{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T20:12:43Z","timestamp":1774642363444,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448154","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1181-1185","source":"Crossref","is-referenced-by-count":2,"title":["Parameter Efficient Audio Captioning with Faithful Guidance Using Audio-Text Shared Latent Representation"],"prefix":"10.1109","author":[{"given":"Arvind Krishna","family":"Sridhar","sequence":"first","affiliation":[{"name":"Qualcomm Technologies"}]},{"given":"Yinyi","family":"Guo","sequence":"additional","affiliation":[{"name":"Qualcomm Technologies"}]},{"given":"Erik","family":"Visser","sequence":"additional","affiliation":[{"name":"Qualcomm Technologies"}]},{"given":"Rehana","family":"Mahfuz","sequence":"additional","affiliation":[{"name":"Qualcomm Technologies"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref2","article-title":"Improving the performance of automated audio captioning via integrating the acoustic and semantic information","volume-title":"Workshop on Detection and Classification of Acoustic Scenes and Events","author":"Ye"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419446"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00413"},{"key":"ref6","first-page":"90","article-title":"Diversity and bias in audio captioning datasets","volume-title":"Proceedings of the 6th Workshop on Detection and Classication of Acoustic Scenes and Events (DCASE 2021)","author":"Morato"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.667"},{"key":"ref8","article-title":"Improved beam search for hallucination mitigation in abstractive summarization","author":"Sridhar","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.gem-1.51"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.156"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26316-3_37"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref13","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","author":"Zheng","year":"2023"},{"key":"ref14","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095969"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00346"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1011"},{"key":"ref20","article-title":"An encoder-decoder based audio captioning system with transfer and reinforcement learning","volume":"abs\/2108.02752","author":"Mei","year":"2021","journal-title":"ArXiv"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448154.pdf?arnumber=10448154","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:52:01Z","timestamp":1722581521000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448154\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448154","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}