{"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/acoustic-scene-classification","name":"Acoustic Scene Classification","slug":"acoustic-scene-classification","description_markdown":"The goal of acoustic scene classification is to classify a test recording into one of the provided predefined classes that characterizes the environment in which it was recorded.\r\n\r\nSource: [DCASE 2019](http://dcase.community/challenge2019/task-acoustic-scene-classification)\r\nSource: [DCASE 2018](https://dcase.community/challenge2018/task-acoustic-scene-classification)","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":132,"papers_with_code":42,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":10,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/acoustic-scene-classification-on-cochlscene","slug":"acoustic-scene-classification-on-cochlscene","dataset":"CochlScene","dataset_url":"/dataset/cochlscene","rows_in_archive":2,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"Audio Flamingo","paper_title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","paper_url":"/paper/audio-flamingo-a-novel-audio-language-model","paper_date":"2024-02-02","arxiv_id":"2402.01831","code_links":[{"title":"NVIDIA/audio-flamingo","url":"https://github.com/NVIDIA/audio-flamingo"}],"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/audio-flamingo-a-novel-audio-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.01831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01831"}},"official":{"repos":["NVIDIA/audio-flamingo"],"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":["unlocated"]}}}},{"leaderboard":"/sota/acoustic-scene-classification-on-dcase-2019","slug":"acoustic-scene-classification-on-dcase-2019","dataset":"DCASE 2019 Mobile","dataset_url":"/dataset/dcase-2019-mobile","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Basic + Spectrum Correction","paper_title":"Spectrum Correction: Acoustic Scene Classification with Mismatched Recording Devices","paper_url":"/paper/spectrum-correction-acoustic-scene","paper_date":"2021-05-25","arxiv_id":"2105.11856","code_links":[{"title":"SRPOL-AUI/spectrum-correction","url":"https://github.com/SRPOL-AUI/spectrum-correction"}],"syntology":null}},{"leaderboard":"/sota/acoustic-scene-classification-on-tau-urban","slug":"acoustic-scene-classification-on-tau-urban","dataset":"TAU Urban Acoustic Scenes 2019","dataset_url":"/dataset/tau-urban-acoustic-scenes-2019","rows_in_archive":1,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"Two-stage ensemble system","paper_title":"A Two-Stage Approach to Device-Robust Acoustic Scene Classification","paper_url":"/paper/a-two-stage-approach-to-device-robust","paper_date":"2020-11-03","arxiv_id":"2011.01447","code_links":[{"title":"MihawkHu/DCASE2020_task1","url":"https://github.com/MihawkHu/DCASE2020_task1"}],"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/a-two-stage-approach-to-device-robust#ran","syntology_url":"https://syntology.ai/paper/2011.01447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.01447"}},"official":{"repos":["MihawkHu/DCASE2020_task1"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/acoustic-scene-classification-on-tut-acoustic","slug":"acoustic-scene-classification-on-tut-acoustic","dataset":"TUT Acoustic Scenes 2017","dataset_url":"/dataset/tut-acoustic-scenes-2017","rows_in_archive":1,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"Qwen-Audio","paper_title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","paper_url":"/paper/qwen-audio-advancing-universal-audio","paper_date":"2023-11-14","arxiv_id":"2311.07919","code_links":[{"title":"alibaba-damo-academy/FunASR","url":"https://github.com/alibaba-damo-academy/FunASR"},{"title":"qwenlm/qwen-audio","url":"https://github.com/qwenlm/qwen-audio"}],"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"]}}}},{"leaderboard":"/sota/acoustic-scene-classification-on-tut-urban","slug":"acoustic-scene-classification-on-tut-urban","dataset":"TUT Urban Acoustic Scenes 