{"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/sound-classification","name":"Sound Classification","slug":"sound-classification","description_markdown":null,"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":148,"papers_with_code":61,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/infantmarmosetsvox","name":"InfantMarmosetsVox","full_name":"InfantMarmosetsVox","num_papers_in_archive":3},{"url":"/dataset/audio-de-mosquitos-aedes-aegypti","name":"Audio de mosquitos Aedes Aegypti","full_name":"Wing beats","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":148,"of_with_code":61,"tagged_in_all":148,"counts":{"archive_papers_tagged":148,"with_a_code_link":61,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":148,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":5,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/deep-convolutional-neural-networks-and-data-1","slug":"deep-convolutional-neural-networks-and-data-1","title":"Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification","date":"2016-08-15","arxiv_id":"1608.04363","repositories_listed":5,"syntology":null},{"url":"/paper/audioclip-extending-clip-to-image-text-and","slug":"audioclip-extending-clip-to-image-text-and","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","date":"2021-06-24","arxiv_id":"2106.13043","repositories_listed":4,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/audioclip-extending-clip-to-image-text-and#ran","syntology_url":"https://syntology.ai/paper/2106.13043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13043"}},"official":{"repos":["AndreyGuzhov/AudioCLIP"],"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/buet-multi-disease-heart-sound-dataset-a","slug":"buet-multi-disease-heart-sound-dataset-a","title":"BUET Multi-disease Heart Sound Dataset: A Comprehensive Auscultation Dataset for Developing Computer-Aided Diagnostic Systems","date":"2024-09-01","arxiv_id":"2409.00724","repositories_listed":2,"syntology":null},{"url":"/paper/differentiable-tracking-based-training-of","slug":"differentiable-tracking-based-training-of","title":"Differentiable Tracking-Based Training of Deep Learning Sound Source Localizers","date":"2021-10-29","arxiv_id":"2111.00030","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-environmental-sound-classification","slug":"end-to-end-environmental-sound-classification","title":"End-to-End Environmental Sound Classification using a 1D Convolutional Neural Network","date":"2019-04-18","arxiv_id":"1904.08990","repositories_listed":2,"syntology":null},{"url":"/paper/masked-conditional-neural-networks-for-1","slug":"masked-conditional-neural-networks-for-1","title":"Masked Conditional Neural Networks for Environmental Sound Classification","date":"2018-05-25","arxiv_id":"1805.10004","repositories_listed":2,"syntology":null},{"url":"/paper/domain-adaptation-method-and-modality-gap","slug":"domain-adaptation-method-and-modality-gap","title":"Domain Adaptation Method and Modality Gap Impact in Audio-Text Models for Prototypical Sound Classification","date":"2025-06-04","arxiv_id":"2506.04376","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/improving-respiratory-sound-classification","slug":"improving-respiratory-sound-classification","title":"Improving Respiratory Sound Classification with Architecture-Agnostic Knowledge Distillation from Ensembles","date":"2025-05-28","arxiv_id":"2505.22027","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/the-computation-of-generalized-embeddings-for","slug":"the-computation-of-generalized-embeddings-for","title":"The Computation of Generalized Embeddings for Underwater Acoustic Target Recognition using Contrastive Learning","date":"2025-05-19","arxiv_id":"2505.12904","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-convolutional-dictionary","slug":"weakly-supervised-convolutional-dictionary","title":"Weakly Supervised Convolutional Dictionary Learning for Multi-Label Classification","date":"2025-03-11","arxiv_id":"2503.08573","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/manikin-recorded-cardiopulmonary-sounds","slug":"manikin-recorded-cardiopulmonary-sounds","title":"Manikin-Recorded Cardiopulmonary Sounds Dataset Using Digital Stethoscope","date":"2024-10-04","arxiv_id":"2410.03280","repositories_listed":1,"syntology":null},{"url":"/paper/heterogeneous-sound-classification-with-the","slug":"heterogeneous-sound-classification-with-the","title":"Heterogeneous