{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:11:25Z","timestamp":1765357885967,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP210101093"],"award-info":[{"award-number":["DP210101093"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754810","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"5883-5892","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Pretraining Large Brain Language Model for Active BCI: Silent Speech"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6620-604X","authenticated-orcid":false,"given":"Jinzhao","family":"Zhou","sequence":"first","affiliation":[{"name":"University of Technology Sydeny, ULTIMO, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3656-0328","authenticated-orcid":false,"given":"Zehong","family":"Cao","sequence":"additional","affiliation":[{"name":"Adelaide University, Adelaide, SA, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1517-994X","authenticated-orcid":false,"given":"Yiqun","family":"Duan","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Ultimo, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3638-8931","authenticated-orcid":false,"given":"Connor","family":"Barkley","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, ULTIMO, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1678-5629","authenticated-orcid":false,"given":"Daniel","family":"Leong","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Ultimo, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3052-5193","authenticated-orcid":false,"given":"Xiaowei","family":"Jiang","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Ultimo, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9256-7087","authenticated-orcid":false,"given":"Quoc-Toan","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Ultimo, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3537-8065","authenticated-orcid":false,"given":"Ziyi","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Ultimo, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8597-5944","authenticated-orcid":false,"given":"Thomas","family":"Do","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Ultimo, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9244-0318","authenticated-orcid":false,"given":"Yu-Cheng","family":"Chang","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Ultimo, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6347-5017","authenticated-orcid":false,"given":"Sheng-Fu","family":"Liang","sequence":"additional","affiliation":[{"name":"National Cheng Kung University, Tainan, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8371-8197","authenticated-orcid":false,"given":"Chin-Teng","family":"Lin","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, ULTIMO, NSW, Australia"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2024.1429130"},{"key":"e_1_3_2_1_2_1","first-page":"67","volume-title":"Handbook of clinical neurology","author":"Wolpaw Jonathan R","year":"2013","unstructured":"Jonathan R Wolpaw. Brain-computer interfaces. In Handbook of clinical neurology, volume 110, pages 67-74. Elsevier, 2013."},{"key":"e_1_3_2_1_3_1","volume-title":"Progress in brain computer interface: Challenges and opportunities. Frontiers in systems neuroscience, 15:578875","author":"Saha Simanto","year":"2021","unstructured":"Simanto Saha, Khondaker A Mamun, Khawza Ahmed, Raqibul Mostafa, Ganesh R Naik, Sam Darvishi, Ahsan H Khandoker, and Mathias Baumert. Progress in brain computer interface: Challenges and opportunities. Frontiers in systems neuroscience, 15:578875, 2021."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2021.732764"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2016.2627556"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2184830"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2012.107"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21186285"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.939829"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-27725-3"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2012.10.014"},{"key":"e_1_3_2_1_12_1","volume-title":"Decoding the genetics of speech and language. Current opinion in neurobiology, 23(1):43-51","author":"Graham Sarah A","year":"2013","unstructured":"Sarah A Graham and Simon E Fisher. Decoding the genetics of speech and language. Current opinion in neurobiology, 23(1):43-51, 2013."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i5.20472"},{"key":"e_1_3_2_1_14_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Duan Yiqun","year":"2023","unstructured":"Yiqun Duan, Jinzhao Zhou, Zhen Wang, Yu-Kai Wang, and Chin teng Lin. Dewave: Discrete encoding of eeg waves for eeg to text translation. In Thirty-seventh Conference on Neural Information Processing Systems, 2023."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00714-5"},{"key":"e_1_3_2_1_16_1","volume-title":"Paul Boon, and Marc M Van Hulle. Imagined speech event detection from electrocorticography and its transfer between speech modes and subjects. communications biology, 7(1):818","author":"de Borman Aur\u00e9lie","year":"2024","unstructured":"Aur\u00e9lie de Borman, Benjamin Wittevrongel, Ine Dauwe, Evelien Carrette, Alfred Meurs, Dirk Van Roost, Paul Boon, and Marc M Van Hulle. Imagined speech event detection from electrocorticography and its transfer between speech modes and subjects. communications biology, 7(1):818, 2024."