{"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":"/paper/the-dcase-2021-challenge-task-6-system","title":"THE DCASE 2021 CHALLENGE TASK 6 SYSTEM: AUTOMATED AUDIO CAPTIONING WITH WEAKLY SUPERVISED PRE-TRAING AND WORD SELECTION METHODS","arxiv_id":null,"date":"2021-07-06","proceeding":"DCASE workshop 2021 7","authors":["Weiqiang Yuan ∗","Qichen Han∗","Dong Liu","Xiang Li","Zhen Yang"],"abstract":"This technical report describes the system participating to the De-\r\ntection and Classification of Acoustic Scenes and Events\r\n(DCASE) 2021 Challenge, Task 6: automated audio captioning.\r\nWe use encoder-decoder modeling framework for audio under-\r\nstanding and caption generation. Our solution focuses on solving\r\ntwo problems in automated audio captioning: data insufficiency\r\nand word selection indeterminacy. As limited audios with golden\r\ncaptions are available, we collect large-scale weakly labeled da-\r\ntaset from Web with heuristic methods. Then we pre-train the en-\r\ncoder-decoder models with this dataset followed by fine-tuning\r\non Clotho dataset. To solve the word selection indeterminacy\r\nproblem, we use keywords extracted from captions of similar au-\r\ndios and audio event tags produced by pre-trained models to guide\r\nwords generation in decoding stage. We tested our submissions\r\nusing the development-testing dataset. Our best submission\r\nachieved 31.8 SPIDEr score where that of the baseline system is\r\n5.4.","url_abs":"https://dcase.community/documents/challenge2021/technical_reports/DCASE2021_Yuan_2_t6.pdf","url_pdf":"https://dcase.community/documents/challenge2021/technical_reports/DCASE2021_Yuan_2_t6.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":[],"tasks":[{"task_slug":"audio-captioning","task_name":"Audio captioning"},{"task_slug":"caption-generation","task_name":"Caption Generation"},{"task_slug":"decoder","task_name":"Decoder"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-captioning-on-clotho","task":"Audio captioning","dataset":"Clotho","model":"Ensemble","rank_in_archive_order":4,"of":11,"metrics":{"CIDEr":"0.400","SPICE":"0.137","SPIDEr":"0.318"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"f497fda7cf42747373772f258c3a79b97f6b2d0d3ab224c35d228081e207ee06","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}