{"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/aces-evaluating-automated-audio-captioning","title":"ACES: Evaluating Automated Audio Captioning Models on the Semantics of Sounds","arxiv_id":"2403.18572","date":"2024-03-27","proceeding":null,"authors":["Gijs Wijngaard","Elia Formisano","Bruno L. Giordano","Michel Dumontier"],"abstract":"Automated Audio Captioning is a multimodal task that aims to convert audio content into natural language. The assessment of audio captioning systems is typically based on quantitative metrics applied to text data. Previous studies have employed metrics derived from machine translation and image captioning to evaluate the quality of generated audio captions. Drawing inspiration from auditory cognitive neuroscience research, we introduce a novel metric approach -- Audio Captioning Evaluation on Semantics of Sound (ACES). ACES takes into account how human listeners parse semantic information from sounds, providing a novel and comprehensive evaluation perspective for automated audio captioning systems. ACES combines semantic similarities and semantic entity labeling. ACES outperforms similar automated audio captioning metrics on the Clotho-Eval FENSE benchmark in two evaluation categories.","url_abs":"https://arxiv.org/abs/2403.18572v1","url_pdf":"https://arxiv.org/pdf/2403.18572v1.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"aces-evaluating-automated-audio-captioning","repo_url":"https://github.com/gljs/aces","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.18572","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18572"}},"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/gljs/aces","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":8,"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":15,"ran":9,"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":"8f4749fab50eb0c6","entry":"align_labels_with_tokens","repo":"gljs/aces","repo_kind":"official","path":"training/utils.py","file_url":"https://github.com/gljs/aces/blob/HEAD/training/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f4749fab50eb0c6"}},{"code_sha256_prefix":"b458d0c75fe390a0","entry":"cook_refs","repo":"gljs/aces","repo_kind":"official","path":"evaluation/coco_caption/pycocoevalcap/cider/cider_scorer.py","file_url":"https://github.com/gljs/aces/blob/HEAD/evaluation/coco_caption/pycocoevalcap/cider/cider_scorer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b458d0c75fe390a0"}},{"code_sha256_prefix":"e1dd2bb001729dde","entry":"cook_test","repo":"gljs/aces","repo_kind":"official","path":"evaluation/coco_caption/pycocoevalcap/bleu/bleu_scorer.py","file_url":"https://github.com/gljs/aces/blob/HEAD/evaluation/coco_caption/pycocoevalcap/bleu/bleu_scorer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e1dd2bb001729dde"}},{"code_sha256_prefix":"486bccc796451075","entry":"cook_test","repo":"gljs/aces","repo_kind":"official","path":"evaluation/coco_caption/pycocoevalcap/cider/cider_scorer.py","file_url":"https://github.com/gljs/aces/blob/HEAD/evaluation/coco_caption/pycocoevalcap/cider/cider_scorer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"486bccc796451075"}},{"code_sha256_prefix":"2ce7c8fe03ef29c6","entry":"get_data_home","repo":"gljs/aces","repo_kind":"official","path":"src/aces/fense/download_utils.py","file_url":"https://github.com/gljs/aces/blob/HEAD/src/aces/fense/download_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2ce7c8fe03ef29c6"}},{"code_sha256_prefix":"e77be74719a260e0","entry":"infer_preprocess","repo":"gljs/aces","repo_kind":"official","path":"src/aces/fense/data.py","file_url":"https://github.com/gljs/aces/blob/HEAD/src/aces/fense/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e77be74719a260e0"}},{"code_sha256_prefix":"ec4448373d72d636","entry":"precook","repo":"gljs/aces","repo_kind":"official","path":"evaluation/coco_caption/pycocoevalcap/bleu/bleu_scorer.py","file_url":"https://github.com/gljs/aces/blob/HEAD/evaluation/coco_caption/pycocoevalcap/bleu/bleu_scorer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec4448373d72d636"}},{"code_sha256_prefix":"9253071bb73fb8b2","entry":"reformat_to_coco","repo":"gljs/aces","repo_kind":"official","path":"evaluation/eval_metrics.py","file_url":"https://github.com/gljs/aces/blob/HEAD/evaluation/eval_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9253071bb73fb8b2"}},{"code_sha256_prefix":"c1d2029cd05b84fc","entry":"text_preprocess","repo":"gljs/aces","repo_kind":"official","path":"src/aces/fense/data.py","file_url":"https://github.com/gljs/aces/blob/HEAD/src/aces/fense/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c1d2029cd05b84fc"}},{"code_sha256_prefix":"ab64c5a8dad76015","entry":"check_download_resource","repo":"gljs/aces","repo_kind":"official","path":"src/aces/fense/download_utils.py","file_url":"https://github.com/gljs/aces/blob/HEAD/src/aces/fense/download_utils.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":"ab64c5a8dad76015"}},{"code_sha256_prefix":"7586e1d32f7325f7","entry":"cook_refs","repo":"gljs/aces","repo_kind":"official","path":"evaluation/coco_caption/pycocoevalcap/bleu/bleu_scorer.py","file_url":"https://github.com/gljs/aces/blob/HEAD/evaluation/coco_caption/pycocoevalcap/bleu/bleu_scorer.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":"7586e1d32f7325f7"}},{"code_sha256_prefix":"855591d1fd6de239","entry":"download","repo":"gljs/aces","repo_kind":"official","path":"src/aces/fense/download_utils.py","file_url":"https://github.com/gljs/aces/blob/HEAD/src/aces/fense/download_utils.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":"855591d1fd6de239"}},{"code_sha256_prefix":"28747d415bf301a3","entry":"evaluate_metrics_from_files","repo":"gljs/aces","repo_kind":"official","path":"evaluation/eval_metrics.py","file_url":"https://github.com/gljs/aces/blob/HEAD/evaluation/eval_metrics.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":"28747d415bf301a3"}},{"code_sha256_prefix":"d49e7cc3375255d0","entry":"evaluate_metrics_from_lists","repo":"gljs/aces","repo_kind":"official","path":"evaluation/eval_metrics.py","file_url":"https://github.com/gljs/aces/blob/HEAD/evaluation/eval_metrics.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":"d49e7cc3375255d0"}},{"code_sha256_prefix":"28580b1d81d80b70","entry":"load_pretrain_echecker","repo":"gljs/aces","repo_kind":"official","path":"src/aces/fense/evaluator.py","file_url":"https://github.com/gljs/aces/blob/HEAD/src/aces/fense/evaluator.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":"28580b1d81d80b70"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}