sound classification with the Broad Sound Taxonomy and Dataset","date":"2024-10-01","arxiv_id":"2410.00980","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/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/self-supervised-learning-for-few-shot-bird","slug":"self-supervised-learning-for-few-shot-bird","title":"Self-Supervised Learning for Few-Shot Bird Sound Classification","date":"2023-12-25","arxiv_id":"2312.15824","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/multi-view-spectrogram-transformer-for","slug":"multi-view-spectrogram-transformer-for","title":"Multi-View Spectrogram Transformer for Respiratory Sound Classification","date":"2023-11-16","arxiv_id":"2311.09655","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/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/patch-mix-contrastive-learning-with-audio","slug":"patch-mix-contrastive-learning-with-audio","title":"Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification","date":"2023-05-23","arxiv_id":"2305.14032","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/patch-mix-contrastive-learning-with-audio#ran","syntology_url":"https://syntology.ai/paper/2305.14032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14032"}},"official":{"repos":["raymin0223/patch-mix_contrastive_learning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/face-fast-accurate-and-context-aware-audio","slug":"face-fast-accurate-and-context-aware-audio","title":"Face: Fast, Accurate and Context-Aware Audio Annotation and Classification","date":"2023-03-07","arxiv_id":"2303.03666","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-classification-to-improve-the","slug":"unsupervised-classification-to-improve-the","title":"Unsupervised classification to improve the quality of a bird song recording dataset","date":"2023-02-15","arxiv_id":"2302.07560","repositories_listed":1,"syntology":null},{"url":"/paper/a-dataset-for-audio-visual-sound-event","slug":"a-dataset-for-audio-visual-sound-event","title":"A dataset for Audio-Visual Sound Event Detection in Movies","date":"2023-02-14","arxiv_id":"2302.07315","repositories_listed":1,"syntology":null},{"url":"/paper/epic-sounds-a-large-scale-dataset-of-actions","slug":"epic-sounds-a-large-scale-dataset-of-actions","title":"Epic-Sounds: A Large-scale Dataset of Actions That Sound","date":"2023-02-01","arxiv_id":"2302.00646","repositories_listed":1,"syntology":null},{"url":"/paper/xkd-cross-modal-knowledge-distillation-with","slug":"xkd-cross-modal-knowledge-distillation-with","title":"XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning","date":"2022-11-25","arxiv_id":"2211.13929","repositories_listed":1,"syntology":null},{"url":"/paper/effective-audio-classification-network-based","slug":"effective-audio-classification-network-based","title":"Effective Audio Classification Network Based on Paired Inverse Pyramid Structure and Dense MLP Block","date":"2022-11-05","arxiv_id":"2211.02940","repositories_listed":1,"syntology":null},{"url":"/paper/supervised-contrastive-learning-for-3","slug":"supervised-contrastive-learning-for-3","title":"Pretraining Respiratory Sound Representations using Metadata and Contrastive Learning","date":"2022-10-27","arxiv_id":"2210.16192","repositories_listed":1,"syntology":null},{"url":"/paper/enemy-spotted-in-game-gun-sound-dataset-for-1","slug":"enemy-spotted-in-game-gun-sound-dataset-for-1","title":"Enemy Spotted: in-game gun sound dataset for gunshot classification and localization","date":"2022-10-12","arxiv_id":"2210.05917","repositories_listed":1,"syntology":null},{"url":"/paper/enemy-spotted-in-game-gun-sound-dataset-for","slug":"enemy-spotted-in-game-gun-sound-dataset-for","title":"Enemy Spotted: in-game gun sound dataset for gunshot classification and localization","date":"2022-08-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/housex-a-fine-grained-house-music-dataset-and","slug":"housex-a-fine-grained-house-music-dataset-and","title":"HouseX: A Fine-grained House Music Dataset and its Potential in the Music Industry","date":"2022-07-24","arxiv_id":"2207.11690","repositories_listed":1,"syntology":null},{"url":"/paper/continual-learning-for-on-device","slug":"continual-learning-for-on-device","title":"Continual Learning For On-Device Environmental Sound