2018","dataset_url":"/dataset/dcase-2018-task-1a","rows_in_archive":1,"metrics":["Acc"],"first_row_in_archive_order":{"model":"ERGL: event relational graph representation learning","paper_title":"Multi-dimensional Edge-based Audio Event Relational Graph Representation Learning for Acoustic Scene Classification","paper_url":"/paper/multi-dimensional-edge-based-audio-event","paper_date":"2022-10-27","arxiv_id":"2210.15366","code_links":[{"title":"yuanbo2020/ergl","url":"https://github.com/yuanbo2020/ergl"}],"syntology":null}}],"datasets":[{"url":"/dataset/mtg-jamendo","name":"MTG-Jamendo","full_name":null,"num_papers_in_archive":39},{"url":"/dataset/dcase-2016","name":"DCASE 2016","full_name":"DCASE 2016","num_papers_in_archive":31},{"url":"/dataset/tau-urban-acoustic-scenes-2019","name":"TAU Urban Acoustic Scenes 2019","full_name":"TAU Urban Acoustic Scenes 2019","num_papers_in_archive":14},{"url":"/dataset/tut-acoustic-scenes-2017","name":"TUT Acoustic Scenes 2017","full_name":"TUT Acoustic Scenes 2017","num_papers_in_archive":13},{"url":"/dataset/dcase-2013","name":"DCASE 2013","full_name":"DCASE 2013","num_papers_in_archive":11},{"url":"/dataset/cochlscene","name":"CochlScene","full_name":"","num_papers_in_archive":7},{"url":"/dataset/dcase-2019-mobile","name":"DCASE 2019 Mobile","full_name":"TAU Urban Acoustic Scenes 2019 Mobile","num_papers_in_archive":5},{"url":"/dataset/litis-rouen","name":"LITIS Rouen","full_name":"LITIS Rouen","num_papers_in_archive":3},{"url":"/dataset/dcase-2018-task-1a","name":"TUT Urban Acoustic Scenes 2018","full_name":"","num_papers_in_archive":2},{"url":"/dataset/tut-sound-events-2018","name":"TUT Sound Events 2018","full_name":"TUT Sound Events 2018","num_papers_in_archive":0}],"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":132,"of_with_code":42,"tagged_in_all":132,"counts":{"archive_papers_tagged":132,"with_a_code_link":42,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":132,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/the-receptive-field-as-a-regularizer-in-deep","slug":"the-receptive-field-as-a-regularizer-in-deep","title":"The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification","date":"2019-07-03","arxiv_id":"1907.01803","repositories_listed":3,"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/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/seld-tcn-sound-event-localization-detection","slug":"seld-tcn-sound-event-localization-detection","title":"SELD-TCN: Sound Event Localization & Detection via Temporal Convolutional Networks","date":"2020-03-03","arxiv_id":"2003.01609","repositories_listed":2,"syntology":null},{"url":"/paper/receptive-field-regularized-cnn-variants-for","slug":"receptive-field-regularized-cnn-variants-for","title":"Receptive-field-regularized CNN variants for acoustic scene classification","date":"2019-09-05","arxiv_id":"1909.02859","repositories_listed":2,"syntology":null},{"url":"/paper/training-neural-audio-classifiers-with-few","slug":"training-neural-audio-classifiers-with-few","title":"Training neural audio classifiers with few data","date":"2018-10-24","arxiv_id":"1810.10274","repositories_listed":2,"syntology":null},{"url":"/paper/a-multi-device-dataset-for-urban-acoustic","slug":"a-multi-device-dataset-for-urban-acoustic","title":"A multi-device dataset for urban acoustic scene classification","date":"2018-07-25","arxiv_id":"1807.09840","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/a-multi-device-dataset-for-urban-acoustic#ran","syntology_url":"https://syntology.ai/paper/1807.09840","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.09840"}},"official":null}},{"url":"/paper/a-simple-fusion-of-deep-and-shallow-learning","slug":"a-simple-fusion-of-deep-and-shallow-learning","title":"A Simple Fusion of Deep and Shallow Learning for Acoustic Scene Classification","date":"2018-06-19","arxiv_id":"1806.07506","repositories_listed":2,"syntology":null},{"url":"/paper/low-complexity-acoustic-scene-classification-4","slug":"low-complexity-acoustic-scene-classification-4","title":"Low-Complexity