{"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/improving-audio-spectrogram-transformers-for","title":"Improving Audio Spectrogram Transformers for Sound Event Detection Through Multi-Stage Training","arxiv_id":"2408.00791","date":"2024-07-17","proceeding":null,"authors":["Florian Schmid","Paul Primus","Tobias Morocutti","Jonathan Greif","Gerhard Widmer"],"abstract":"This technical report describes the CP-JKU team's submission for Task 4 Sound Event Detection with Heterogeneous Training Datasets and Potentially Missing Labels of the DCASE 24 Challenge. We fine-tune three large Audio Spectrogram Transformers, PaSST, BEATs, and ATST, on the joint DESED and MAESTRO datasets in a two-stage training procedure. The first stage closely matches the baseline system setup and trains a CRNN model while keeping the large pre-trained transformer model frozen. In the second stage, both CRNN and transformer are fine-tuned using heavily weighted self-supervised losses. After the second stage, we compute strong pseudo-labels for all audio clips in the training set using an ensemble of all three fine-tuned transformers. Then, in a second iteration, we repeat the two-stage training process and include a distillation loss based on the pseudo-labels, boosting single-model performance substantially. Additionally, we pre-train PaSST and ATST on the subset of AudioSet that comes with strong temporal labels, before fine-tuning them on the Task 4 datasets.","url_abs":"https://arxiv.org/abs/2408.00791v1","url_pdf":"https://arxiv.org/pdf/2408.00791v1.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":"improving-audio-spectrogram-transformers-for","repo_url":"https://github.com/cpjku/cpjku_dcase24","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"event-detection","task_name":"Event Detection"},{"task_slug":"missing-labels","task_name":"Missing Labels"},{"task_slug":"sound-event-detection","task_name":"Sound Event Detection"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.00791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00791"}},"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/cpjku/cpjku_dcase24","reach":{"status":"ok"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"f88ff6506ef7f11e","entry":"ExponentialLR","repo":"cpjku/cpjku_dcase24","repo_kind":"official","path":"ex_audioset_kd.py","file_url":"https://github.com/cpjku/cpjku_dcase24/blob/HEAD/ex_audioset_kd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f88ff6506ef7f11e"}},{"code_sha256_prefix":"65e3bd18b3e17e20","entry":"audioset_transform","repo":"cpjku/cpjku_dcase24","repo_kind":"official","path":"data_util/audioset.py","file_url":"https://github.com/cpjku/cpjku_dcase24/blob/HEAD/data_util/audioset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"65e3bd18b3e17e20"}},{"code_sha256_prefix":"391b9a300afa7123","entry":"cv_transform","repo":"cpjku/cpjku_dcase24","repo_kind":"official","path":"data_util/audioset.py","file_url":"https://github.com/cpjku/cpjku_dcase24/blob/HEAD/data_util/audioset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"391b9a300afa7123"}},{"code_sha256_prefix":"ce8cb3c67aa800ea","entry":"get_hf_local_path","repo":"cpjku/cpjku_dcase24","repo_kind":"official","path":"data_util/audioset.py","file_url":"https://github.com/cpjku/cpjku_dcase24/blob/HEAD/data_util/audioset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ce8cb3c67aa800ea"}},{"code_sha256_prefix":"d24cf003bec39b8f","entry":"merge_overlapping_events","repo":"cpjku/cpjku_dcase24","repo_kind":"official","path":"data_util/audioset_strong.py","file_url":"https://github.com/cpjku/cpjku_dcase24/blob/HEAD/data_util/audioset_strong.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d24cf003bec39b8f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}