Classification","date":"2022-07-15","arxiv_id":"2207.07429","repositories_listed":1,"syntology":null},{"url":"/paper/a-resnet-attention-model-for-classifying","slug":"a-resnet-attention-model-for-classifying","title":"A ResNet attention model for classifying mosquitoes from wing‑beating sounds","date":"2022-06-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-audio-strikes-back-boosting","slug":"end-to-end-audio-strikes-back-boosting","title":"End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network","date":"2022-04-25","arxiv_id":"2204.11479","repositories_listed":1,"syntology":null},{"url":"/paper/example-based-explanations-with-adversarial","slug":"example-based-explanations-with-adversarial","title":"Example-based Explanations with Adversarial Attacks for Respiratory Sound Analysis","date":"2022-03-30","arxiv_id":"2203.16141","repositories_listed":1,"syntology":null},{"url":"/paper/auco-resnet-an-end-to-end-network-for-covid","slug":"auco-resnet-an-end-to-end-network-for-covid","title":"AUCO ResNet: an end-to-end network for Covid-19 pre-screening from cough and breath","date":"2022-03-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hts-at-a-hierarchical-token-semantic-audio","slug":"hts-at-a-hierarchical-token-semantic-audio","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","date":"2022-02-02","arxiv_id":"2202.00874","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hts-at-a-hierarchical-token-semantic-audio#ran","syntology_url":"https://syntology.ai/paper/2202.00874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.00874"}},"official":{"repos":["retrocirce/hts-audio-transformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/interpreting-deep-urban-sound-classification","slug":"interpreting-deep-urban-sound-classification","title":"Interpreting deep urban sound classification using Layer-wise Relevance Propagation","date":"2021-11-19","arxiv_id":"2111.10235","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-audio-visual-representation","slug":"self-supervised-audio-visual-representation","title":"Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity","date":"2021-11-09","arxiv_id":"2111.05329","repositories_listed":1,"syntology":null},{"url":"/paper/lungattn-advanced-lung-sound-classification","slug":"lungattn-advanced-lung-sound-classification","title":"LungAttn: advanced lung sound classification using attention mechanism with dual TQWT and triple STFT spectrogram","date":"2021-10-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-visual-domain-transfer-learning-approach","slug":"a-visual-domain-transfer-learning-approach","title":"A Visual Domain Transfer Learning Approach for Heartbeat Sound Classification","date":"2021-07-28","arxiv_id":"2107.13237","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-learning-of-global-and-local-1","slug":"contrastive-learning-of-global-and-local-1","title":"Contrastive Learning of Global-Local Video Representations","date":"2021-04-07","arxiv_id":"2104.05418","repositories_listed":1,"syntology":null},{"url":"/paper/tiny-transformers-for-environmental-sound","slug":"tiny-transformers-for-environmental-sound","title":"Tiny Transformers for Environmental Sound Classification at the Edge","date":"2021-03-22","arxiv_id":"2103.12157","repositories_listed":1,"syntology":null},{"url":"/paper/learning-spectro-temporal-representations-of","slug":"learning-spectro-temporal-representations-of","title":"Learning spectro-temporal representations of complex sounds with parameterized neural networks","date":"2021-03-12","arxiv_id":"2103.07125","repositories_listed":1,"syntology":null},{"url":"/paper/environmental-sound-classification-on-the","slug":"environmental-sound-classification-on-the","title":"Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices","date":"2021-03-05","arxiv_id":"2103.03483","repositories_listed":1,"syntology":null},{"url":"/paper/soundclr-contrastive-learning-of","slug":"soundclr-contrastive-learning-of","title":"SoundCLR: Contrastive Learning of Representations For Improved Environmental Sound Classification","date":"2021-03-02","arxiv_id":"2103.01929","repositories_listed":1,"syntology":null},{"url":"/paper/improving-deep-learning-based-semi-supervised","slug":"improving-deep-learning-based-semi-supervised","title":"Comparison of semi-supervised deep learning algorithms for audio