Acoustic Scene Classification with Device Information in the DCASE 2025 Challenge","date":"2025-05-03","arxiv_id":"2505.01747","repositories_listed":1,"syntology":null},{"url":"/paper/low-complexity-acoustic-scene-classification-3","slug":"low-complexity-acoustic-scene-classification-3","title":"Low-Complexity Acoustic Scene Classification Using Parallel Attention-Convolution Network","date":"2024-06-12","arxiv_id":"2406.08119","repositories_listed":1,"syntology":null},{"url":"/paper/data-efficient-low-complexity-acoustic-scene","slug":"data-efficient-low-complexity-acoustic-scene","title":"Data-Efficient Low-Complexity Acoustic Scene Classification in the DCASE 2024 Challenge","date":"2024-05-16","arxiv_id":"2405.10018","repositories_listed":1,"syntology":null},{"url":"/paper/description-on-ieee-icme-2024-grand-challenge","slug":"description-on-ieee-icme-2024-grand-challenge","title":"Description on IEEE ICME 2024 Grand Challenge: Semi-supervised Acoustic Scene Classification under Domain Shift","date":"2024-02-05","arxiv_id":"2402.02694","repositories_listed":1,"syntology":null},{"url":"/paper/audio-flamingo-a-novel-audio-language-model","slug":"audio-flamingo-a-novel-audio-language-model","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","date":"2024-02-02","arxiv_id":"2402.01831","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/audio-flamingo-a-novel-audio-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.01831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01831"}},"official":{"repos":["NVIDIA/audio-flamingo"],"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":["unlocated"]}}},{"url":"/paper/audiolog-llms-powered-long-audio-logging-with","slug":"audiolog-llms-powered-long-audio-logging-with","title":"AudioLog: LLMs-Powered Long Audio Logging with Hybrid Token-Semantic Contrastive Learning","date":"2023-11-21","arxiv_id":"2311.12371","repositories_listed":1,"syntology":null},{"url":"/paper/audio-event-relational-graph-representation","slug":"audio-event-relational-graph-representation","title":"Audio Event-Relational Graph Representation Learning for Acoustic Scene Classification","date":"2023-10-05","arxiv_id":"2310.03889","repositories_listed":1,"syntology":null},{"url":"/paper/bringing-the-discussion-of-minima-sharpness","slug":"bringing-the-discussion-of-minima-sharpness","title":"Bringing the Discussion of Minima Sharpness to the Audio Domain: a Filter-Normalised Evaluation for Acoustic Scene Classification","date":"2023-09-28","arxiv_id":"2309.16369","repositories_listed":1,"syntology":null},{"url":"/paper/domain-information-control-at-inference-time","slug":"domain-information-control-at-inference-time","title":"Domain Information Control at Inference Time for Acoustic Scene Classification","date":"2023-06-13","arxiv_id":"2306.08010","repositories_listed":1,"syntology":null},{"url":"/paper/device-robust-acoustic-scene-classification-1","slug":"device-robust-acoustic-scene-classification-1","title":"Device-Robust Acoustic Scene Classification via Impulse Response Augmentation","date":"2023-05-12","arxiv_id":"2305.07499","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-improvement-of-audio-text-cross","slug":"unsupervised-improvement-of-audio-text-cross","title":"Unsupervised Improvement of Audio-Text Cross-Modal Representations","date":"2023-05-03","arxiv_id":"2305.01864","repositories_listed":1,"syntology":null},{"url":"/paper/cochlscene-acquisition-of-acoustic-scene-data","slug":"cochlscene-acquisition-of-acoustic-scene-data","title":"CochlScene: Acquisition of acoustic scene data using crowdsourcing","date":"2022-11-04","arxiv_id":"2211.02289","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-similarity-based-passive-filter","slug":"efficient-similarity-based-passive-filter","title":"Efficient Similarity-based Passive Filter Pruning for Compressing CNNs","date":"2022-10-27","arxiv_id":"2210.17416","repositories_listed":1,"syntology":null},{"url":"/paper/multi-dimensional-edge-based-audio-event","slug":"multi-dimensional-edge-based-audio-event","title":"Multi-dimensional