"2025-05-28","paper":"/paper/patient-aware-feature-alignment-for-robust","paper_url":"https://arxiv.org/abs/2505.23834v1","paper_title":"Patient-Aware Feature Alignment for Robust Lung Sound Classification:Cohesion-Separation and Global Alignment Losses","code":"https://github.com/wa976/pafa","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"BTS","metrics":{"ICBHI Score":"63.54","Sensitivity":"45.67","Specificity":"81.4"},"uses_additional_data":false,"paper_date":"2024-06-10","paper":"/paper/bts-bridging-text-and-sound-modalities-for","paper_url":"https://arxiv.org/abs/2406.06786v2","paper_title":"BTS: Bridging Text and Sound Modalities for Metadata-Aided Respiratory Sound Classification","code":"https://github.com/kaen2891/bts","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"BEATs (CE)","metrics":{"ICBHI Score":"63.49","Sensitivity":"48.21","Specificity":"78.77"},"uses_additional_data":true,"paper_date":"2025-05-28","paper":"/paper/patient-aware-feature-alignment-for-robust","paper_url":"https://arxiv.org/abs/2505.23834v1","paper_title":"Patient-Aware Feature Alignment for Robust Lung Sound Classification:Cohesion-Separation and Global Alignment Losses","code":"https://github.com/wa976/pafa","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"M2D-X/0.7 (η=0.3)","metrics":{"ICBHI Score":"63.29"},"uses_additional_data":true,"paper_date":"2024-04-09","paper":"/paper/masked-modeling-duo-towards-a-universal-audio","paper_url":"https://arxiv.org/abs/2404.06095v1","paper_title":"Masked Modeling Duo: Towards a Universal Audio Pre-training Framework","code":"https://github.com/nttcslab/m2d","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":6,"model":"CycleGuardian","metrics":{"ICBHI Score":"63.26","Sensitivity":"44.47","Specificity":"82.06"},"uses_additional_data":false,"paper_date":"2025-02-02","paper":"/paper/cycleguardian-a-framework-for-automatic","paper_url":"https://arxiv.org/abs/2502.00734v1","paper_title":"CycleGuardian: A Framework for Automatic RespiratorySound classification Based on Improved Deep clustering and Contrastive Learning","code":"https://github.com/chumingqian/CycleGuardian","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"M2D/0.7 (e=0.3)","metrics":{"ICBHI Score":"62.73"},"uses_additional_data":false,"paper_date":"2024-04-09","paper":"/paper/masked-modeling-duo-towards-a-universal-audio","paper_url":"https://arxiv.org/abs/2404.06095v1","paper_title":"Masked Modeling Duo: Towards a Universal Audio Pre-training Framework","code":"https://github.com/nttcslab/m2d","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":8,"model":"Audio-CLAP","metrics":{"ICBHI Score":"62.56","Sensitivity":"44.67","Specificity":"80.85"},"uses_additional_data":false,"paper_date":"2024-06-10","paper":"/paper/bts-bridging-text-and-sound-modalities-for","paper_url":"https://arxiv.org/abs/2406.06786v2","paper_title":"BTS: Bridging Text and Sound Modalities for Metadata-Aided Respiratory Sound Classification","code":"https://github.com/kaen2891/bts","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"AST (Patch-Mix CL)","metrics":{"ICBHI Score":"62.37","Sensitivity":"43.07","Specificity":"81.66"},"uses_additional_data":true,"paper_date":"2023-05-23","paper":"/paper/patch-mix-contrastive-learning-with-audio","paper_url":"https://arxiv.org/abs/2305.14032v5","paper_title":"Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification","code":"https://github.com/raymin0223/patch-mix_contrastive_learning","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"AFT on Mixed-500","metrics":{"ICBHI