[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83750-en":3,"doc-seo-83750-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83750,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","EEG-Based Imagined Speech Decoding Using a Hybrid CNN-SNN Architecture","Imagined speech decoding from EEG signals is a key direction for brain-computer interfaces aimed at restoring communication for people with severe speech impairments. The task is difficult because EEG is non-stationary, low in amplitude, and highly variable. Conventional ML and deep learning methods do not capture spike-driven temporal dynamics modeled by spiking neural networks. This work proposes a hybrid pipeline that couples CNN-based temporal representation learning with SNN-based event-driven classification, achieving 80.13% accuracy on the 2020 BCI Competition III benchmark, exceeding prior reported results up to 70.19%.","EEG-Based Imagined Speech Decoding Using a Hybrid CNN-SNN Architecture  \nFatima Shalhoub∗ , Mariam Al Mawla∗†, Kabalan Chaccour∗‡, Senior Member, IEEE, Ivn Lpez-Espejo§  \nHoda Fares¶∥ , Member, IEEE  \n∗ TICKET Lab., Antonine University, Hadat-Baabda, Lebanon  \n† Doctoral School of Science, Technology, and Engineering, University of Granada, Granada, Spain  \n‡ University of Technology Belfort-Montbliard, SINERGIES, F-90000 Belfort, France  \n§ Department of Signal Theory, Telematics and Communications, University of Granada, Granada, Spain ¶ Department of Chemical Engineering, Stanford University, Stanford, USA ∥ Department of Electrical and Computer Engineering, Aarhus University, Denmark  \narXiv :2607 .03844v 1 [ cs . SD] 4 Jul 2026  \nAbstract—Imagined speech decoding using EEG signals has emerged as a promising frontier in brain-computer interface (BCI) research, particularly to restore communication for individuals with severe speech impairments. However, decoding imagined speech remains a complex task due to the nonstationary, low-amplitude, and highly variable nature of EEG signals. Existing methods often rely on classical machine learning or deep learning models that fail to exploit spike-based temporal dynamics or event-driven firing mechanisms of biological neurons, which are naturally modeled by spiking neural networks (SNNs). In this study, we propose a hybrid decoding pipeline that extracts temporal representations using convolutional neural networks (CNNs) followed by biologically inspired temporal classification via SNNs. To our knowledge, this is the first study to integrate SNNs into EEG-based imagined speech decoding. Experimental results show that the proposed CNN-SNN architecture achieves an accuracy of 80.13% on the 2020 BCI Competition III benchmark, surpassing existing methods reported in the literature (up to 70.19%) under comparable evaluation settings. These findings demonstrate the effectiveness of spikebased temporal decoding for imagined speech, highlighting the promise of biologically grounded pipelines for next generation neuromorphic BCI applications.  \nIndex Terms—Brain-Computer Interface (BCI), Imagined Speech Decoding, Spiking Neural Network (SNN), Hybrid CNNSNN, EEG Signals, Neuromorphic Computing.  \nI. INTRODUCTION  \nSpeech is the natural form of communication between humans. Scientists differentiate two types of speech: 1) overt speech, which involves vocal and muscle articulations, and 2) covert speech, which refers to inner speech that requires only internal activity of the brain [1] .  \nOvert speech can be adversely affected by a range of neurological disorders that disrupt the neural mechanisms underlying speech production. In particular, cerebrovascular accidents, including cerebellar strokes, are well known to impair motor speech control, resulting in reduced speech clarity and limited verbal communication abilities [2] . Nevertheless, cognitive and linguistic functions may remain relatively preserved despite severe motor impairment. Brain-computer interfaces (BCIs) provide a promising assistive technology in decoding covert speech directly from neural activity. The clinical potential of  \nthis field has been significantly highlighted by recent advancements in high-bandwidth neural implants which have opened new horizons for speech restoration [3] . However, while invasive systems show great promise, there is a parallel need for robust non-invasive solutions. For instance, the authors in [4] demonstrated the feasibility of using electroencephalography (EEG) to establish a bidirectional communication channel between the brain and external environments.  \nThe integration of AI into BCI systems has significantly refined the interpretation of complex brain signals, offering new perspectives in healthcare [5] . AI-enabled BCIs currently facilitate diagnostic precision and assistive communication for individuals with severe speech impairment [6] . Decoding covert speech is vital for restoring","cbCaio5EyM9SNwGC","https://ap.wps.com/l/cbCaio5EyM9SNwGC","pdf",1166557,4,1,6,"English","en",105,"# Introduction\n## Speech types and clinical motivation\n## Role of AI and EEG-based decoding\n## Limitations of conventional ML/DL\n## Contribution of the proposed CNN-SNN approach","[{\"question\":\"Why is imagined speech decoding from EEG considered challenging?\",\"answer\":\"EEG signals are non-stationary, low-amplitude, and highly variable, producing complex neural signatures with low signal-to-noise ratio.\"},{\"question\":\"What limitation of existing ML/DL methods motivates the proposed approach?\",\"answer\":\"Many conventional models use continuous-valued activations and do not explicitly model the event-driven spike dynamics inherent in neural activity, which SNNs can better represent.\"},{\"question\":\"How does the proposed hybrid CNN-SNN architecture work and what performance does it reach?\",\"answer\":\"The pipeline uses a CNN to extract temporal representations and an SNN for spike-based temporal classification. It reports 80.13% accuracy on the 2020 BCI Competition III benchmark, outperforming prior methods up to 70.19% under comparable settings.\"}]",1784190202,15,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"eeg-based-imagined-speech-decoding-using-a-hybrid-cnn-snn-architecture","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/eeg-based-imagined-speech-decoding-using-a-hybrid-cnn-snn-architecture/83750/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-26","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is imagined speech decoding from EEG considered challenging?","Question",{"text":75,"@type":76},"EEG signals are non-stationary, low-amplitude, and highly variable, producing complex neural signatures with low signal-to-noise ratio.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What limitation of existing ML/DL methods motivates the proposed approach?",{"text":80,"@type":76},"Many conventional models use continuous-valued activations and do not explicitly model the event-driven spike dynamics inherent in neural activity, which SNNs can better represent.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed hybrid CNN-SNN architecture work and what performance does it reach?",{"text":84,"@type":76},"The pipeline uses a CNN to extract temporal representations and an SNN for spike-based temporal classification. It reports 80.13% accuracy on the 2020 BCI Competition III benchmark, outperforming prior methods up to 70.19% under comparable settings.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]