Edge-based Audio Event Relational Graph Representation Learning for Acoustic Scene Classification","date":"2022-10-27","arxiv_id":"2210.15366","repositories_listed":1,"syntology":null},{"url":"/paper/a-passive-similarity-based-cnn-filter-pruning","slug":"a-passive-similarity-based-cnn-filter-pruning","title":"A Passive Similarity based CNN Filter Pruning for Efficient Acoustic Scene Classification","date":"2022-03-29","arxiv_id":"2203.15751","repositories_listed":1,"syntology":null},{"url":"/paper/acoustic-scene-classification-using-auditory","slug":"acoustic-scene-classification-using-auditory","title":"Acoustic scene classification using auditory datasets","date":"2021-12-26","arxiv_id":"2112.13450","repositories_listed":1,"syntology":null},{"url":"/paper/towards-audio-domain-adaptation-for-acoustic","slug":"towards-audio-domain-adaptation-for-acoustic","title":"Towards Audio Domain Adaptation for Acoustic Scene Classification using Disentanglement Learning","date":"2021-10-26","arxiv_id":"2110.13586","repositories_listed":1,"syntology":null},{"url":"/paper/a-variational-bayesian-approach-to-learning","slug":"a-variational-bayesian-approach-to-learning","title":"A Variational Bayesian Approach to Learning Latent Variables for Acoustic Knowledge Transfer","date":"2021-10-16","arxiv_id":"2110.08598","repositories_listed":1,"syntology":null},{"url":"/paper/low-complexity-acoustic-scene-classification","slug":"low-complexity-acoustic-scene-classification","title":"Low-complexity acoustic scene classification for multi-device audio: analysis of DCASE 2021 Challenge systems","date":"2021-05-28","arxiv_id":"2105.13734","repositories_listed":1,"syntology":null},{"url":"/paper/receptive-field-regularization-techniques-for","slug":"receptive-field-regularization-techniques-for","title":"Receptive Field Regularization Techniques for Audio Classification and Tagging with Deep Convolutional Neural Networks","date":"2021-05-26","arxiv_id":"2105.12395","repositories_listed":1,"syntology":null},{"url":"/paper/spectrum-correction-acoustic-scene","slug":"spectrum-correction-acoustic-scene","title":"Spectrum Correction: Acoustic Scene Classification with Mismatched Recording Devices","date":"2021-05-25","arxiv_id":"2105.11856","repositories_listed":1,"syntology":null},{"url":"/paper/low-complexity-models-for-acoustic-scene","slug":"low-complexity-models-for-acoustic-scene","title":"Low-Complexity Models for Acoustic Scene Classification Based on Receptive Field Regularization and Frequency Damping","date":"2020-11-05","arxiv_id":"2011.02955","repositories_listed":1,"syntology":null},{"url":"/paper/a-two-stage-approach-to-device-robust","slug":"a-two-stage-approach-to-device-robust","title":"A Two-Stage Approach to Device-Robust Acoustic Scene Classification","date":"2020-11-03","arxiv_id":"2011.01447","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/a-two-stage-approach-to-device-robust#ran","syntology_url":"https://syntology.ai/paper/2011.01447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.01447"}},"official":{"repos":["MihawkHu/DCASE2020_task1"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dcasenet-a-joint-pre-trained-deep-neural","slug":"dcasenet-a-joint-pre-trained-deep-neural","title":"DCASENET: A joint pre-trained deep neural network for detecting and classifying acoustic scenes and events","date":"2020-09-21","arxiv_id":"2009.09642","repositories_listed":1,"syntology":null},{"url":"/paper/citisen-a-deep-learning-based-speech-signal","slug":"citisen-a-deep-learning-based-speech-signal","title":"CITISEN: A Deep Learning-Based Speech Signal-Processing Mobile Application","date":"2020-08-21","arxiv_id":"2008.09264","repositories_listed":1,"syntology":null},{"url":"/paper/device-robust-acoustic-scene-classification","slug":"device-robust-acoustic-scene-classification","title":"Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation","date":"2020-07-16","arxiv_id":"2007.08389","repositories_listed":1,"syntology":null},{"url":"/paper/emotion-and-theme-recognition-in-music-with","slug":"emotion-and-theme-recognition-in-music-with","title":"Emotion