classification","date":"2021-02-16","arxiv_id":"2102.08183","repositories_listed":1,"syntology":null},{"url":"/paper/urban-sound-classification-striving-towards-a","slug":"urban-sound-classification-striving-towards-a","title":"Urban Sound Classification : striving towards a fair comparison","date":"2020-10-22","arxiv_id":"2010.11805","repositories_listed":1,"syntology":null},{"url":"/paper/deep-neural-network-for-respiratory-sound","slug":"deep-neural-network-for-respiratory-sound","title":"Deep Neural Network for Respiratory Sound Classification in Wearable Devices Enabled by Patient Specific Model Tuning","date":"2020-04-16","arxiv_id":"2004.08287","repositories_listed":1,"syntology":null},{"url":"/paper/esresnet-environmental-sound-classification","slug":"esresnet-environmental-sound-classification","title":"ESResNet: Environmental Sound Classification Based on Visual Domain Models","date":"2020-04-15","arxiv_id":"2004.07301","repositories_listed":1,"syntology":null},{"url":"/paper/lungbrn-a-smart-digital-stethoscope-for","slug":"lungbrn-a-smart-digital-stethoscope-for","title":"LungBRN: A Smart Digital Stethoscope for Detecting Respiratory Disease Using bi-ResNet Deep Learning Algorithm","date":"2019-12-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/spectrogram-frame-linear-network-and","slug":"spectrogram-frame-linear-network-and","title":"Spectrogram-frame linear network and continuous frame sequence for bird sound classification","date":"2019-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/urban-sound-tagging-using-convolutional","slug":"urban-sound-tagging-using-convolutional","title":"Urban Sound Tagging using Convolutional Neural Networks","date":"2019-09-27","arxiv_id":"1909.12699","repositories_listed":1,"syntology":null},{"url":"/paper/environmental-sound-classification-on","slug":"environmental-sound-classification-on","title":"Environmental Sound Classification on Microcontrollers using Convolutional Neural Networks","date":"2019-05-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/an-ensemble-of-transfer-semi-supervised-and","slug":"an-ensemble-of-transfer-semi-supervised-and","title":"An Ensemble of Transfer, Semi-supervised and Supervised Learning Methods for Pathological Heart Sound Classification","date":"2018-06-18","arxiv_id":"1806.06506","repositories_listed":1,"syntology":null},{"url":"/paper/utilizing-domain-knowledge-in-end-to-end","slug":"utilizing-domain-knowledge-in-end-to-end","title":"Utilizing Domain Knowledge in End-to-End Audio Processing","date":"2017-12-01","arxiv_id":"1712.00254","repositories_listed":1,"syntology":null},{"url":"/paper/look-listen-and-learn","slug":"look-listen-and-learn","title":"Look, Listen and Learn","date":"2017-05-23","arxiv_id":"1705.08168","repositories_listed":1,"syntology":null},{"url":"/paper/deep-convolutional-neural-networks-and-data-2","slug":"deep-convolutional-neural-networks-and-data-2","title":"Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification","date":"2017-01-23","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/empirical-study-of-drone-sound-detection-in","slug":"empirical-study-of-drone-sound-detection-in","title":"Empirical Study of Drone Sound Detection in Real-Life Environment with Deep Neural Networks","date":"2017-01-20","arxiv_id":"1701.05779","repositories_listed":1,"syntology":null},{"url":null,"slug":"usad-universal-speech-and-audio","title":"USAD: Universal Speech and Audio Representation via Distillation","date":"2025-06-23","arxiv_id":"2506.18843","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-scattering-ai-for-non-invasive","title":"Acoustic scattering AI for non-invasive object classifications: A case study on hair assessment","date":"2025-06-17","arxiv_id":"2506.14148","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangling-dual-encoder-masked-autoencoder","title":"Disentangling Dual-Encoder Masked Autoencoder for Respiratory Sound Classification","date":"2025-06-12","arxiv_id":"2506.10698","repositories_listed":0,"syntology":null},{"url":null,"slug":"mudas-mote-scale-unsupervised-domain","title":"MUDAS: Mote-scale Unsupervised Domain Adaptation in Multi-label Sound Classification","date":"2025-06-12","arxiv_id":"2506.11331","repositories_listed":0,"syntology":null},{"url":null,"slug":"general-purpose-audio-representation-learning","title":"General-purpose audio representation learning for real-world sound