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1910939117"},{"key":"e_1_3_2_1_18_1","volume-title":"The auditory representation of speech sounds in human motor cortex. elife, 5:e12577","author":"Cheung Connie","year":"2016","unstructured":"Connie Cheung, Liberty S Hamilton, Keith Johnson, and Edward F Chang. The auditory representation of speech sounds in human motor cortex. elife, 5:e12577, 2016."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2018.01.080"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0207741"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.291"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1101\/2022.11.17.516860"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Alejandro P\u00e9rez Matthew H Davis Robin AA Ince Hanna Zhang Zhanao Fu Melanie Lamarca Matthew A Lambon Ralph and Philip J Monahan. Joint entrainment to the speech envelope during speaking and listening cannot completely explain brain-to-brain synchronisation. Joint entrainment to the speech envelope during speaking and listening cannot completely explain brain-to-brain synchronisation 2021.","DOI":"10.31234\/osf.io\/tzhn4"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.05.008"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01147-2"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178118"},{"key":"e_1_3_2_1_27_1","first-page":"1","volume-title":"Transactions on Machine Learning Research Journal","author":"Oquab Maxime","year":"2024","unstructured":"Maxime Oquab, Timoth\u00e9e Darcet, Th\u00e9o Moutakanni, Huy Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, et al. Dinov2: Learning robust visual features without supervision. Transactions on Machine Learning Research Journal, pages 1-31, 2024."},{"key":"e_1_3_2_1_28_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems, 33:1877-1901","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. Language models are few-shot learners. Advances in neural information processing systems, 33:1877-1901, 2020."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00714-5"},{"key":"e_1_3_2_1_30_1","volume-title":"Belt-2: Bootstrapping eeg-to-language representation alignment for multi-task brain decoding. arXiv preprint arXiv:2409.00121","author":"Zhou Jinzhao","year":"2024","unstructured":"Jinzhao Zhou, Yiqun Duan, Fred Chang, Thomas Do, Yu-Kai Wang, and Chin-Teng Lin. Belt-2: Bootstrapping eeg-to-language representation alignment for multi-task brain decoding. arXiv preprint arXiv:2409.00121, 2024."},{"key":"e_1_3_2_1_31_1","volume-title":"Large brain model for learning generic representations with tremendous eeg data in bci. arXiv preprint arXiv:2405.18765","author":"Jiang Wei-Bang","year":"2024","unstructured":"Wei-Bang Jiang, Li-Ming Zhao, and Bao-Liang Lu. Large brain model for learning generic representations with tremendous eeg data in bci. arXiv preprint arXiv:2405.18765, 2024."},{"key":"e_1_3_2_1_32_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Wang Guangyu","year":"2024","unstructured":"Guangyu Wang, Wenchao Liu, Yuhong He, Cong Xu, Lin Ma, and Haifeng Li. Eegpt: Pretrained transformer for universal and reliable representation of eeg signals. In The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024."},{"volume-title":"Forty-second International Conference on Machine Learning.","author":"Jayalath Dulhan","key":"e_1_3_2_1_33_1","unstructured":"Dulhan Jayalath, Gilad Landau, Brendan Shillingford, Mark Woolrich, and Oiwi Parker Jones. The brain's bitter lesson: Scaling speech decoding with self-supervised learning. In Forty-second International Conference on Machine Learning."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2013.06.034"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICORR.2019.8779499"},{"key":"e_1_3_2_1_36_1","volume-title":"Eeg classification of imagined syllable rhythm using hilbert spectrum methods. Journal of neural engineering, 7(4):046006","author":"Deng Siyi","year":"2010","unstructured":"Siyi Deng, Ramesh Srinivasan, Tom Lappas, and Michael D'Zmura. Eeg classification of imagined syllable rhythm using hilbert spectrum methods. Journal of neural engineering, 7(4):046006, 2010."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICHMS53169.2021.9582457"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2018.8512520"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.3390\/s20164629"},{"key":"e_1_3_2_1_40_1","volume-title":"Are eeg-to-text models working? arXiv preprint arXiv:2405.06459","author":"Jo Hyejeong","year":"2024","unstructured":"Hyejeong Jo, Yiqian Yang, Juhyeok Han, Yiqun Duan, Hui Xiong, and Won Hee Lee. Are eeg-to-text models working? arXiv preprint arXiv:2405.06459, 2024."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3688862.3689109"},{"key":"e_1_3_2_1_42_1","first-page":"78240","article-title":"Biosignal transformer for cross-data learning in the wild","volume":"36","author":"Yang Chaoqi","year":"2023","unstructured":"Chaoqi Yang, M Westover, and Jimeng Sun. Biot: Biosignal transformer for cross-data learning in the wild. Advances in Neural Information Processing Systems, 36:78240-78260, 2023.","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Wang Jiquan","key":"e_1_3_2_1_43_1","unstructured":"Jiquan Wang, Sha Zhao, Zhiling Luo, Yangxuan Zhou, Haiteng Jiang, Shijian Li, Tao Li, and Gang Pan. Cbramod: A criss-cross brain foundation model for eeg decoding. