{"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/multi-level-attention-model-for-weakly","title":"Multi-level Attention Model for Weakly Supervised Audio Classification","arxiv_id":"1803.02353","date":"2018-03-06","proceeding":null,"authors":["Changsong Yu","Karim Said Barsim","Qiuqiang Kong","Bin Yang"],"abstract":"In this paper, we propose a multi-level attention model to solve the weakly\nlabelled audio classification problem. The objective of audio classification is\nto predict the presence or absence of audio events in an audio clip. Recently,\nGoogle published a large scale weakly labelled dataset called Audio Set, where\neach audio clip contains only the presence or absence of the audio events,\nwithout the onset and offset time of the audio events. Our multi-level\nattention model is an extension to the previously proposed single-level\nattention model. It consists of several attention modules applied on\nintermediate neural network layers. The output of these attention modules are\nconcatenated to a vector followed by a multi-label classifier to make the final\nprediction of each class. Experiments shown that our model achieves a mean\naverage precision (mAP) of 0.360, outperforms the state-of-the-art single-level\nattention model of 0.327 and Google baseline of 0.314.","url_abs":"http://arxiv.org/abs/1803.02353v1","url_pdf":"http://arxiv.org/pdf/1803.02353v1.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":"multi-level-attention-model-for-weakly","repo_url":"https://github.com/IBM/MAX-Audio-Classifier","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multi-level-attention-model-for-weakly","repo_url":"https://github.com/IBM/audioset-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"multi-level-attention-model-for-weakly","repo_url":"https://github.com/clarivando/MAX-Audio-Classifier","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multi-level-attention-model-for-weakly","repo_url":"https://github.com/deephdc/audio-classification-tf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multi-level-attention-model-for-weakly","repo_url":"https://github.com/semantic-search/MAX-Audio-ClassifierX","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.02353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.02353"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/semantic-search/MAX-Audio-ClassifierX","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IBM/audioset-classification","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/clarivando/MAX-Audio-Classifier","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deephdc/audio-classification-tf","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IBM/MAX-Audio-Classifier","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":11},"by_repo_kind":{"listed":{"samples":11,"ran":0,"repositories":2}},"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":"6caa9ea74b6d3d4e","entry":"catch_error","repo":"deephdc/audio-classification-tf","repo_kind":"listed","path":"audioclas/api.py","file_url":"https://github.com/deephdc/audio-classification-tf/blob/HEAD/audioclas/api.py","link_basis":"harvester_set","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":"6caa9ea74b6d3d4e"}},{"code_sha256_prefix":"f841a666a816cd65","entry":"create_model","repo":"deephdc/audio-classification-tf","repo_kind":"listed","path":"audioclas/model_utils.py","file_url":"https://github.com/deephdc/audio-classification-tf/blob/HEAD/audioclas/model_utils.py","link_basis":"harvester_set","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":"f841a666a816cd65"}},{"code_sha256_prefix":"e4f3d3fc80850e1f","entry":"find_audiofiles","repo":"deephdc/audio-classification-tf","repo_kind":"listed","path":"audioclas/misc.py","file_url":"https://github.com/deephdc/audio-classification-tf/blob/HEAD/audioclas/misc.py","link_basis":"harvester_set","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":"e4f3d3fc80850e1f"}},{"code_sha256_prefix":"3f76530d9bfe10a4","entry":"frame","repo":"IBM/MAX-Audio-Classifier","repo_kind":"listed","path":"core/mel_features.py","file_url":"https://github.com/IBM/MAX-Audio-Classifier/blob/HEAD/core/mel_features.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3f76530d9bfe10a4"}},{"code_sha256_prefix":"203fb22ce3ba8219","entry":"is_audio","repo":"deephdc/audio-classification-tf","repo_kind":"listed","path":"audioclas/misc.py","file_url":"https://github.com/deephdc/audio-classification-tf/blob/HEAD/audioclas/misc.py","link_basis":"harvester_set","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":"203fb22ce3ba8219"}},{"code_sha256_prefix":"8ee89543c8a663b9","entry":"load_class_names","repo":"deephdc/audio-classification-tf","repo_kind":"listed","path":"audioclas/data_utils.py","file_url":"https://github.com/deephdc/audio-classification-tf/blob/HEAD/audioclas/data_utils.py","link_basis":"harvester_set","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":"8ee89543c8a663b9"}},{"code_sha256_prefix":"72e572ebf4ebd962","entry":"load_data_splits","repo":"deephdc/audio-classification-tf","repo_kind":"listed","path":"audioclas/data_utils.py","file_url":"https://github.com/deephdc/audio-classification-tf/blob/HEAD/audioclas/data_utils.py","link_basis":"harvester_set","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":"72e572ebf4ebd962"}},{"code_sha256_prefix":"49e5bbc639f49bb4","entry":"mount_nextcloud","repo":"deephdc/audio-classification-tf","repo_kind":"listed","path":"audioclas/data_utils.py","file_url":"https://github.com/deephdc/audio-classification-tf/blob/HEAD/audioclas/data_utils.py","link_basis":"harvester_set","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":"49e5bbc639f49bb4"}},{"code_sha256_prefix":"1ce325daf49dbb55","entry":"open_compressed","repo":"deephdc/audio-classification-tf","repo_kind":"listed","path":"audioclas/misc.py","file_url":"https://github.com/deephdc/audio-classification-tf/blob/HEAD/audioclas/misc.py","link_basis":"harvester_set","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":"1ce325daf49dbb55"}},{"code_sha256_prefix":"ed0ef7fc8a5f1840","entry":"periodic_hann","repo":"IBM/MAX-Audio-Classifier","repo_kind":"listed","path":"core/mel_features.py","file_url":"https://github.com/IBM/MAX-Audio-Classifier/blob/HEAD/core/mel_features.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ed0ef7fc8a5f1840"}},{"code_sha256_prefix":"0f0fa853ceaa04db","entry":"stft_magnitude","repo":"IBM/MAX-Audio-Classifier","repo_kind":"listed","path":"core/mel_features.py","file_url":"https://github.com/IBM/MAX-Audio-Classifier/blob/HEAD/core/mel_features.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0f0fa853ceaa04db"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}