and Theme Recognition in Music with Frequency-Aware RF-Regularized CNNs","date":"2019-10-28","arxiv_id":"1911.05833","repositories_listed":1,"syntology":null},{"url":"/paper/acoustic-scene-analysis-with-multi-head","slug":"acoustic-scene-analysis-with-multi-head","title":"Acoustic scene analysis with multi-head attention networks","date":"2019-09-16","arxiv_id":"1909.08961","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-parallel-audio-recordings-to","slug":"exploiting-parallel-audio-recordings-to","title":"Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification","date":"2019-09-04","arxiv_id":"1909.02869","repositories_listed":1,"syntology":null},{"url":"/paper/city-classification-from-multiple-real-world","slug":"city-classification-from-multiple-real-world","title":"City classification from multiple real-world sound scenes","date":"2019-07-29","arxiv_id":"1905.00979","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-adversarial-domain-adaptation-1","slug":"unsupervised-adversarial-domain-adaptation-1","title":"Unsupervised Adversarial Domain Adaptation Based On The Wasserstein Distance For Acoustic Scene Classification","date":"2019-04-24","arxiv_id":"1904.10678","repositories_listed":1,"syntology":null},{"url":"/paper/acoustic-scene-classification-by-implicitly","slug":"acoustic-scene-classification-by-implicitly","title":"Acoustic Scene Classification by Implicitly Identifying Distinct Sound Events","date":"2019-04-10","arxiv_id":"1904.05204","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-adversarial-domain-adaptation","slug":"unsupervised-adversarial-domain-adaptation","title":"Unsupervised adversarial domain adaptation for acoustic scene classification","date":"2018-08-17","arxiv_id":"1808.05777","repositories_listed":1,"syntology":null},{"url":"/paper/classifying-variable-length-audio-files-with","slug":"classifying-variable-length-audio-files-with","title":"Classifying Variable-Length Audio Files with All-Convolutional Networks and Masked Global Pooling","date":"2016-07-11","arxiv_id":"1607.02857","repositories_listed":1,"syntology":null},{"url":null,"slug":"city2scene-improving-acoustic-scene","title":"Improving Acoustic Scene Classification with City Features","date":"2025-03-21","arxiv_id":"2503.16862","repositories_listed":0,"syntology":null},{"url":null,"slug":"creating-a-good-teacher-for-knowledge","title":"Creating a Good Teacher for Knowledge Distillation in Acoustic Scene Classification","date":"2025-03-14","arxiv_id":"2503.11363","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-bayesian-adaptive-learning-of","title":"Variational Bayesian Adaptive Learning of Deep Latent Variables for Acoustic Knowledge Transfer","date":"2025-01-26","arxiv_id":"2501.15496","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-enhanced-transformers-for-robust","title":"Quantum-Enhanced Transformers for Robust Acoustic Scene Classification in IoT Environments","date":"2025-01-16","arxiv_id":"2501.09394","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-acoustic-scene-classification-in","title":"Improving Acoustic Scene Classification in Low-Resource Conditions","date":"2024-12-30","arxiv_id":"2412.20722","repositories_listed":0,"syntology":null},{"url":null,"slug":"neurobench-dcase-2020-acoustic-scene","title":"Neurobench: DCASE 2020 Acoustic Scene Classification benchmark on XyloAudio 2","date":"2024-10-31","arxiv_id":"2410.23776","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-efficient-acoustic-scene-classification","title":"Data Efficient Acoustic Scene Classification using Teacher-Informed Confusing Class Instruction","date":"2024-09-18","arxiv_id":"2409.11964","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-enhancement-for-computer-audition-an","title":"Audio Enhancement for Computer Audition -- An Iterative Training Paradigm Using Sample