{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:30:29Z","timestamp":1776882629951,"version":"3.51.2"},"reference-count":25,"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"}],"funder":[{"DOI":"10.13039\/100007880","name":"Johns Hopkins University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007880","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096882","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":8,"title":["M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval"],"prefix":"10.1109","author":[{"given":"Layne","family":"Berry","sequence":"first","affiliation":[{"name":"University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Jen","family":"Shih","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsuan-Fu","family":"Wang","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng-Jui","family":"Chang","sequence":"additional","affiliation":[{"name":"MIT CSAIL"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Harwath","sequence":"additional","affiliation":[{"name":"University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Learning deep features for scene recognition using places database","volume":"27","author":"zhou","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref15","article-title":"Vision as an interlingua: Learning multilingual semantic embeddings of untranscribed speech","author":"harwath","year":"2018","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref14","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.411"},{"key":"ref10","article-title":"Fast-slow transformer for visually grounding speech","author":"peng","year":"2022","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref2","article-title":"Speechclip: Integrating speech with pre-trained vision and language model","author":"shih","year":"2022","journal-title":"IEEE Spoken Language Technology Workshop"},{"key":"ref1","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3078"},{"key":"ref16","first-page":"4352","article-title":"Trilingual semantic embeddings of visually grounded speech with self-attention mechanisms","author":"ohishi","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1352"},{"key":"ref18","article-title":"Models of visually grounded speech signal pay attention to nouns: a bilingual experiment on english and japanese","author":"havard","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref24","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"31st Conference on Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1006"},{"key":"ref20","article-title":"Semantic speech retrieval with a visually grounded model of untranscribed speech","author":"kamper","year":"2018"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.21437\/SLTU.2018-53","article-title":"Visually grounded cross-lingual keyword spotting in speech","author":"kamper","year":"2018","journal-title":"SLTU - Workshop on Spoken Language Technologies for Under-Resourced Languages"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3051"},{"key":"ref8","first-page":"6848","article-title":"Cross-lingual and multilingual clip","author":"carlsson","year":"2022","journal-title":"Proceedings of the Language Resources and Evaluation Conference"},{"key":"ref7","article-title":"Language models are unsupervised multitask learners","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref9","article-title":"Towards zero-shot cross-lingual image retrieval and tagging","author":"aggarwal","year":"2021","journal-title":"The Web Conference Workshop on Multilingual Search"},{"key":"ref4","article-title":"Visual genome: Connecting language and vision using crowd-sourced dense image annotations","author":"krishna","year":"2016","journal-title":"International Journal of Computer Vision"},{"key":"ref3","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref6","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"9th International Conference on Learning Representations"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"}],"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\/10096882.pdf?arnumber=10096882","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:09:17Z","timestamp":1700507357000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096882\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096882","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}