{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:28:51Z","timestamp":1774420131953,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889814","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Audiopedia: Audio QA with Knowledge"],"prefix":"10.1109","author":[{"given":"Abhirama Subramanyam","family":"Penamakuri","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Jodhpur"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kiran","family":"Chhatre","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akshat","family":"Jain","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Jodhpur"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref2","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref3","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909680"},{"key":"ref5","article-title":"Clear: A dataset for compositional language and elementary acoustic reasoning","author":"Abdelnour","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3010650"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1816"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.925"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/146"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26598"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00470"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1151"},{"key":"ref16","article-title":"Audio flamingo: A novel audio language model with few-shot learning and dialogue abilities","author":"Kong","year":"2024","journal-title":"ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.361"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389742"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2124"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w17-2623"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/280"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68790-8_27"},{"key":"ref29","article-title":"The refinedweb dataset for falcon llm: Outperforming curated corpora with web data only","author":"Penedo","year":"2024","journal-title":"NeurIPS"},{"key":"ref30","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"NeurIPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1301"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"ref33","article-title":"Ted-el: A corpus for speech entity linking","author":"Li","year":"2024","journal-title":"LREC-COLING 2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref35","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"NeurIPS"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889814.pdf?arnumber=10889814","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:35Z","timestamp":1774416395000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889814\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889814","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}