{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:54:56Z","timestamp":1772906096123,"version":"3.50.1"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446888","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"7970-7974","source":"Crossref","is-referenced-by-count":6,"title":["Towards Practical and Efficient Image-to-Speech Captioning with Vision-Language Pre-Training and Multi-Modal Tokens"],"prefix":"10.1109","author":[{"given":"Minsu","family":"Kim","sequence":"first","affiliation":[{"name":"KAIST,Integrated Vision and Language Lab,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeongsoo","family":"Choi","sequence":"additional","affiliation":[{"name":"KAIST,Integrated Vision and Language Lab,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soumi","family":"Maiti","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeong Hun","family":"Yeo","sequence":"additional","affiliation":[{"name":"KAIST,Integrated Vision and Language Lab,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong Man","family":"Ro","sequence":"additional","affiliation":[{"name":"KAIST,Integrated Vision and Language Lab,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"65","article-title":"Image2speech: Automatically generating audio descriptions of images","author":"Hasegawa-Johnson","year":"2017","journal-title":"Casablanca 2017"},{"key":"ref2","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"ICML","author":"Xu"},{"key":"ref3","article-title":"Neural discrete representation learning","volume-title":"NIPS","volume":"30","author":"Van Den Oord"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095582"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120644"},{"key":"ref6","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.872"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11032"},{"key":"ref9","article-title":"Many-to-many spoken language translation via unified speech and text representation learning with unit-to-unit translation","author":"Kim","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097097"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00545"},{"key":"ref12","article-title":"Discretalk: Text-to-speech as a machine translation problem","author":"Hayashi","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-194"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2051"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01409"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1057"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022954"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01801"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref21","article-title":"Git: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref23","article-title":"Vector-quantized image modeling with improved vqgan","volume-title":"ICLR","author":"Yu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2003"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095710"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.411"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3071541"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref31","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"NIPS","author":"Kong"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref34","first-page":"1791","article-title":"Neural variational inference and learning in belief networks","volume-title":"ICML","author":"Mnih"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01582"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref38","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref39","first-page":"311","article-title":"Bleu: A method for automatic evaluation of machine translation","volume-title":"Proc. ACL","author":"Papineni"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref41","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref44","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"ICML","author":"Kim"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref46","volume-title":"The lj speech dataset","author":"Ito","year":"2017"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref48","article-title":"Im2text: Describing images using 1 million captioned photographs","volume":"24","author":"Ordonez","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.63"},{"key":"ref50","first-page":"98","article-title":"Findings of the iwslt 2022 evaluation campaign","volume-title":"Proc. IWSLT","author":"Antonios"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446888.pdf?arnumber=10446888","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:39:39Z","timestamp":1722573579000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446888\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446888","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}