{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:27:47Z","timestamp":1774420067141,"version":"3.50.1"},"reference-count":31,"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\/icassp49660.2025.10890484","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Bridging the Modality Gap for Speech-image Retrieval with Text Supervision"],"prefix":"10.1109","author":[{"given":"Yuting","family":"Yang","sequence":"first","affiliation":[{"name":"Netease,Yidun AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lifeng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Netease,Yidun AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuke","family":"Li","sequence":"additional","affiliation":[{"name":"Netease,Yidun AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guodong","family":"Ma","sequence":"additional","affiliation":[{"name":"Netease,Yidun AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-96"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747103"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10022954"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref5","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"Neural Information Processing Systems,Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref8","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"International Conference on Machine Learning","author":"Baevski"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref13","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref14","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref15","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"ref17","first-page":"6216","article-title":"Data determines distributional robustness in contrastive language image pre-training (clip)","volume-title":"International Conference on Machine Learning","author":"Fang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.411"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10625827"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-745"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-135"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2404"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094820"},{"key":"ref26","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"International conference on machine learning","author":"Graves"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.411"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref31","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"}],"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\/10890484.pdf?arnumber=10890484","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:12Z","timestamp":1774416372000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890484\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890484","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}