scenes","date":"2025-06-01","arxiv_id":"2506.00934","repositories_listed":0,"syntology":null},{"url":null,"slug":"patient-domain-supervised-contrastive","title":"Patient Domain Supervised Contrastive Learning for Lung Sound Classification Using Mobile Phone","date":"2025-05-29","arxiv_id":"2505.23132","repositories_listed":0,"syntology":null},{"url":null,"slug":"tri-mtl-a-triple-multitask-learning-approach","title":"Tri-MTL: A Triple Multitask Learning Approach for Respiratory Disease Diagnosis","date":"2025-05-06","arxiv_id":"2505.06271","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-masked-autoencoders-also-listen-to-birds","title":"Can Masked Autoencoders Also Listen to Birds?","date":"2025-04-17","arxiv_id":"2504.12880","repositories_listed":0,"syntology":null},{"url":null,"slug":"respiratory-inhaler-sound-event","title":"Respiratory Inhaler Sound Event Classification Using Self-Supervised Learning","date":"2025-04-15","arxiv_id":"2504.11246","repositories_listed":0,"syntology":null},{"url":null,"slug":"mind-the-prompt-prompting-strategies-in-audio","title":"Mind the Prompt: Prompting Strategies in Audio Generations for Improving Sound Classification","date":"2025-04-04","arxiv_id":"2504.03329","repositories_listed":0,"syntology":null},{"url":null,"slug":"symbolic-audio-classification-via-modal","title":"Symbolic Audio Classification via Modal Decision Tree Learning","date":"2025-03-21","arxiv_id":"2503.17018","repositories_listed":0,"syntology":null},{"url":null,"slug":"lungmix-a-mixup-based-strategy-for","title":"Lungmix: A Mixup-Based Strategy for Generalization in Respiratory Sound Classification","date":"2024-12-29","arxiv_id":"2501.00064","repositories_listed":0,"syntology":null},{"url":null,"slug":"sound-classification-of-four-insect-classes","title":"Sound Classification of Four Insect Classes","date":"2024-12-16","arxiv_id":"2412.12395","repositories_listed":0,"syntology":null},{"url":null,"slug":"classification-of-adventitious-sounds","title":"Classification of Adventitious Sounds Combining Cochleogram and Vision Transformers","date":"2024-11-08","arxiv_id":"2411.05955","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-detection-and-classification-of","title":"Unsupervised detection and classification of heartbeats using the dissimilarity matrix in PCG signals","date":"2024-11-05","arxiv_id":"2411.03061","repositories_listed":0,"syntology":null},{"url":null,"slug":"echo-environmental-sound-classification-with","title":"ECHO: Environmental Sound Classification with Hierarchical Ontology-guided Semi-Supervised Learning","date":"2024-09-21","arxiv_id":"2409.14043","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalization-in-birdsong-classification","title":"Generalization in birdsong classification: impact of transfer learning methods and dataset characteristics","date":"2024-09-21","arxiv_id":"2409.15383","repositories_listed":0,"syntology":null},{"url":null,"slug":"studying-the-effect-of-audio-filters-in-pre","title":"Studying the Effect of Audio Filters in Pre-Trained Models for Environmental Sound Classification","date":"2024-08-24","arxiv_id":"2408.13644","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-robustness-and-clinical","title":"Improving the Robustness and Clinical Applicability of Automatic Respiratory Sound Classification Using Deep Learning-Based Audio Enhancement: Algorithm Development and Validation","date":"2024-07-18","arxiv_id":"2407.13895","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-enhanced-classification-of-abnormal","title":"Towards Enhanced Classification of Abnormal Lung sound in Multi-breath: A Light Weight Multi-label and Multi-head Attention Classification Method","date":"2024-07-15","arxiv_id":"2407.10828","repositories_listed":0,"syntology":null},{"url":null,"slug":"advanced-framework-for-animal-sound","title":"Advanced Framework for Animal Sound Classification With Features Optimization","date":"2024-07-03","arxiv_id":"2407.03440","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-classification-of-heart-sounds-using","title":"Enhanced Heart Sound Classification Using Mel Frequency Cepstral Coefficients and Comparative Analysis of Single vs. Ensemble Classifier Strategies","date":"2024-06-02","arxiv_id":"2406.00702","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-feature-fusion-network-via","title":"Attention Feature Fusion Network via Knowledge Propagation for Automated Respiratory Sound