{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:28:52Z","timestamp":1774420132598,"version":"3.50.1"},"reference-count":28,"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\/icassp49660.2025.10890285","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["From Pixels to Voice: A Simple and Efficient End-to-End Spoken Image Description Approach via Vision Codec Language Models"],"prefix":"10.1109","author":[{"given":"Chung","family":"Tran","sequence":"first","affiliation":[{"name":"Nara Institute of Science and Technology,Graduate School of Science and Technology,Ikoma,Japan"}]},{"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology,Graduate School of Science and Technology,Ikoma,Japan"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 Technical Report","volume-title":"CoRR","year":"2023"},{"key":"ref2","article-title":"The Llama 3 Herd of Models","volume-title":"CoRR","author":"Dubey","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref4","article-title":"High Fidelity Neural Audio Compression","volume-title":"Trans. Mach. Learn. Res.","author":"D\u00e9fossez","year":"2023"},{"key":"ref5","article-title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","volume-title":"CoRR","author":"Wang","year":"2023"},{"key":"ref6","article-title":"Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling","volume-title":"CoRR","author":"Zhang","year":"2023"},{"key":"ref7","article-title":"Viola: Unified codec language models for speech recognition, synthesis, and translation","author":"Wang","year":"2023"},{"key":"ref8","article-title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","author":"Wang","year":"2024"},{"key":"ref9","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":"ref10","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia"},{"key":"ref11","article-title":"Ethnologue: Languages of the world","author":"Lewis","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.411"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446888"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3071541"},{"key":"ref15","article-title":"Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Harwath"},{"key":"ref16","article-title":"Neural discrete representation learning","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3033"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref22","article-title":"Simple and controllable music generation","volume":"36","author":"Copet","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","article-title":"Decoupled Weight Decay Regularization","volume-title":"7th International Conference on Learning Representations, ICLR 2019","author":"Loshchilov"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref25","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee"},{"key":"ref26","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proceedings of the Workshop on Text Summarization Branches Out","author":"Chin-Yew"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref28","article-title":"aac-metrics","author":"Labb\u00e9","year":"2024"}],"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\/10890285.pdf?arnumber=10890285","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:36Z","timestamp":1774416396000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890285\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890285","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}