Importance","date":"2024-08-12","arxiv_id":"2408.06264","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-domain-incremental-learning-approach","title":"Online Domain-Incremental Learning Approach to Classify Acoustic Scenes in All Locations","date":"2024-06-19","arxiv_id":"2406.13386","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-space-separable-distillation-for","title":"Deep Space Separable Distillation for Lightweight Acoustic Scene Classification","date":"2024-05-06","arxiv_id":"2405.03567","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-toolchain-for-comprehensive-audio-video","title":"A Toolchain for Comprehensive Audio/Video Analysis Using Deep Learning Based Multimodal Approach (A use case of riot or violent context detection)","date":"2024-05-02","arxiv_id":"2407.03110","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-adaptive-learning-to-latent","title":"Bayesian adaptive learning to latent variables via Variational Bayes and Maximum a Posteriori","date":"2024-01-24","arxiv_id":"2401.13766","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-frequency-wise-normalizations-for-better","title":"On Frequency-Wise Normalizations for Better Recording Device Generalization in Audio Spectrogram Transformers","date":"2023-06-20","arxiv_id":"2306.11764","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-scene-clustering-using-joint","title":"Acoustic Scene Clustering Using Joint Optimization of Deep Embedding Learning and Clustering Iteration","date":"2023-06-09","arxiv_id":"2306.05621","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-complexity-acoustic-scene-classification-2","title":"Low-Complexity Acoustic Scene Classification Using Data Augmentation and Lightweight ResNet","date":"2023-06-03","arxiv_id":"2306.02054","repositories_listed":0,"syntology":null},{"url":null,"slug":"decor-defy-knowledge-forgetting-by-predicting","title":"DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codes","date":"2023-05-29","arxiv_id":"2305.18441","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-complexity-deep-learning-frameworks-for-1","title":"Low-complexity deep learning frameworks for acoustic scene classification using teacher-student scheme and multiple spectrograms","date":"2023-05-16","arxiv_id":"2305.09463","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-audio-cnns-with-graph-centrality","title":"Compressing audio CNNs with graph centrality based filter pruning","date":"2023-05-05","arxiv_id":"2305.03391","repositories_listed":0,"syntology":null},{"url":null,"slug":"incremental-learning-of-acoustic-scenes-and","title":"Incremental Learning of Acoustic Scenes and Sound Events","date":"2023-02-28","arxiv_id":"2302.14815","repositories_listed":0,"syntology":null},{"url":null,"slug":"short-term-memory-convolutions","title":"Short-Term Memory Convolutions","date":"2023-02-08","arxiv_id":"2302.04331","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":"robust-general-and-low-complexity-acoustic","title":"Robust, General, and Low Complexity Acoustic Scene Classification Systems and An Effective Visualization for Presenting a Sound Scene Context","date":"2022-10-16","arxiv_id":"2210.08610","repositories_listed":0,"syntology":null},{"url":null,"slug":"binaural-signal-representations-for-joint","title":"Binaural Signal Representations for Joint Sound Event Detection and Acoustic Scene Classification","date":"2022-09-13","arxiv_id":"2209.05900","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-complexity-cnns-for-acoustic-scene-1","title":"Low-complexity CNNs for Acoustic Scene Classification","date":"2022-08-02","arxiv_id":"2208.01555","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-complexity-cnns-for-acoustic-scene","title":"Low-complexity CNNs for Acoustic Scene Classification","date":"2022-07-23","arxiv_id":"2207.11529","repositories_listed":0,"syntology":null},{"url":null,"slug":"difference-in-euclidean-norm-can-cause","title":"$L_2$BN: Enhancing Batch Normalization by Equalizing the $L_2$ Norms of