{"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/av-rir-audio-visual-room-impulse-response","title":"AV-RIR: Audio-Visual Room Impulse Response Estimation","arxiv_id":"2312.00834","date":"2023-11-30","proceeding":"CVPR 2024 1","authors":["Anton Ratnarajah","Sreyan Ghosh","Sonal Kumar","Purva Chiniya","Dinesh Manocha"],"abstract":"Accurate estimation of Room Impulse Response (RIR), which captures an environment's acoustic properties, is important for speech processing and AR/VR applications. We propose AV-RIR, a novel multi-modal multi-task learning approach to accurately estimate the RIR from a given reverberant speech signal and the visual cues of its corresponding environment. AV-RIR builds on a novel neural codec-based architecture that effectively captures environment geometry and materials properties and solves speech dereverberation as an auxiliary task by using multi-task learning. We also propose Geo-Mat features that augment material information into visual cues and CRIP that improves late reverberation components in the estimated RIR via image-to-RIR retrieval by 86%. Empirical results show that AV-RIR quantitatively outperforms previous audio-only and visual-only approaches by achieving 36% - 63% improvement across various acoustic metrics in RIR estimation. Additionally, it also achieves higher preference scores in human evaluation. As an auxiliary benefit, dereverbed speech from AV-RIR shows competitive performance with the state-of-the-art in various spoken language processing tasks and outperforms reverberation time error score in the real-world AVSpeech dataset. Qualitative examples of both synthesized reverberant speech and enhanced speech can be found at https://www.youtube.com/watch?v=tTsKhviukAE.","url_abs":"https://arxiv.org/abs/2312.00834v2","url_pdf":"https://arxiv.org/pdf/2312.00834v2.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":"av-rir-audio-visual-room-impulse-response","repo_url":"https://github.com/anton-jeran/AV-RIR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"av-rir-audio-visual-room-impulse-response","repo_url":"https://github.com/anton-jeran/Speech2RIR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"room-impulse-response-rir","task_name":"Room Impulse Response (RIR)"},{"task_slug":"speech-dereverberation","task_name":"Speech Dereverberation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.00834","atlas_url":"https://app.syntology.ai/?focus=2312.00834","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}