Score":"61.79","Sensitivity":"42.86","Specificity":"80.72"},"uses_additional_data":true,"paper_date":"2023-11-11","paper":"/paper/adversarial-fine-tuning-using-generated","paper_url":"https://arxiv.org/abs/2311.06480v1","paper_title":"Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalance","code":"https://github.com/kaen2891/adversarial_fine-tuning_using_generated_respiratory_sound","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":11,"model":"SG-SCL (AST)","metrics":{"ICBHI Score":"61.71","Sensitivity":"43.55","Specificity":"79.87"},"uses_additional_data":true,"paper_date":"2023-12-15","paper":"/paper/stethoscope-guided-supervised-contrastive","paper_url":"https://arxiv.org/abs/2312.09603v1","paper_title":"Stethoscope-guided Supervised Contrastive Learning for Cross-domain Adaptation on Respiratory Sound Classification","code":"https://github.com/kaen2891/stethoscope-guided_supervised_contrastive_learning","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"DAT (AST)","metrics":{"ICBHI Score":"59.81","Sensitivity":"42.50","Specificity":"77.11"},"uses_additional_data":true,"paper_date":"2023-12-15","paper":"/paper/stethoscope-guided-supervised-contrastive","paper_url":"https://arxiv.org/abs/2312.09603v1","paper_title":"Stethoscope-guided Supervised Contrastive Learning for Cross-domain Adaptation on Respiratory Sound Classification","code":"https://github.com/kaen2891/stethoscope-guided_supervised_contrastive_learning","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"AST (fine-tuning)","metrics":{"ICBHI Score":"59.55"},"uses_additional_data":true,"paper_date":"2023-05-23","paper":"/paper/patch-mix-contrastive-learning-with-audio","paper_url":"https://arxiv.org/abs/2305.14032v5","paper_title":"Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification","code":"https://github.com/raymin0223/patch-mix_contrastive_learning","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"ResNet-50","metrics":{"ICBHI Score":"58.29","Sensitivity":"37.24","Specificity":"79.34"},"uses_additional_data":true,"paper_date":"2021-08-04","paper":"/paper/lung-sound-classification-using-co-tuning-and","paper_url":"https://arxiv.org/abs/2108.01991v1","paper_title":"Lung Sound Classification Using Co-tuning and Stochastic Normalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"CNN6 (+metadata)","metrics":{"ICBHI Score":"58.04"},"uses_additional_data":false,"paper_date":"2022-10-27","paper":"/paper/supervised-contrastive-learning-for-3","paper_url":"https://arxiv.org/abs/2210.16192v3","paper_title":"Pretraining Respiratory Sound Representations using Metadata and Contrastive Learning","code":"https://github.com/ilyassmoummad/scl_icbhi2017","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"CNN6","metrics":{"ICBHI Score":"57.55","Specificity":"75.95"},"uses_additional_data":true,"paper_date":"2022-10-27","paper":"/paper/supervised-contrastive-learning-for-3","paper_url":"https://arxiv.org/abs/2210.16192v3","paper_title":"Pretraining Respiratory Sound Representations using Metadata and Contrastive Learning","code":"https://github.com/ilyassmoummad/scl_icbhi2017","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"bi-ResNet-Att","metrics":{"ICBHI Score":"56.76","Sensitivity":"46.38","Specificity":"67.13"},"uses_additional_data":true,"paper_date":"2022-01-14","paper":"/paper/arsc-net-adventitious-respiratory-sound","paper_url":"https://ieeexplore.ieee.org/document/9669787/","paper_title":"ARSC-Net: Adventitious Respiratory Sound Classification Network Using Parallel Paths with Channel-Spatial Attention","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"ResNet-34","metrics":{"ICBHI Score":"56.20","Sensitivity":"40.10","Specificity":"72.30"},"uses_additional_data":true,"paper_date":"2020-10-31","paper":"/paper/respirenet-a-deep-neural-network-for","paper_url":"https://arxiv.org/abs/2011.00196v2","paper_title":"RespireNet: A Deep Neural Network for Accurately Detecting Abnormal Lung Sounds in Limited Data