Features","date":"2022-07-06","arxiv_id":"2207.02625","repositories_listed":0,"syntology":null},{"url":null,"slug":"qti-submission-to-dcase-2021-residual","title":"QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design","date":"2022-06-28","arxiv_id":"2206.13909","repositories_listed":0,"syntology":null},{"url":null,"slug":"impact-of-acoustic-event-tagging-on-scene","title":"Impact of Acoustic Event Tagging on Scene Classification in a Multi-Task Learning Framework","date":"2022-06-27","arxiv_id":"2206.13476","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-generalization-with-relaxed-instance","title":"Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification","date":"2022-06-24","arxiv_id":"2206.12513","repositories_listed":0,"syntology":null},{"url":null,"slug":"dcase-2022-comparative-analysis-of-cnns-for","title":"DCASE 2022: Comparative Analysis Of CNNs For Acoustic Scene Classification Under Low-Complexity Considerations","date":"2022-06-16","arxiv_id":"2206.08007","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-complexity-deep-learning-frameworks-for","title":"Low-complexity deep learning frameworks for acoustic scene classification","date":"2022-06-13","arxiv_id":"2206.06057","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-complexity-acoustic-scene-classification-1","title":"Low-complexity acoustic scene classification in DCASE 2022 Challenge","date":"2022-06-08","arxiv_id":"2206.03835","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-learning-of-audio-1","title":"Self-supervised Learning of Audio Representations from Audio-Visual Data using Spatial Alignment","date":"2022-06-02","arxiv_id":"2206.00970","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-on-approaches-to-acoustic","title":"A Comparative Study on Approaches to Acoustic Scene Classification using CNNs","date":"2022-04-26","arxiv_id":"2204.12177","repositories_listed":0,"syntology":null},{"url":null,"slug":"1-d-cnn-based-acoustic-scene-classification","title":"1-D CNN based Acoustic Scene Classification via Reducing Layer-wise Dimensionality","date":"2022-03-31","arxiv_id":"2204.00555","repositories_listed":0,"syntology":null},{"url":null,"slug":"wider-or-deeper-neural-network-architecture","title":"Wider or Deeper Neural Network Architecture for Acoustic Scene Classification with Mismatched Recording Devices","date":"2022-03-23","arxiv_id":"2203.12314","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-squeeze-and-excitation-and-transformer","title":"A Squeeze-and-Excitation and Transformer based Cross-task System for Environmental Sound Recognition","date":"2022-03-16","arxiv_id":"2203.08350","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-neural-decision-forest-for-acoustic","title":"Deep Neural Decision Forest for Acoustic Scene Classification","date":"2022-03-07","arxiv_id":"2203.03436","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-effect-of-coding-artifacts-on-acoustic","title":"On The Effect Of Coding Artifacts On Acoustic Scene Classification","date":"2021-12-09","arxiv_id":"2112.04841","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-generalization-on-efficient-acoustic","title":"Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization","date":"2021-11-12","arxiv_id":"2111.06531","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-domain-adaptation-with-paired","title":"Adversarial Domain Adaptation with Paired Examples for Acoustic Scene Classification on Different Recording Devices","date":"2021-10-18","arxiv_id":"2110.09598","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-evaluation-of-data-augmentation-methods","title":"An evaluation of data augmentation methods for sound scene geotagging","date":"2021-10-09","arxiv_id":"2110.04585","repositories_listed":0,"syntology":null},{"url":null,"slug":"visually-exploring-multi-purpose-audio-data","title":"Visually Exploring Multi-Purpose Audio Data","date":"2021-10-09","arxiv_id":"2110.04584","repositories_listed":0,"syntology":null},{"url":null,"slug":"fairness-and-underspecification-in-acoustic","title":"Fairness