{"id":4932,"date":"2022-09-29T01:34:16","date_gmt":"2022-09-28T23:34:16","guid":{"rendered":"https:\/\/equinoxgroup.eu\/?p=4932"},"modified":"2022-11-23T21:10:25","modified_gmt":"2022-11-23T20:10:25","slug":"an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy","status":"publish","type":"post","link":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/","title":{"rendered":"An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy"},"content":{"rendered":"<div class=\"wpb-content-wrapper\"><p>[vc_row css=&#8221;.vc_custom_1667941658566{margin-top: -320px !important;margin-bottom: 419px !important;}&#8221; el_class=&#8221;vc_hidden-sm vc_hidden-xs&#8221;][vc_column][vc_row_inner][vc_column_inner][vc_column_text css=&#8221;.vc_custom_1667850591729{padding-top: -200px !important;}&#8221;]<\/p>\r\n<p><span data-offset-key=\"7pffb-19-0\">Spe<\/span><span data-offset-key=\"7pffb-20-0\">ech<\/span><span data-offset-key=\"7pffb-21-0\"> is<\/span><span data-offset-key=\"7pffb-22-0\"> an<\/span><span data-offset-key=\"7pffb-23-0\"> essential<\/span><span data-offset-key=\"7pffb-24-0\"> part<\/span><span data-offset-key=\"7pffb-25-0\"> of<\/span><span data-offset-key=\"7pffb-26-0\"> human<\/span><span data-offset-key=\"7pffb-27-0\"> communication<\/span><span data-offset-key=\"7pffb-28-0\">.<\/span><span data-offset-key=\"7pffb-29-0\"> It<\/span><span data-offset-key=\"7pffb-30-0\"> is<\/span><span data-offset-key=\"7pffb-31-0\"> the<\/span><span data-offset-key=\"7pffb-32-0\"> ability<\/span><span data-offset-key=\"7pffb-33-0\"> to<\/span><span data-offset-key=\"7pffb-34-0\"> express<\/span><span data-offset-key=\"7pffb-35-0\"> thoughts<\/span><span data-offset-key=\"7pffb-36-0\"> and<\/span><span data-offset-key=\"7pffb-37-0\"> feelings<\/span><span data-offset-key=\"7pffb-38-0\"> through<\/span><span data-offset-key=\"7pffb-39-0\"> the<\/span><span data-offset-key=\"7pffb-40-0\"> use<\/span><span data-offset-key=\"7pffb-41-0\"> of<\/span><span data-offset-key=\"7pffb-42-0\"> spoken<\/span><span data-offset-key=\"7pffb-43-0\"> language<\/span><span data-offset-key=\"7pffb-44-0\">.<\/span><span data-offset-key=\"7pffb-45-0\"> The<\/span><span data-offset-key=\"7pffb-46-0\"> brain<\/span><span data-offset-key=\"7pffb-47-0\"> is<\/span><span data-offset-key=\"7pffb-48-0\"> responsible<\/span><span data-offset-key=\"7pffb-49-0\"> for<\/span><span data-offset-key=\"7pffb-50-0\"> the<\/span><span data-offset-key=\"7pffb-51-0\"> production<\/span><span data-offset-key=\"7pffb-52-0\"> of<\/span><span data-offset-key=\"7pffb-53-0\"> speech<\/span><span data-offset-key=\"7pffb-54-0\">.<\/span><span data-offset-key=\"7pffb-55-0\"> This<\/span><span data-offset-key=\"7pffb-56-0\"> process<\/span><span data-offset-key=\"7pffb-57-0\"> involves<\/span><span data-offset-key=\"7pffb-58-0\"> the<\/span><span data-offset-key=\"7pffb-59-0\"> coordination<\/span><span data-offset-key=\"7pffb-60-0\"> of<\/span><span data-offset-key=\"7pffb-61-0\"> many<\/span><span data-offset-key=\"7pffb-62-0\"> different<\/span><span data-offset-key=\"7pffb-63-0\"> muscles<\/span><span data-offset-key=\"7pffb-64-0\"> and<\/span><span data-offset-key=\"7pffb-65-0\"> structures<\/span><span