{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T11:47:58Z","timestamp":1774352878348,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,22]],"date-time":"2024-09-22T00:00:00Z","timestamp":1726963200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,22]],"date-time":"2024-09-22T00:00:00Z","timestamp":1726963200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council (EPSRC)","doi-asserted-by":"publisher","award":["EP\/T019751\/1"],"award-info":[{"award-number":["EP\/T019751\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,22]]},"DOI":"10.1109\/mlsp58920.2024.10734763","type":"proceedings-article","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T18:31:55Z","timestamp":1730745115000},"page":"1-6","source":"Crossref","is-referenced-by-count":11,"title":["T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining"],"prefix":"10.1109","author":[{"given":"Yi","family":"Yuan","sequence":"first","affiliation":[{"name":"University of Surrey,United Kingdom"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance,China"}]},{"given":"Xubo","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Surrey,United Kingdom"}]},{"given":"Haohe","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Surrey,United Kingdom"}]},{"given":"Xuenan","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}]},{"given":"Dongya","family":"Jia","sequence":"additional","affiliation":[{"name":"ByteDance,China"}]},{"given":"Yuanzhe","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance,China"}]},{"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[{"name":"University of Surrey,United Kingdom"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Surrey,United Kingdom"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"ref5","article-title":"CLIPcap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv:2111.09734"},{"key":"ref6","article-title":"Zero-shot image-to-text generation for visual-semantic arithmetic","author":"Tewel","year":"2021","journal-title":"arXiv:2111.14447"},{"key":"ref7","article-title":"EDIFFI: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022","journal-title":"arXiv:2211.01324"},{"key":"ref8","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"International Conference on Machine Learning","author":"Nichol","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref10","article-title":"AudioLDM: Text-to-Audio generation with latent diffusion models","volume-title":"International Conference on Machine Learning","author":"Liu","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447898"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01050"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.230"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1614"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref16","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019","journal-title":"CoRR"},{"key":"ref17","article-title":"Audio retrieval with Wavtext5K and CLAP training","author":"Deshmukh","year":"2022","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2227"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11115"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096972"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00294"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref24","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Annual Conference of the North American Chapter of the Association for Computational Linguistics","author":"Kim","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681472"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097117"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613820"}],"event":{"name":"2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)","location":"London, United Kingdom","start":{"date-parts":[[2024,9,22]]},"end":{"date-parts":[[2024,9,25]]}},"container-title":["2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10734669\/10734712\/10734763.pdf?arnumber=10734763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T11:05:02Z","timestamp":1732705502000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10734763\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,22]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/mlsp58920.2024.10734763","relation":{},"subject":[],"published":{"date-parts":[[2024,9,22]]}}}