Setting","code":"https://github.com/microsoft/RespireNet","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"ResNeSt","metrics":{"ICBHI Score":"55.30","Sensitivity":"40.20","Specificity":"70.40"},"uses_additional_data":true,"paper_date":"2022-04-27","paper":"/paper/a-domain-transfer-based-data-augmentation","paper_url":"https://ieeexplore.ieee.org/document/9746941","paper_title":"A DOMAIN TRANSFER BASED DATA AUGMENTATION METHOD FOR AUTOMATED RESPIRATORY CLASSIFICATION","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"CNN6\n(scratch)","metrics":{"ICBHI Score":"54.74","Sensitivity":"33.84","Specificity":"75.35"},"uses_additional_data":false,"paper_date":"2022-10-27","paper":"/paper/supervised-contrastive-learning-for-3","paper_url":"https://arxiv.org/abs/2210.16192v3","paper_title":"Pretraining Respiratory Sound Representations using Metadata and Contrastive Learning","code":"https://github.com/ilyassmoummad/scl_icbhi2017","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"ResNet-Att\n(scratch)","metrics":{"ICBHI Score":"53.90","Sensitivity":"36.36","Specificity":"71.44"},"uses_additional_data":false,"paper_date":"2021-10-29","paper":"/paper/lungattn-advanced-lung-sound-classification","paper_url":"https://iopscience.iop.org/article/10.1088/1361-6579/ac27b9","paper_title":"LungAttn: advanced lung sound classification using attention mechanism with dual TQWT and triple STFT spectrogram","code":"https://github.com/SJTU-YONGFU-RESEARCH-GRP/LungAttn","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"ResNet\n(scratch)","metrics":{"ICBHI Score":"52.26","Sensitivity":"41.32","Specificity":"63.20"},"uses_additional_data":false,"paper_date":"2020-08-01","paper":"/paper/lungrn-nl-an-improved-adventitious-lung-sound","paper_url":"https://www.isca-speech.org/archive/interspeech_2020/ma20_interspeech.html","paper_title":"LungRN+NL: An Improved Adventitious Lung Sound Classification Using Non-Local Block ResNet Neural Network with Mixup Data Augmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"bi-ResNet\n(scratch)","metrics":{"ICBHI Score":"50.16","Sensitivity":"31.10","Specificity":"69.20"},"uses_additional_data":false,"paper_date":"2019-12-05","paper":"/paper/lungbrn-a-smart-digital-stethoscope-for","paper_url":"https://ieeexplore.ieee.org/document/8919021","paper_title":"LungBRN: A Smart Digital Stethoscope for Detecting Respiratory Disease Using bi-ResNet Deep Learning Algorithm","code":"https://github.com/SJTU-YONGFU-RESEARCH-GRP/Lung-Sound-Classification-System-LungSys-I","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"AST (fine-tuning)","metrics":{"Sensitivity":"41.97","Specificity":"77.14"},"uses_additional_data":false,"paper_date":"2023-05-23","paper":"/paper/patch-mix-contrastive-learning-with-audio","paper_url":"https://arxiv.org/abs/2305.14032v5","paper_title":"Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification","code":"https://github.com/raymin0223/patch-mix_contrastive_learning","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"CNN6\n(+metadata)","metrics":{"Sensitivity":"39.15","Specificity":"76.93"},"uses_additional_data":true,"paper_date":"2022-10-27","paper":"/paper/supervised-contrastive-learning-for-3","paper_url":"https://arxiv.org/abs/2210.16192v3","paper_title":"Pretraining Respiratory Sound Representations using Metadata and Contrastive Learning","code":"https://github.com/ilyassmoummad/scl_icbhi2017","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":7,"rows_with_any_sample_ran":6,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":11,"n_unverified":8,"n_samples":19,"n_pointer_only_licence":10,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":20,"n_unverified":18,"n_samples":38,"n_pointer_only_licence":17,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}