{"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/audio-captioning-via-generative-pair-to-pair","title":"Enhancing Retrieval-Augmented Audio Captioning with Generation-Assisted Multimodal Querying and Progressive Learning","arxiv_id":"2410.10913","date":"2024-10-14","proceeding":null,"authors":["Choi Changin","Lim Sungjun","Rhee Wonjong"],"abstract":"Retrieval-augmented generation can improve audio captioning by incorporating relevant audio-text pairs from a knowledge base. Existing methods typically rely solely on the input audio as a unimodal retrieval query. In contrast, we propose Generation-Assisted Multimodal Querying, which generates a text description of the input audio to enable multimodal querying. This approach aligns the query modality with the audio-text structure of the knowledge base, leading to more effective retrieval. Furthermore, we introduce a novel progressive learning strategy that gradually increases the number of interleaved audio-text pairs to enhance the training process. Our experiments on AudioCaps, Clotho, and Auto-ACD demonstrate that our approach achieves state-of-the-art results across these benchmarks.","url_abs":"https://arxiv.org/abs/2410.10913v3","url_pdf":"https://arxiv.org/pdf/2410.10913v3.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":null,"task_name":"AudioCaps"},{"task_slug":"rag","task_name":"RAG"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"base","method_name":"BASE"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"rag","method_name":"RAG"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-captioning-on-audiocaps","task":"Audio captioning","dataset":"AudioCaps","model":"MQ-Cap","rank_in_archive_order":1,"of":18,"metrics":{"BLEU-4":"0.301","CIDEr":"0.845","METEOR":"0.266","SPICE":"0.194","SPIDEr":"0.519"},"uses_additional_data":true},{"leaderboard":"/sota/audio-captioning-on-clotho","task":"Audio captioning","dataset":"Clotho","model":"MQ-Cap","rank_in_archive_order":3,"of":11,"metrics":{"BLEU-4":"18.1","CIDEr":"0.496","METEOR":"0.192","SPICE":"0.143","SPIDEr":"0.319"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2410.10913","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}