{"id":"W3163016414","doi":"10.1109/icassp39728.2021.9413989","title":"A Deep Spatio-Temporal Model for EEG-Based Imagined Speech Recognition","year":2021,"lang":"en","type":"article","venue":"","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Speech recognition; Generalization; Convolutional neural network; Brain–computer interface; Interface (matter); Electroencephalography; Variety (cybernetics); Artificial intelligence; Long short term memory; Architecture; Recurrent neural network; Deep learning; Artificial neural network","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009222027,0.0001149557,0.0001206718,0.00005318127,0.00008194712,0.0001124901,0.0001365013,0.00004079863,0.0002371865],"category_scores_gemma":[0.0002154474,0.0001038976,0.00008744642,0.0001485643,0.00003388417,0.0001999587,0.00003621465,0.00007047986,0.00006550597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002092836,"about_ca_system_score_gemma":0.00009025473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000125388,"about_ca_topic_score_gemma":0.000116284,"domain_scores_codex":[0.9990066,0.00004458806,0.0001823486,0.0003978335,0.0001549182,0.0002137445],"domain_scores_gemma":[0.9993865,0.0002038899,0.00004950799,0.000174812,0.0001248331,0.00006048324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004913287,0.001157438,0.0008277684,0.0002896268,0.00002323677,0.0001915478,0.0008322571,0.02049516,0.7210615,0.002740768,0.0541412,0.1977482],"study_design_scores_gemma":[0.0003477623,0.00002836543,0.000006641515,0.000008625964,0.000003780998,0.000007710718,0.00001007513,0.5349193,0.4611237,0.002838337,0.000620121,0.00008553018],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2026263,0.00001114949,0.7896481,0.002228714,0.0001743097,0.0002585326,0.00002284289,0.0001839593,0.004846036],"genre_scores_gemma":[0.9042951,0.000001262599,0.08806242,0.004669917,0.00005436033,0.00003202643,0.00006477002,0.0000166012,0.002803551],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7016687,"threshold_uncertainty_score":0.4236819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05827492703207727,"score_gpt":0.2913077479228913,"score_spread":0.2330328208908141,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}