data-offset-key=\"7pffb-66-0\"> in<\/span><span data-offset-key=\"7pffb-67-0\"> the<\/span><span data-offset-key=\"7pffb-68-0\"> body<\/span><span data-offset-key=\"7pffb-69-0\">,<\/span><span data-offset-key=\"7pffb-70-0\"> including<\/span><span data-offset-key=\"7pffb-71-0\"> the<\/span><span data-offset-key=\"7pffb-72-0\"> vocal<\/span><span data-offset-key=\"7pffb-73-0\"> cords<\/span><span data-offset-key=\"7pffb-74-0\">,<\/span><span data-offset-key=\"7pffb-75-0\"> lips<\/span><span data-offset-key=\"7pffb-76-0\">,<\/span><span data-offset-key=\"7pffb-77-0\"> tongue<\/span><span data-offset-key=\"7pffb-78-0\">,<\/span><span data-offset-key=\"7pffb-79-0\"> and<\/span><span data-offset-key=\"7pffb-80-0\"> teeth<\/span><span data-offset-key=\"7pffb-81-0\">.<\/span> <span data-offset-key=\"7pffb-84-0\">Brain<\/span><span data-offset-key=\"7pffb-85-0\"> activity<\/span><span data-offset-key=\"7pffb-86-0\"> plays<\/span><span data-offset-key=\"7pffb-87-0\"> a<\/span><span data-offset-key=\"7pffb-88-0\"> vital<\/span><span data-offset-key=\"7pffb-89-0\"> role<\/span><span data-offset-key=\"7pffb-90-0\"> in<\/span><span data-offset-key=\"7pffb-91-0\"> speech<\/span><span data-offset-key=\"7pffb-92-0\"> production<\/span><span data-offset-key=\"7pffb-93-0\">.<\/span><span data-offset-key=\"7pffb-94-0\"> The<\/span><span data-offset-key=\"7pffb-95-0\"> motor<\/span><span data-offset-key=\"7pffb-96-0\"> cortex<\/span><span data-offset-key=\"7pffb-97-0\"> is<\/span><span data-offset-key=\"7pffb-98-0\"> responsible<\/span><span data-offset-key=\"7pffb-99-0\"> for<\/span><span data-offset-key=\"7pffb-100-0\"> controlling<\/span><span data-offset-key=\"7pffb-101-0\"> the<\/span><span data-offset-key=\"7pffb-102-0\"> muscles<\/span><span data-offset-key=\"7pffb-103-0\"> used<\/span><span data-offset-key=\"7pffb-104-0\"> in<\/span><span data-offset-key=\"7pffb-105-0\"> speaking<\/span><span data-offset-key=\"7pffb-106-0\">.<\/span><span data-offset-key=\"7pffb-107-0\"> This<\/span><span data-offset-key=\"7pffb-108-0\"> area<\/span><span data-offset-key=\"7pffb-109-0\"> of<\/span><span data-offset-key=\"7pffb-110-0\"> the<\/span><span data-offset-key=\"7pffb-111-0\"> brain<\/span><span data-offset-key=\"7pffb-112-0\"> sends<\/span><span data-offset-key=\"7pffb-113-0\"> signals<\/span><span data-offset-key=\"7pffb-114-0\"> to<\/span><span data-offset-key=\"7pffb-115-0\"> the<\/span><span data-offset-key=\"7pffb-116-0\"> muscles<\/span><span data-offset-key=\"7pffb-117-0\"> that<\/span><span data-offset-key=\"7pffb-118-0\"> control<\/span><span data-offset-key=\"7pffb-119-0\"> the<\/span><span data-offset-key=\"7pffb-120-0\"> movement<\/span><span data-offset-key=\"7pffb-121-0\"> of<\/span><span data-offset-key=\"7pffb-122-0\"> the<\/span><span data-offset-key=\"7pffb-123-0\"> vocal<\/span><span data-offset-key=\"7pffb-124-0\"> cords<\/span><span data-offset-key=\"7pffb-125-0\">,<\/span><span data-offset-key=\"7pffb-126-0\"> lips<\/span><span data-offset-key=\"7pffb-127-0\">,<\/span><span data-offset-key=\"7pffb-128-0\"> tongue<\/span><span data-offset-key=\"7pffb-129-0\">,<\/span><span data-offset-key=\"7pffb-130-0\"> and<\/span><span data-offset-key=\"7pffb-131-0\"> teeth<\/span><span data-offset-key=\"7pffb-132-0\">.