{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:19:14Z","timestamp":1775578754427,"version":"3.50.1"},"reference-count":104,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2022R1A2C2005529"],"award-info":[{"award-number":["NRF-2022R1A2C2005529"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information & communications Technology Planning & Evaluation","award":["RS-2022-II220124"],"award-info":[{"award-number":["RS-2022-II220124"]}]},{"name":"BK21 FOUR","award":["4120200113769"],"award-info":[{"award-number":["4120200113769"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3659297","type":"journal-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T21:25:04Z","timestamp":1769721904000},"page":"1976-1988","source":"Crossref","is-referenced-by-count":1,"title":["TMT: Tri-Modal Translation Between Speech, Image, and Text by Processing Different Modalities as Different Languages"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6514-0018","authenticated-orcid":false,"given":"Minsu","family":"Kim","sequence":"first","affiliation":[{"name":"Integrated Vision and Language Lab., School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0505-2988","authenticated-orcid":false,"given":"Jee-weon","family":"Jung","sequence":"additional","affiliation":[{"name":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9301-2760","authenticated-orcid":false,"given":"Hyeongseop","family":"Rha","sequence":"additional","affiliation":[{"name":"Integrated Vision and Language Lab., School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6940-0115","authenticated-orcid":false,"given":"Soumi","family":"Maiti","sequence":"additional","affiliation":[{"name":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siddhant","family":"Arora","sequence":"additional","affiliation":[{"name":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5221-5412","authenticated-orcid":false,"given":"Xuankai","family":"Chang","sequence":"additional","affiliation":[{"name":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5306-6853","authenticated-orcid":false,"given":"Yong Man","family":"Ro","sequence":"additional","affiliation":[{"name":"Integrated Vision and Language Lab., School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3009500"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291503"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3150469"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01801"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447215"},{"key":"ref8","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref10","first-page":"53366","article-title":"Next-GPT: Any-to-any multimodal LLM","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu","year":"2024"},{"key":"ref11","article-title":"Imagebind-LLM: Multi-modality instruction tuning","author":"Han","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2051"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446888"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1346"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3444470"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_25"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447112"},{"key":"ref23","article-title":"Planting a seed of vision in large language model","author":"Ge","year":"2023"},{"key":"ref24","article-title":"Making LLaMA see and draw with seed tokenizer","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Ge","year":"2024"},{"key":"ref25","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref27","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref29","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref30","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"},{"key":"ref31","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref32","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref33","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.411"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3071541"},{"key":"ref36","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Den","year":"2017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref38","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref42","first-page":"4055","article-title":"MUSE: Text-to-image generation via masked generative transformers","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Chang","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3358086"},{"key":"ref44","first-page":"21487","article-title":"Generating images with multimodal language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Koh","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987417"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1759"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.63"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12007"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3092187"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1525\/9780520940420-020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.34"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.68"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1951"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17684"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3324540"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41676-7_28"},{"key":"ref58","article-title":"High fidelity neural audio compression","volume-title":"Trans. Mach. Learn. Res.","author":"Dfossez","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3530270"},{"key":"ref60","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00430"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11032"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02580"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref67","article-title":"Discretalk: Text-to-speech as a machine translation problem","author":"Hayashi","year":"2020"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01582"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681221"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"ref73","article-title":"Cross-lingual language model pretraining","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Conneau","year":"2019"},{"key":"ref74","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amodei","year":"2016"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3328283"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-0827-1"},{"key":"ref78","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Ardila","year":"2020"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref84","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref85","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref89","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.373"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120644"},{"key":"ref94","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref95","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kong","year":"2020"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.235"},{"key":"ref97","article-title":"The LJ speech dataset","author":"Ito"},{"key":"ref98","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2021"},{"key":"ref99","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref100","article-title":"amused: An open muse reproduction","author":"Patil","year":"2024"},{"key":"ref101","first-page":"1692","article-title":"One transformer fits all distributions in multi-modal diffusion at scale","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bao","year":"2023"},{"key":"ref102","article-title":"Vector-quantized image modeling with improved VQGAN","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu","year":"2021"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095710"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11367782.pdf?arnumber=11367782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T19:59:09Z","timestamp":1773086349000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11367782\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":104,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3659297","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}