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-020-04954-0"},{"key":"e_1_3_2_1_45_1","volume-title":"N-beats: Neural basis expansion analysis for interpretable time series forecasting. arXiv preprint arXiv:1905.10437","author":"Oreshkin Boris N","year":"2019","unstructured":"Boris N Oreshkin, Dmitri Carpov, Nicolas Chapados, and Yoshua Bengio. N-beats: Neural basis expansion analysis for interpretable time series forecasting. arXiv preprint arXiv:1905.10437, 2019."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2019.07.001"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2021.03.012"},{"key":"e_1_3_2_1_48_1","volume-title":"A time series is worth 64 words: Long-term forecasting with transformers. arXiv preprint arXiv:2211.14730","author":"Nie Yuqi","year":"2022","unstructured":"Yuqi Nie, Nam H Nguyen, Phanwadee Sinthong, and Jayant Kalagnanam. A time series is worth 64 words: Long-term forecasting with transformers. arXiv preprint arXiv:2211.14730, 2022."},{"key":"e_1_3_2_1_49_1","volume-title":"A decoder-only foundation model for time-series forecasting. arXiv preprint arXiv:2310.10688","author":"Das Abhimanyu","year":"2023","unstructured":"Abhimanyu Das, Weihao Kong, Rajat Sen, and Yichen Zhou. A decoder-only foundation model for time-series forecasting. arXiv preprint arXiv:2310.10688, 2023."},{"key":"e_1_3_2_1_50_1","volume-title":"et al. Conformer: Convolution-augmented transformer for speech recognition. arXiv preprint arXiv:2005.08100","author":"Gulati Anmol","year":"2020","unstructured":"Anmol Gulati, James Qin, Chung-Cheng Chiu, Niki Parmar, Yu Zhang, Jiahui Yu, Wei Han, Shibo Wang, Zhengdong Zhang, Yonghui Wu, et al. Conformer: Convolution-augmented transformer for speech recognition. arXiv preprint arXiv:2005.08100, 2020."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1137\/20M1318043"},{"key":"e_1_3_2_1_54_1","unstructured":"Mihaela Rosca Yan Wu Chongli Qin and Benoit Dherin. On a continuous time model of gradient descent dynamics and instability in deep learning. Transactions on Machine Learning Research."},{"key":"e_1_3_2_1_55_1","volume-title":"Generalized huber loss for robust learning and its efficient minimization for a robust statistics. arXiv preprint arXiv:2108.12627","author":"Gokcesu Kaan","year":"2021","unstructured":"Kaan Gokcesu and Hakan Gokcesu. Generalized huber loss for robust learning and its efficient minimization for a robust statistics. arXiv preprint arXiv:2108.12627, 2021."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-021-02396-w"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMC42975.2020.9283028"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553378"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2007.914468"},{"key":"e_1_3_2_1_60_1","volume-title":"Eegnet: a compact convolutional neural network for eeg-based brain-computer interfaces. Journal of neural engineering, 15(5):056013","author":"Lawhern Vernon J","year":"2018","unstructured":"Vernon J Lawhern, Amelia J Solon, Nicholas R Waytowich, Stephen M Gordon, Chou P Hung, and Brent J Lance. Eegnet: a compact convolutional neural network for eeg-based brain-computer interfaces. Journal of neural engineering, 15(5):056013, 2018."},{"key":"e_1_3_2_1_61_1","volume-title":"Multiclass covert speech classification using extreme learning machine. Biomedical engineering letters, 10(2):217-226","author":"Pawar Dipti","year":"2020","unstructured":"Dipti Pawar and Sudhir Dhage. Multiclass covert speech classification using extreme learning machine. Biomedical engineering letters, 10(2):217-226, 2020."},{"key":"e_1_3_2_1_62_1","volume-title":"International conference on learning representations","author":"Kim Taesung","year":"2021","unstructured":"Taesung Kim, Jinhee Kim, Yunwon Tae, Cheonbok Park, Jang-Ho Choi, and Jaegul Choo. Reversible instance normalization for accurate time-series forecasting against distribution shift. In International conference on learning representations, 2021."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2022.3230250"},{"key":"e_1_3_2_1_64_1","volume-title":"Transformer-based spatial-temporal feature learning for eeg decoding. arXiv preprint arXiv:2106.11170","author":"Song Yonghao","year":"2021","unstructured":"Yonghao Song, Xueyu Jia, Lie Yang, and Longhan Xie. Transformer-based spatial-temporal feature learning for eeg decoding. arXiv preprint arXiv:2106.11170, 2021."},{"key":"e_1_3_2_1_65_1","volume-title":"Neurolm: A universal multi-task foundation model for bridging the gap between language and eeg signals. arXiv preprint arXiv:2409.00101","author":"Jiang Wei-Bang","year":"2024","unstructured":"Wei-Bang Jiang, Yansen Wang, Bao-Liang Lu, and Dongsheng Li. Neurolm: A universal multi-task foundation model for bridging the gap between language and eeg signals. arXiv preprint arXiv:2409.00101, 2024."},{"key":"e_1_3_2_1_66_1","volume-title":"Predicting human brain states with transformer. arXiv preprint arXiv:2412.19814","author":"Sun Yifei","year":"2024","unstructured":"Yifei Sun, Mariano Cabezas, Jiah Lee, Chenyu Wang, Wei Zhang, Fernando Calamante, and Jinglei Lv. Predicting human brain states with transformer. arXiv preprint arXiv:2412.19814, 2024."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754810","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:45:14Z","timestamp":1765309514000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754810"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":66,"alternative-id":["10.1145\/3746027.3754810","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754810","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}