{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:23:35Z","timestamp":1778603015490,"version":"3.51.4"},"reference-count":25,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"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":["IEEE J. Biomed. Health Inform."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/jbhi.2025.3618998","type":"journal-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:41:40Z","timestamp":1765219300000},"page":"8735-8742","source":"Crossref","is-referenced-by-count":1,"title":["Optimizing Deep Neural Networks for EEG-Based Speech Recognition: A Multimodal Approach to Assistive Communication"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8146-2482","authenticated-orcid":false,"given":"Anarghya","family":"Das","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2267-2256","authenticated-orcid":false,"given":"Puru","family":"Soni","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9408-4724","authenticated-orcid":false,"given":"Hubin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Medical Physics and Biomedical Engineering, University College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming-Chun","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Data and Computational Science, Duke Kunshan University, Kunshan, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6444-9411","authenticated-orcid":false,"given":"Wenyao","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Augmentative & Alternative Communication: Supporting Children and Adults With Complex Communication Needs","author":"Beukelman","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10073-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1159\/000511042"},{"key":"ref4","first-page":"131858","article-title":"Automatic speech recognition: Systematic literature review","volume":"9","author":"Alharbi","year":"2021"},{"key":"ref5","first-page":"63","article-title":"Automatic speech recognition models for pathological speech: Challenges and insights","volume-title":"Proc. 32nd Ir. Conf. Artif. Intell. Cogn. Sci.","author":"Mokgosi","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1523\/eneuro.0057-19.2019"},{"issue":"6","key":"ref7","first-page":"935","article-title":"The neural encoding of continuous speech - recent advances in EEG and MEG studies","volume":"71","author":"Pan","year":"2019","journal-title":"Acta Physiologica Sinica"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1044\/2024_ajslp-24-00285"},{"key":"ref9","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref10","article-title":"Opportunities, pitfalls and trade-offs in designing protocols for measuring the neural correlates of speech","volume-title":"Neurosci. Biobehavioral Rev.","volume":"140","author":"Cooney","year":"2022"},{"key":"ref11","article-title":"A state-of-the-art review of EEG-Based imagined speech decoding","volume-title":"Front. Hum. Neurosci.","volume":"16","author":"Lopez-Bernal","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.642251"},{"key":"ref13","article-title":"Decoding imagined speech with delay differential analysis","volume-title":"Front. Hum. Neurosci.","volume":"18","author":"Carvalho","year":"2024"},{"key":"ref14","article-title":"Multimodal speech recognition using EEG and audio signals: A novel approach for enhancing ASR systems","volume-title":"Smart Health","volume":"32","author":"Das","year":"2024"},{"key":"ref15","first-page":"113769","article-title":"Deep learning approaches for bimodal speech emotion recognition: Advancements, challenges, and a multi-learning model","volume-title":"IEEE Access","volume":"11","author":"Kakuba","year":"2023"},{"key":"ref16","first-page":"1","article-title":"Feature importance and model performance in deep learning for speech emotion recognition","volume-title":"Proc. 11th Int. Conf. Adv. Comput. Commun. (ICACC)","author":"P","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2024.1493163"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1117\/12.2255697"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178118"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2023.1194554"},{"issue":"13","key":"ref21","article-title":"CNN architectures and feature extraction methods for EEG imaginary speech recognition","volume-title":"Sensors","volume":"22","author":"Rusnac","year":"2022"},{"issue":"4","key":"ref22","first-page":"357","article-title":"Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences","volume-title":"IEEE Trans. Acoust. Speech Signal Process.","volume":"28","author":"Davis","year":"1980"},{"key":"ref23","first-page":"1090","article-title":"Speech recognition with no speech or with noisy speech","volume-title":"Proc. 2019 IEEE Int. Conf. Acoust. Speech Signal Process. (ICASSP)","author":"Krishna","year":"2019"},{"key":"ref24","article-title":"Deep multimodal fusion for semantic image segmentation: A survey","volume-title":"Image Vis. Comput.","volume":"105","author":"Zhang","year":"2021"},{"key":"ref25","first-page":"143","article-title":"The aligned rank transform for nonparametric factorial analyses using only anova procedures","volume-title":"Proc. ACM Conf. Hum. Factors Comput. Syst.","author":"Wobbrock","year":"2011"}],"container-title":["IEEE Journal of Biomedical and Health Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221020\/11284538\/11283642.pdf?arnumber=11283642","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:34:15Z","timestamp":1766082855000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11283642\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":25,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/jbhi.2025.3618998","relation":{},"ISSN":["2168-2194","2168-2208"],"issn-type":[{"value":"2168-2194","type":"print"},{"value":"2168-2208","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}