<\/span><span data-offset-key=\"7pffb-133-0\"> These<\/span><span data-offset-key=\"7pffb-134-0\"> signals<\/span><span data-offset-key=\"7pffb-135-0\"> tell<\/span><span data-offset-key=\"7pffb-136-0\"> the<\/span><span data-offset-key=\"7pffb-137-0\"> muscles<\/span><span data-offset-key=\"7pffb-138-0\"> when<\/span><span data-offset-key=\"7pffb-139-0\"> to<\/span><span data-offset-key=\"7pffb-140-0\"> contract<\/span><span data-offset-key=\"7pffb-141-0\"> and<\/span><span data-offset-key=\"7pffb-142-0\"> relax<\/span><span data-offset-key=\"7pffb-143-0\"> in<\/span><span data-offset-key=\"7pffb-144-0\"> order<\/span><span data-offset-key=\"7pffb-145-0\"> to<\/span><span data-offset-key=\"7pffb-146-0\"> produce<\/span><span data-offset-key=\"7pffb-147-0\"> sound<\/span><span data-offset-key=\"7pffb-148-0\">.<\/span> <span data-offset-key=\"7pffb-151-0\">Brain<\/span><span data-offset-key=\"7pffb-152-0\">&#8211;<\/span><span data-offset-key=\"7pffb-153-0\">machine<\/span><span data-offset-key=\"7pffb-154-0\"> interfaces<\/span><span data-offset-key=\"7pffb-155-0\"> (<\/span><span data-offset-key=\"7pffb-156-0\">BM<\/span><span data-offset-key=\"7pffb-157-0\">Is<\/span><span data-offset-key=\"7pffb-158-0\">)<\/span><span data-offset-key=\"7pffb-159-0\"> are<\/span><span data-offset-key=\"7pffb-160-0\"> devices<\/span><span data-offset-key=\"7pffb-161-0\"> that<\/span><span data-offset-key=\"7pffb-162-0\"> allow<\/span><span data-offset-key=\"7pffb-163-0\"> humans<\/span><span data-offset-key=\"7pffb-164-0\"> to<\/span><span data-offset-key=\"7pffb-165-0\"> control<\/span><span data-offset-key=\"7pffb-166-0\"> machines<\/span><span data-offset-key=\"7pffb-167-0\"> with<\/span><span data-offset-key=\"7pffb-168-0\"> their<\/span><span data-offset-key=\"7pffb-169-0\"> thoughts<\/span><span data-offset-key=\"7pffb-170-0\">.<\/span><span data-offset-key=\"7pffb-171-0\"> BM<\/span><span data-offset-key=\"7pffb-172-0\">Is<\/span><span data-offset-key=\"7pffb-173-0\"> can<\/span><span data-offset-key=\"7pffb-174-0\"> be<\/span><span data-offset-key=\"7pffb-175-0\"> used<\/span><span data-offset-key=\"7pffb-176-0\"> to<\/span><span data-offset-key=\"7pffb-177-0\"> control<\/span><span data-offset-key=\"7pffb-178-0\"> robotic<\/span><span data-offset-key=\"7pffb-179-0\"> arms<\/span><span data-offset-key=\"7pffb-180-0\"> or<\/span><span data-offset-key=\"7pffb-181-0\"> legs<\/span><span data-offset-key=\"7pffb-182-0\">,<\/span><span data-offset-key=\"7pffb-183-0\"> prost<\/span><span data-offset-key=\"7pffb-184-0\">hetic<\/span><span data-offset-key=\"7pffb-185-0\"> devices<\/span><span data-offset-key=\"7pffb-186-0\">,<\/span><span data-offset-key=\"7pffb-187-0\"> or<\/span><span data-offset-key=\"7pffb-188-0\"> even<\/span><span data-offset-key=\"7pffb-189-0\"> computer<\/span><span data-offset-key=\"7pffb-190-0\"> curs<\/span><span data-offset-key=\"7pffb-191-0\">ors<\/span><span data-offset-key=\"7pffb-192-0\">.