{"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/fusionaudio-1-2m-towards-fine-grained-audio","title":"FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion","arxiv_id":"2506.01111","date":"2025-06-01","proceeding":null,"authors":["Shunian Chen","Xinyuan Xie","Zheshu Chen","Liyan Zhao","Owen Lee","Zhan Su","Qilin Sun","Benyou Wang"],"abstract":"High-quality, large-scale audio captioning is crucial for advancing audio understanding, yet current automated methods often generate captions that lack fine-grained detail and contextual accuracy, primarily due to their reliance on limited unimodal or superficial multimodal information. Drawing inspiration from human auditory perception, which adeptly integrates cross-modal cues and performs sophisticated auditory scene analysis, we introduce a novel two-stage automated pipeline. This pipeline first employs specialized pretrained models to extract diverse contextual cues (e.g., speech, music, general sounds, and visual information from associated video). A large language model (LLM) then synthesizes these rich, multimodal inputs to generate detailed and context-aware audio captions. Key contributions of this work include: (1) the proposed scalable method for fine-grained audio caption generation; (2) FusionAudio, a new large-scale dataset comprising 1.2 million such detailed captions, combined with 6 million QA pairs; and (3) enhanced audio models developed using FusionAudio, specifically a CLAP-based audio encoder with superior audio-text alignment and instruction following. This paper paves the way for more nuanced and accurate automated understanding of complex audio environments. Code and data can be found in https://github.com/satsuki2486441738/FusionAudio.","url_abs":"https://arxiv.org/abs/2506.01111v1","url_pdf":"https://arxiv.org/pdf/2506.01111v1.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":"fusionaudio-1-2m-towards-fine-grained-audio","repo_url":"https://github.com/satsuki2486441738/fusionaudio","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"audio-captioning","task_name":"Audio captioning"},{"task_slug":"caption-generation","task_name":"Caption Generation"},{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2506.01111","atlas_url":"https://app.syntology.ai/?focus=2506.01111","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}