{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:03:23Z","timestamp":1784736203987,"version":"3.55.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10688214","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":5,"title":["Audiolog: LLMs-Powered Long Audio Logging with Hybrid Token-Semantic Contrastive Learning"],"prefix":"10.1109","author":[{"given":"Jisheng","family":"Bai","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Yin","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mou","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Acoustics,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongyuan","family":"Shi","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Electrical & Electronic Engineering,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Woon-Seng","family":"Gan","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Electrical & Electronic Engineering,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Susanto","family":"Rahardja","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2022.3160168"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3090678"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419446"},{"key":"ref5","article-title":"A comprehensive survey of automated audio captioning","author":"Xu","year":"2022"},{"key":"ref6","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref7","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Advances in neural information processing systems","volume":"33","author":"Brown"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-022-00259-2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053912"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2022.3222350"},{"key":"ref13","first-page":"2530","article-title":"Clar: Contrastive learning of auditory representations","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Al-Tahan"},{"key":"ref14","article-title":"Multi-format contrastive learning of audio representations","author":"Wang","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3233468"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3233468"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979926"},{"key":"ref20","article-title":"DCASE 2023 challenge task4 technical report","volume-title":"Tech. Rep., DCASE2023 Challenge","author":"Jin","year":"2023"},{"key":"ref21","article-title":"How information on soft labels and hard labels mutually benefits sound event detection tasks","volume-title":"Tech. Rep., DCASE2023 Challenge","author":"Yin","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1250\/ast.44.167"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10688214.pdf?arnumber=10688214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:29:05Z","timestamp":1732735745000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10688214\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10688214","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}