<\/span><span data-offset-key=\"7pffb-193-0\"> In<\/span><span data-offset-key=\"7pffb-194-0\"> some<\/span><span data-offset-key=\"7pffb-195-0\"> cases<\/span><span data-offset-key=\"7pffb-196-0\">,<\/span><span data-offset-key=\"7pffb-197-0\"> BM<\/span><span data-offset-key=\"7pffb-198-0\">Is<\/span><span data-offset-key=\"7pffb-199-0\"> have<\/span><span data-offset-key=\"7pffb-200-0\"> been<\/span><span data-offset-key=\"7pffb-201-0\"> used<\/span><span data-offset-key=\"7pffb-202-0\"> to<\/span><span data-offset-key=\"7pffb-203-0\"> restore<\/span><span data-offset-key=\"7pffb-204-0\"> lost<\/span><span data-offset-key=\"7pffb-205-0\"> functions<\/span><span data-offset-key=\"7pffb-206-0\"> such<\/span><span data-offset-key=\"7pffb-207-0\"> as<\/span><span data-offset-key=\"7pffb-208-0\"> movement<\/span><span data-offset-key=\"7pffb-209-0\"> or<\/span><span data-offset-key=\"7pffb-210-0\"> speech<\/span><span data-offset-key=\"7pffb-211-0\">.<\/span> <span data-offset-key=\"7pffb-214-0\"> BM<\/span><span data-offset-key=\"7pffb-215-0\">Is<\/span><span data-offset-key=\"7pffb-216-0\"> work<\/span><span data-offset-key=\"7pffb-217-0\"> by<\/span><span data-offset-key=\"7pffb-218-0\"> reading<\/span><span data-offset-key=\"7pffb-219-0\"> electrical<\/span><span data-offset-key=\"7pffb-220-0\"> activity<\/span><span data-offset-key=\"7pffb-221-0\"> in<\/span><span data-offset-key=\"7pffb-222-0\"> the<\/span><span data-offset-key=\"7pffb-223-0\"> brain<\/span><span data-offset-key=\"7pffb-224-0\">.<\/span><span data-offset-key=\"7pffb-225-0\"> This<\/span><span data-offset-key=\"7pffb-226-0\"> activity<\/span><span data-offset-key=\"7pffb-227-0\"> is<\/span><span data-offset-key=\"7pffb-228-0\"> detected<\/span><span data-offset-key=\"7pffb-229-0\"> by<\/span><span data-offset-key=\"7pffb-230-0\"> sensors<\/span><span data-offset-key=\"7pffb-231-0\"> that<\/span><span data-offset-key=\"7pffb-232-0\"> are<\/span><span data-offset-key=\"7pffb-233-0\"> placed<\/span><span data-offset-key=\"7pffb-234-0\"> on<\/span><span data-offset-key=\"7pffb-235-0\"> the<\/span><span data-offset-key=\"7pffb-236-0\"> surface<\/span><span data-offset-key=\"7pffb-237-0\"> of<\/span><span data-offset-key=\"7pffb-238-0\"> the<\/span><span data-offset-key=\"7pffb-239-0\"> skull<\/span><span data-offset-key=\"7pffb-240-0\"> or<\/span><span data-offset-key=\"7pffb-241-0\"> surg<\/span><span data-offset-key=\"7pffb-242-0\">ically<\/span><span data-offset-key=\"7pffb-243-0\"> implanted<\/span><span data-offset-key=\"7pffb-244-0\"> into<\/span><span data-offset-key=\"7pffb-245-0\"> the<\/span><span data-offset-key=\"7pffb-246-0\"> brain<\/span><span data-offset-key=\"7pffb-247-0\"> itself<\/span><span data-offset-key=\"7pffb-248-0\">.<\/span><span data-offset-key=\"7pffb-249-0\"> The<\/span><span data-offset-key=\"7pffb-250-0\"> sensors<\/span><span data-offset-key=\"7pffb-251-0\"> pick<\/span><span data-offset-key=\"7pffb-252-0\"> up<\/span><span data-offset-key=\"7pffb-253-0\"> tiny<\/span><span data-offset-key=\"7pffb-254-0\"> changes<\/span><span data-offset-key=\"7pffb-255-0\"> in<\/span><span data-offset-key=\"7pffb-256-0\"> voltage<\/span><span data-offset-key=\"7pffb-257-0\"> that<\/span><span data-offset-key=\"7pffb-258-0\"> occur<\/span><span data-offset-key=\"7pffb-259-0\"> when<\/span><span data-offset-key=\"7pffb-260-0\"> neurons<\/span><span data-offset-key=\"7pffb-261-0\"> fire<\/span><span data-offset-key=\"7pffb-262-0\">.