and underspecification in acoustic scene classification: The case for disaggregated evaluations","date":"2021-10-04","arxiv_id":"2110.01506","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-robust-domain-generalization-in-2d","title":"Towards Robust Domain Generalization in 2D Neural Audio Processing","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-feature-learning-on-long-duration","title":"Robust Feature Learning on Long-Duration Sounds for Acoustic Scene Classification","date":"2021-08-11","arxiv_id":"2108.05008","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-acoustic-scene-classification-in-the","title":"Robust Acoustic Scene Classification in the Presence of Active Foreground Speech","date":"2021-08-02","arxiv_id":"2108.00912","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-1a-dcase-2021-acoustic-scene","title":"Task 1A DCASE 2021: Acoustic Scene Classification with mismatch-devices using squeeze-excitation technique and low-complexity constraint","date":"2021-07-30","arxiv_id":"2107.14658","repositories_listed":0,"syntology":null},{"url":null,"slug":"over-parameterization-and-generalization-in","title":"Over-Parameterization and Generalization in Audio Classification","date":"2021-07-19","arxiv_id":"2107.08933","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-lottery-ticket-hypothesis-framework-for-low","title":"A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classification","date":"2021-07-03","arxiv_id":"2107.01461","repositories_listed":0,"syntology":null},{"url":null,"slug":"attentive-max-feature-map-for-acoustic-scene","title":"Attentive max feature map and joint training for acoustic scene classification","date":"2021-04-15","arxiv_id":"2104.07213","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-analysis-of-state-of-the-art-activation","title":"An Analysis of State-of-the-art Activation Functions For Supervised Deep Neural Network","date":"2021-04-05","arxiv_id":"2104.02523","repositories_listed":0,"syntology":null},{"url":null,"slug":"specaugment-a-hidden-space-data-augmentation","title":"SpecAugment++: A Hidden Space Data Augmentation Method for Acoustic Scene Classification","date":"2021-03-31","arxiv_id":"2103.16858","repositories_listed":0,"syntology":null},{"url":null,"slug":"environmental-sound-analysis-with-mixup-based","title":"Environmental sound analysis with mixup based multitask learning and cross-task fusion","date":"2021-03-30","arxiv_id":"2103.16079","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-open-set-acoustic-scene","title":"Deep Learning Based Open Set Acoustic Scene Classification","date":"2020-08-17","arxiv_id":"2008.07247","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-acoustic-segment-model-based-segment-unit","title":"An Acoustic Segment Model Based Segment Unit Selection Approach to Acoustic Scene Classification with Partial Utterances","date":"2020-07-31","arxiv_id":"2008.00107","repositories_listed":0,"syntology":null},{"url":null,"slug":"relational-teacher-student-learning-with","title":"Relational Teacher Student Learning with Neural Label Embedding for Device Adaptation in Acoustic Scene Classification","date":"2020-07-31","arxiv_id":"2008.00110","repositories_listed":0,"syntology":null},{"url":null,"slug":"dd-cnn-depthwise-disout-convolutional-neural","title":"DD-CNN: Depthwise Disout Convolutional Neural Network for Low-complexity Acoustic Scene Classification","date":"2020-07-25","arxiv_id":"2007.12864","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/acoustic-scene-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/acoustic-scene-classification/papers/2","json":"/task/acoustic-scene-classification/papers/2.json","rows":32},{"order":"ran","page":1,"of":1,"url":"/task/acoustic-scene-classification/papers/ran/1","json":"/task/acoustic-scene-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":"f45bd625293ee2d508bdcea6dd5020336920ea38ae46f0d62e9e5ac2cd6a9e5a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}