{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T22:15:47Z","timestamp":1784931347594,"version":"3.55.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095969","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":440,"title":["Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation"],"prefix":"10.1109","author":[{"given":"Yusong","family":"Wu","sequence":"first","affiliation":[{"name":"Université de Montréal,Mila, Quebec Artificial Intelligence Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Chen","sequence":"additional","affiliation":[{"name":"University of California San Diego"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Université de Montréal,Mila, Quebec Artificial Intelligence Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Hui","sequence":"additional","affiliation":[{"name":"Université de Montréal,Mila, Quebec Artificial Intelligence Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taylor","family":"Berg-Kirkpatrick","sequence":"additional","affiliation":[{"name":"University of California San Diego"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shlomo","family":"Dubnov","sequence":"additional","affiliation":[{"name":"University of California San Diego"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Roberta: A robustly optimized BERT pretraining approach","author":"liu","year":"2019","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref11","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc NAACL-HLT"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref1","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"CoRR"},{"key":"ref17","article-title":"Audiocaps: Generating captions for audios in the wild","author":"kim","year":"2019","journal-title":"Proc NAACL-HLT"},{"key":"ref16","article-title":"Audio retrieval with natural language queries: A benchmark study","author":"koepke","year":"2021","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref18","article-title":"Deep learning using rectified linear units (relu)","author":"agarap","year":"2018","journal-title":"CoRR"},{"key":"ref24","article-title":"Accurate, large minibatch sgd: Training imagenet in 1 hour","author":"goyal","year":"2017"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc ICLR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-227"},{"key":"ref25","article-title":"Attention bottlenecks for multimodal fusion","author":"nagrani","year":"2021","journal-title":"Proc NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref22","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"raffel","year":"2020","journal-title":"JMLR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00360"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11115"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2227"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref4","article-title":"CLAP: learning audio concepts from natural language supervision","author":"elizalde","year":"2022","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref6","article-title":"Text-to-audio retrieval via large-scale contrastive learning","author":"wu","year":"2022","journal-title":"Proc DCASE"},{"key":"ref5","article-title":"Audio retrieval with wavtext5k and CLAP training","author":"deshmukh","year":"2022","journal-title":"CoRR"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095969.pdf?arnumber=10095969","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:06:30Z","timestamp":1700507190000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095969\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095969","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}