{"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/enhancing-automated-audio-captioning-via","title":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding","arxiv_id":"2406.13275","date":"2024-06-19","proceeding":null,"authors":["Jizhong Liu","Gang Li","Junbo Zhang","Heinrich Dinkel","Yongqing Wang","Zhiyong Yan","Yujun Wang","Bin Wang"],"abstract":"Automated audio captioning (AAC) is an audio-to-text task to describe audio contents in natural language. Recently, the advancements in large language models (LLMs), with improvements in training approaches for audio encoders, have opened up possibilities for improving AAC. Thus, we explore enhancing AAC from three aspects: 1) a pre-trained audio encoder via consistent ensemble distillation (CED) is used to improve the effectivity of acoustic tokens, with a querying transformer (Q-Former) bridging the modality gap to LLM and compress acoustic tokens; 2) we investigate the advantages of using a Llama 2 with 7B parameters as the decoder; 3) another pre-trained LLM corrects text errors caused by insufficient training data and annotation ambiguities. Both the audio encoder and text decoder are optimized by low-rank adaptation (LoRA). Experiments show that each of these enhancements is effective. Our method obtains a 33.0 SPIDEr-FL score, outperforming the winner of DCASE 2023 Task 6A.","url_abs":"https://arxiv.org/abs/2406.13275v2","url_pdf":"https://arxiv.org/pdf/2406.13275v2.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":"enhancing-automated-audio-captioning-via","repo_url":"https://github.com/frankenliu/LOAE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"audio-captioning","task_name":"Audio captioning"},{"task_slug":"decoder","task_name":"Decoder"}],"methods":[{"method_slug":"llama","method_name":"LLaMA"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-captioning-on-audiocaps","task":"Audio captioning","dataset":"AudioCaps","model":"LOAE","rank_in_archive_order":6,"of":18,"metrics":{"CIDEr":"0.816","FENSE":"0.664","METEOR":"0.267","SPICE":"0.193","SPIDEr":"0.505","Sentence-BERT":"0.664"},"uses_additional_data":true},{"leaderboard":"/sota/audio-captioning-on-clotho","task":"Audio captioning","dataset":"Clotho","model":"LOAE","rank_in_archive_order":2,"of":11,"metrics":{"CIDEr":"0.513","FENSE":"0.538","METEOR":"0.197","SPICE":"0.147","SPIDEr":"0.330","SPIDEr-FL":"0.330","Sentence-BERT":"0.538"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.13275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13275"}},"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/frankenliu/LOAE","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"ran_fixture":1,"unverified":3},"by_repo_kind":{"official":{"samples":8,"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":0,"samples":[{"code_sha256_prefix":"c91abe7318f78bdc","entry":"build_mdl","repo":"frankenliu/LOAE","repo_kind":"official","path":"models/ced/checkpoints.py","file_url":"https://github.com/frankenliu/LOAE/blob/HEAD/models/ced/checkpoints.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c91abe7318f78bdc"}},{"code_sha256_prefix":"872651496d568a89","entry":"collate_fn","repo":"frankenliu/LOAE","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/frankenliu/LOAE/blob/HEAD/dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"872651496d568a89"}},{"code_sha256_prefix":"87577b3ff9d32712","entry":"drop_path","repo":"frankenliu/LOAE","repo_kind":"official","path":"models/ced/layers.py","file_url":"https://github.com/frankenliu/LOAE/blob/HEAD/models/ced/layers.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"87577b3ff9d32712"}},{"code_sha256_prefix":"01a8fe68c38dbac5","entry":"to_2tuple","repo":"frankenliu/LOAE","repo_kind":"official","path":"models/ced/layers.py","file_url":"https://github.com/frankenliu/LOAE/blob/HEAD/models/ced/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"01a8fe68c38dbac5"}},{"code_sha256_prefix":"7601879b595df35a","entry":"trunc_normal_","repo":"frankenliu/LOAE","repo_kind":"official","path":"models/ced/layers.py","file_url":"https://github.com/frankenliu/LOAE/blob/HEAD/models/ced/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7601879b595df35a"}},{"code_sha256_prefix":"532ac1611a9eb3a6","entry":"get_gpu_info","repo":"frankenliu/LOAE","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/frankenliu/LOAE/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","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":"532ac1611a9eb3a6"}},{"code_sha256_prefix":"7bba3ef74639259f","entry":"get_tcp_address","repo":"frankenliu/LOAE","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/frankenliu/LOAE/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","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":"7bba3ef74639259f"}},{"code_sha256_prefix":"9264a154be38fcdb","entry":"register_model","repo":"frankenliu/LOAE","repo_kind":"official","path":"models/ced/checkpoints.py","file_url":"https://github.com/frankenliu/LOAE/blob/HEAD/models/ced/checkpoints.py","link_basis":"first_harvest_node","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":"9264a154be38fcdb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}