<\/span><span data-offset-key=\"7pffb-263-0\"> These<\/span><span data-offset-key=\"7pffb-264-0\"> changes<\/span><span data-offset-key=\"7pffb-265-0\"> are<\/span><span data-offset-key=\"7pffb-266-0\"> then<\/span><span data-offset-key=\"7pffb-267-0\"> converted<\/span><span data-offset-key=\"7pffb-268-0\"> into<\/span><span data-offset-key=\"7pffb-269-0\"> commands<\/span><span data-offset-key=\"7pffb-270-0\"> that<\/span><span data-offset-key=\"7pffb-271-0\"> can<\/span><span data-offset-key=\"7pffb-272-0\"> be<\/span><span data-offset-key=\"7pffb-273-0\"> understood<\/span><span data-offset-key=\"7pffb-274-0\"> by<\/span><span data-offset-key=\"7pffb-275-0\"> a<\/span><span data-offset-key=\"7pffb-276-0\"> machine<\/span><span data-offset-key=\"7pffb-277-0\">.<\/span> <span data-offset-key=\"7pffb-280-0\">BM<\/span><span data-offset-key=\"7pffb-281-0\">Is<\/span><span data-offset-key=\"7pffb-282-0\"> hold<\/span><span data-offset-key=\"7pffb-283-0\"> great<\/span><span data-offset-key=\"7pffb-284-0\"> promise<\/span><span data-offset-key=\"7pffb-285-0\"> for<\/span><span data-offset-key=\"7pffb-286-0\"> people<\/span><span data-offset-key=\"7pffb-287-0\"> with<\/span><span data-offset-key=\"7pffb-288-0\"> speech<\/span><span data-offset-key=\"7pffb-289-0\"> impair<\/span><span data-offset-key=\"7pffb-290-0\">ments<\/span><span data-offset-key=\"7pffb-291-0\"> caused<\/span><span data-offset-key=\"7pffb-292-0\"> by<\/span><span data-offset-key=\"7pffb-293-0\"> neurological<\/span><span data-offset-key=\"7pffb-294-0\"> conditions<\/span><span data-offset-key=\"7pffb-295-0\"> such<\/span><span data-offset-key=\"7pffb-296-0\"> as<\/span><span data-offset-key=\"7pffb-297-0\"> ALS<\/span><span data-offset-key=\"7pffb-298-0\"> (<\/span><span data-offset-key=\"7pffb-299-0\"> amy<\/span><span data-offset-key=\"7pffb-300-0\">ot<\/span><span data-offset-key=\"7pffb-301-0\">rophic<\/span><span data-offset-key=\"7pffb-302-0\"> lateral<\/span><span data-offset-key=\"7pffb-303-0\"> sclerosis<\/span><span data-offset-key=\"7pffb-304-0\">)<\/span><span data-offset-key=\"7pffb-305-0\"> or<\/span><span data-offset-key=\"7pffb-306-0\"> stroke<\/span><span data-offset-key=\"7pffb-307-0\"> .<\/span><\/p>\r\n<p>[\/vc_column_text][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row el_class=&#8221;vc_hidden-lg vc_hidden-md&#8221;][vc_column][vc_empty_space height=&#8221;240px&#8221;][\/vc_column][\/vc_row][vc_row bg_type=&#8221;image&#8221; parallax_style=&#8221;vcpb-hz-jquery&#8221; bg_image_new=&#8221;id^4935|url^https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2022\/09\/MEG_Brain.png|caption^An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy|alt^An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy|title^An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy|description^An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy&#8221; bg_image_repeat=&#8221;no-repeat&#8221; bg_image_size=&#8221;contain&#8221; css=&#8221;.vc_custom_1667942084232{margin-top: -20px !important;}&#8221;][vc_column][vc_empty_space