{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T17:14:39Z","timestamp":1761930879737,"version":"build-2065373602"},"reference-count":23,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209914","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":["Zero-Shot Speech Perception Decoding via Advancing Representation Consistency"],"prefix":"10.1109","author":[{"given":"Yi","family":"Xiao","sequence":"first","affiliation":[{"name":"Beijing Normal University,School of Artificial Intelligence,China"}]},{"given":"XuYi","family":"Qiao","sequence":"additional","affiliation":[{"name":"Beijing Normal University,School of Artificial Intelligence,China"}]},{"given":"Yu-Xuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Normal University,State Key Laboratory of Cognitive Neuroscience and Learning,China"}]},{"given":"Xianchuan","family":"Yu","sequence":"additional","affiliation":[{"name":"Beijing Normal University,School of Artificial Intelligence,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108705"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03506-2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1812757"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2300807"},{"article-title":"The brain\u2019s bitter lesson: Scaling speech decoding with self-supervised learning","year":"2024","author":"Jayalath","key":"ref5"},{"article-title":"Visual neural decoding via improved visual-eeg semantic consistency","year":"2024","author":"Chen","key":"ref6"},{"article-title":"How Many Bytes Can You Take Out Of Brain-To-Text Decoding?","year":"2024","author":"Antonello","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-023-01304-9"},{"article-title":"CLIPMUSED: clip-guided multi-subject visual neural information semantic decoding","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","author":"Zhou","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02175"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00714-5"},{"article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","key":"ref12"},{"article-title":"Decoding Natural Images from EEG for Object Recognition","volume-title":"International Conference on Learning Representations","author":"Song","key":"ref13"},{"article-title":"Visual decoding and reconstruction via eeg embeddings with guided diffusion","year":"2024","author":"Li","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"article-title":"Mad: Multi-alignment meg-to-text decoding","year":"2024","author":"Yang","key":"ref16"},{"key":"ref17","article-title":"EEG2Video: Towards decoding dynamic visual perception from EEG signals","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume-title":"NeurIPS","author":"Liang","key":"ref18"},{"key":"ref19","first-page":"21927","article-title":"Self-supervised models of audio effectively explain human cortical responses to speech","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Vaidya"},{"key":"ref20","first-page":"33428","article-title":"Toward a realistic model of speech processing in the brain with self-supervised learning","volume":"35","author":"MILLET","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","article-title":"Achieving cross modal generalization with multimodal unified representation","volume":"36","author":"Xia","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3325533"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02752-5"}],"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\/11209914.pdf?arnumber=11209914","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T17:09:11Z","timestamp":1761930551000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209914\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209914","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}