{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:11:25Z","timestamp":1761894685860,"version":"build-2065373602"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210156","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Multi-modal Speech Transformer Decoders: When Do Multiple Modalities Improve Accuracy?"],"prefix":"10.1109","author":[{"given":"Yiwen","family":"Guan","sequence":"first","affiliation":[{"name":"Worcester Polytechnic Institute"}]},{"given":"Viet Anh","family":"Trinh","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute"}]},{"given":"Vivek","family":"Voleti","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute"}]},{"given":"Jacob","family":"Whitehill","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447929"},{"article-title":"Gemini: a family of highly capable multimodal models","year":"2023","author":"Team","key":"ref2"},{"article-title":"Discrete multimodal transformers with a pretrained large language model for mixed-supervision speech processing","year":"2024","author":"Trinh","key":"ref3"},{"key":"ref4","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1669"},{"article-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.alvr-1.11"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1111\/bjet.13518"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/math11122665"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/s23042284"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3163771"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00229"},{"article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"International Conference on Learning Representations","author":"Shi","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01801"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448079"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.738"},{"article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","year":"2023","author":"Chu","key":"ref21"},{"key":"ref22","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"article-title":"Minigpt5: Interleaved vision-and-language generation via generative vokens","year":"2023","author":"Zheng","key":"ref23"},{"article-title":"Next-gpt: Any-to-any multimodal llm","volume-title":"Forty-first International Conference on Machine Learning","author":"Wu","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.666"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889251"},{"key":"ref27","article-title":"pyttsx3: Offline text to speech (tts) converter for python"},{"key":"ref28","article-title":"Easyocr: Ready-to-use ocr with 80+ supported languages"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"article-title":"Musan: A music, speech, and noise corpus","year":"2015","author":"Snyder","key":"ref30"},{"article-title":"Opt: Open pretrained transformer language models","year":"2022","author":"Zhang","key":"ref31"},{"article-title":"Seamlessm4t-massively multilingual & multimodal machine translation","year":"2023","author":"Barrault","key":"ref32"},{"key":"ref33","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"article-title":"Cvss corpus and massively multilingual speech-to-speech translation","year":"2022","author":"Jia","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2027"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","key":"ref38"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210156.pdf?arnumber=11210156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:33:36Z","timestamp":1761888816000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210156\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210156","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}