Classification","date":"2024-05-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"repaugment-input-agnostic-representation","title":"RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification","date":"2024-05-05","arxiv_id":"2405.02996","repositories_listed":0,"syntology":null},{"url":null,"slug":"audioprotopnet-an-interpretable-deep-learning","title":"AudioProtoPNet: An interpretable deep learning model for bird sound classification","date":"2024-04-16","arxiv_id":"2404.10420","repositories_listed":0,"syntology":null},{"url":null,"slug":"classification-of-short-segment-pediatric","title":"Classification of Short Segment Pediatric Heart Sounds Based on a Transformer-Based Convolutional Neural Network","date":"2024-03-30","arxiv_id":"2404.00470","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthesizing-soundscapes-leveraging-text-to","title":"Synthetic training set generation using text-to-audio models for environmental sound classification","date":"2024-03-26","arxiv_id":"2403.17864","repositories_listed":0,"syntology":null},{"url":null,"slug":"tuning-in-analysis-of-audio-classifier","title":"Tuning In: Analysis of Audio Classifier Performance in Clinical Settings with Limited Data","date":"2024-02-07","arxiv_id":"2402.10100","repositories_listed":0,"syntology":null},{"url":null,"slug":"focal-modulation-networks-for-interpretable","title":"Focal Modulation Networks for Interpretable Sound Classification","date":"2024-02-05","arxiv_id":"2402.02754","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-aggregation-in-joint-sound","title":"Feature Aggregation in Joint Sound Classification and Localization Neural Networks","date":"2023-10-29","arxiv_id":"2310.19063","repositories_listed":0,"syntology":null},{"url":null,"slug":"codec-data-augmentation-for-time-domain-heart","title":"Codec Data Augmentation for Time-domain Heart Sound Classification","date":"2023-09-14","arxiv_id":"2309.07466","repositories_listed":0,"syntology":null},{"url":null,"slug":"echovest-real-time-sound-classification-and","title":"EchoVest: Real-Time Sound Classification and Depth Perception Expressed through Transcutaneous Electrical Nerve Stimulation","date":"2023-07-10","arxiv_id":"2307.04604","repositories_listed":0,"syntology":null},{"url":null,"slug":"channel-spatial-based-few-shot-bird-sounds","title":"Channel-Spatial-Based Few-Shot Bird Sound Event Detection","date":"2023-06-18","arxiv_id":"2306.10499","repositories_listed":0,"syntology":null},{"url":null,"slug":"correlation-clustering-of-bird-sounds","title":"Correlation Clustering of Bird Sounds","date":"2023-06-16","arxiv_id":"2306.09906","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-rich-audio-model-inversion-for-data","title":"Feature-Rich Audio Model Inversion for Data-Free Knowledge Distillation Towards General Sound Classification","date":"2023-03-14","arxiv_id":"2303.07643","repositories_listed":0,"syntology":null},{"url":null,"slug":"spectnet-end-to-end-audio-signal","title":"SpectNet : End-to-End Audio Signal Classification Using Learnable Spectrograms","date":"2022-11-17","arxiv_id":"2211.09352","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-impact-of-noise-and","title":"Exploring the Impact of Noise and Degradations on Heart Sound Classification Models","date":"2022-11-14","arxiv_id":"2211.07445","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-semi-supervised-algorithm-for-improving-the","title":"A Semi-Supervised Algorithm for Improving the Consistency of Crowdsourced Datasets: The COVID-19 Case Study on Respiratory Disorder Classification","date":"2022-09-09","arxiv_id":"2209.04360","repositories_listed":0,"syntology":null},{"url":"/paper/sprsound-open-source-sjtu-paediatric","slug":"sprsound-open-source-sjtu-paediatric","title":"SPRSound: Open-Source SJTU Paediatric Respiratory Sound Database","date":"2022-09-07","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/task/sound-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":2,"url":"/task/sound-classification/papers/2","json":"/task/sound-classification/papers/2.json","rows":48},{"order":"ran","page":1,"of":1,"url":"/task/sound-classification/papers/ran/1","json":"/task/sound-classification/papers/ran/1.json","rows":5}],"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":"fe23545c4ae1edc520daa70526c71aaf1f8e342a7cee29abd56ee853fa56c9fc","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}