{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/a-two-stage-approach-to-device-robust","title":"A Two-Stage Approach to Device-Robust Acoustic Scene Classification","arxiv_id":"2011.01447","date":"2020-11-03","proceeding":null,"authors":["Hu Hu","Chao-Han Huck Yang","Xianjun Xia","Xue Bai","Xin Tang","Yajian Wang","Shutong Niu","Li Chai","Juanjuan Li","Hongning Zhu","Feng Bao","Yuanjun Zhao","Sabato Marco Siniscalchi","Yannan Wang","Jun Du","Chin-Hui Lee"],"abstract":"To improve device robustness, a highly desirable key feature of a competitive data-driven acoustic scene classification (ASC) system, a novel two-stage system based on fully convolutional neural networks (CNNs) is proposed. Our two-stage system leverages on an ad-hoc score combination based on two CNN classifiers: (i) the first CNN classifies acoustic inputs into one of three broad classes, and (ii) the second CNN classifies the same inputs into one of ten finer-grained classes. Three different CNN architectures are explored to implement the two-stage classifiers, and a frequency sub-sampling scheme is investigated. Moreover, novel data augmentation schemes for ASC are also investigated. Evaluated on DCASE 2020 Task 1a, our results show that the proposed ASC system attains a state-of-the-art accuracy on the development set, where our best system, a two-stage fusion of CNN ensembles, delivers a 81.9% average accuracy among multi-device test data, and it obtains a significant improvement on unseen devices. Finally, neural saliency analysis with class activation mapping (CAM) gives new insights on the patterns learnt by our models.","url_abs":"https://arxiv.org/abs/2011.01447v1","url_pdf":"https://arxiv.org/pdf/2011.01447v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-two-stage-approach-to-device-robust","repo_url":"https://github.com/MihawkHu/DCASE2020_task1","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"acoustic-scene-classification","task_name":"Acoustic Scene Classification"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"scene-classification","task_name":"Scene Classification"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/acoustic-scene-classification-on-tau-urban","task":"Acoustic Scene Classification","dataset":"TAU Urban Acoustic Scenes 2019","model":"Two-stage ensemble system","rank_in_archive_order":1,"of":1,"metrics":{"1:1 Accuracy":"81.9"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.01447","atlas_url":"https://app.syntology.ai/?focus=2011.01447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.01447"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MihawkHu/DCASE2020_task1","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":10,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"b7b59b8162d03a3f","entry":"My_freq_split1","repo":"MihawkHu/DCASE2020_task1","repo_kind":"official","path":"other_TF2_format_pretrained/resnet.py","file_url":"https://github.com/MihawkHu/DCASE2020_task1/blob/HEAD/other_TF2_format_pretrained/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b7b59b8162d03a3f"}},{"code_sha256_prefix":"6d7713d3d9944832","entry":"channel_attention","repo":"MihawkHu/DCASE2020_task1","repo_kind":"official","path":"other_TF2_format_pretrained/attention_layer.py","file_url":"https://github.com/MihawkHu/DCASE2020_task1/blob/HEAD/other_TF2_format_pretrained/attention_layer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6d7713d3d9944832"}},{"code_sha256_prefix":"dc9e7eb5bd140a8c","entry":"cmvn","repo":"MihawkHu/DCASE2020_task1","repo_kind":"official","path":"task1b/funcs.py","file_url":"https://github.com/MihawkHu/DCASE2020_task1/blob/HEAD/task1b/funcs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dc9e7eb5bd140a8c"}},{"code_sha256_prefix":"e8e40a5d7c8a914b","entry":"conv_layer1","repo":"MihawkHu/DCASE2020_task1","repo_kind":"official","path":"other_TF2_format_pretrained/fcnn_att.py","file_url":"https://github.com/MihawkHu/DCASE2020_task1/blob/HEAD/other_TF2_format_pretrained/fcnn_att.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e8e40a5d7c8a914b"}},{"code_sha256_prefix":"7a928b2854b78f59","entry":"freq_split1","repo":"MihawkHu/DCASE2020_task1","repo_kind":"official","path":"other_TF2_format_pretrained/mobnet.py","file_url":"https://github.com/MihawkHu/DCASE2020_task1/blob/HEAD/other_TF2_format_pretrained/mobnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7a928b2854b78f59"}},{"code_sha256_prefix":"e91b10240378b5b3","entry":"frequency_masking","repo":"MihawkHu/DCASE2020_task1","repo_kind":"official","path":"task1b/funcs.py","file_url":"https://github.com/MihawkHu/DCASE2020_task1/blob/HEAD/task1b/funcs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e91b10240378b5b3"}},{"code_sha256_prefix":"9938cdab9fb51473","entry":"pad_depth","repo":"MihawkHu/DCASE2020_task1","repo_kind":"official","path":"other_TF2_format_pretrained/mobnet.py","file_url":"https://github.com/MihawkHu/DCASE2020_task1/blob/HEAD/other_TF2_format_pretrained/mobnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9938cdab9fb51473"}},{"code_sha256_prefix":"12cf81ec779a163f","entry":"relu6","repo":"MihawkHu/DCASE2020_task1","repo_kind":"official","path":"other_TF2_format_pretrained/fcnn_att.py","file_url":"https://github.com/MihawkHu/DCASE2020_task1/blob/HEAD/other_TF2_format_pretrained/fcnn_att.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"12cf81ec779a163f"}},{"code_sha256_prefix":"c27af96c652b89af","entry":"resnet_layer","repo":"MihawkHu/DCASE2020_task1","repo_kind":"official","path":"other_TF2_format_pretrained/mobnet.py","file_url":"https://github.com/MihawkHu/DCASE2020_task1/blob/HEAD/other_TF2_format_pretrained/mobnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c27af96c652b89af"}},{"code_sha256_prefix":"7e6103127d4b6834","entry":"time_masking","repo":"MihawkHu/DCASE2020_task1","repo_kind":"official","path":"task1b/funcs.py","file_url":"https://github.com/MihawkHu/DCASE2020_task1/blob/HEAD/task1b/funcs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7e6103127d4b6834"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}