height=&#8221;340px&#8221;][\/vc_column][\/vc_row][vc_row el_class=&#8221;vc_hidden-lg vc_hidden-sm vc_hidden-xs&#8221;][vc_column][vc_empty_space height=&#8221;30px&#8221; el_class=&#8221;vc_hidden-lg vc_hidden-md vc_hidden-sm&#8221;][\/vc_column][\/vc_row][vc_row el_class=&#8221;vc_hidden-xs&#8221;][vc_column][vc_empty_space height=&#8221;50px&#8221; el_class=&#8221;vc_hidden-xs&#8221;][\/vc_column][\/vc_row][vc_row][vc_column][vc_custom_heading icon=&#8221;fas fa-shield-alt&#8221; text=&#8221;An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy&#8221; font_container=&#8221;tag:h2|font_size:32|text_align:left|line_height:1.2&#8243; use_theme_fonts=&#8221;yes&#8221; css_animation=&#8221;fadeInLeft&#8221;][vc_empty_space height=&#8221;20px&#8221;][\/vc_column][\/vc_row][vc_row css=&#8221;.vc_custom_1620565725690{margin-bottom: 20px !important;}&#8221;][vc_column offset=&#8221;vc_col-lg-9 vc_col-md-9&#8243; css=&#8221;.vc_custom_1452702342137{padding-right: 45px !important;}&#8221;][vc_row_inner css=&#8221;.vc_custom_1664324848949{background-color: #f2f4fa !important;}&#8221;][vc_column_inner width=&#8221;2\/3&#8243; css=&#8221;.vc_custom_1664324067445{margin-top: 50px !important;}&#8221;]<div class=\"audioplayer-tobe  playerid-4937 ap_idx_4932_1 is-single-player apconfig-default-settings-for-zoomsounds button-aspect-noir  skin-wave  ap4937 auto-init\"  data-options='{\"skinwave_comments_playerid\":4937,\"design_skin\":\"skin-wave\",\"disable_scrubbar\":\"off\",\"skinwave_enablereflect\":\"on\",\"skinwave_wave_mode_canvas_waves_number\":\"3\",\"skinwave_wave_mode_canvas_waves_padding\":\"1\",\"skinwave_wave_mode_canvas_reflection_size\":\"0.25\",\"cue\":\"auto\",\"embedded\":\"off\",\"mobile_disable_fakeplayer\":\"on\",\"settings_php_handler\":\"wpdefault\"}' style=\" opacity: 0; \" data-posttype=\"attachment\" id=\"ap4937\" data-playerid=\"4937\" data-computed-playerid=\"4937\" data-real-playerid=\"4937\" data-sanitized_source=\"httpsequinoxgroupeuwpcontentuploads202209AnAIAlgorithmDecodesSpeechFromBrainActivityWithSurprisinglyHighAccuracymp3\" data-sample_time_total=\"339\" data-pcm='[0.26,0.15,0.34,0.44,0.25,0.35,0.13,0,0.32,0.62,0.25,0.01,0.24,0.2,0.35,0.06,0.26,0.63,0.52,0.43,0.06,0.63,0.22,0.61,0.05,0.47,0.29,0.29,0.17,0.1,0,0.32,0.22,0.43,0.31,0.5,0.3,0.1,0.24,0.41,0.22,0.02,0.06,0.51,0.29,0.54,0.34,0.07,0.22,0.17,0.26,0.31,0.21,0.19,0.27,0.46,0.18,0.04,0.37,0.56,0.14,0.77,0.16,0.29,0.22,0.27,0.27,0.3,0.11,0.04,0.31,0.5,0.08,0.3,0.16,0.22,0.27,0.3,0.44,0.39,0.49,0.28,0.24,0.24,0.53,0.11,0.32,0.67,0.28,0.04,0.4,0.25,0.14,0.04,0.09,0.19,0.28,0.04,0.33,0.38,0.23,0.44,0.18,0.4,0.17,0.43,0.44,0.34,0.12,0.18,0.54,0.17,0.55,0.41,0.52,0.14,0.09,0.32,0.33,0.17,0.37,0.05,0.36,0.35,0.31,0.38,0.41,0.24,0.2,0.28,0.18,0.19,0.13,0.42,0.51,0.32,0.51,0.34,0.1,0.53,0.24,0.03,0.25,0.62,0.15,0.07,0.14,0.29,0.52,0.12,0.15,0.32,0.42,0.13,0.36,0.18,0.25,0.19,0.29,0.19,0.63,0.11,0.27,0.44,0.13,0.07,0.3,0.61,0.26,0.6,0.21,0.24,0.19,0.62,0.14,0.12,0.04,0.14,0.27,0.18,0.26,0.44,0.04,0.34,0.33,0.28,0.4,0.05,0.34,0.07,0.51,0.2,0.25,0.36,0.2,0.5,0.28,0.21,0.29,0.1,0.31,0.27,0.53,0.24,0.32,0.55,0.4,0.29,0.21,0.51,0.03,0.34,0.18,0.32,0.16,0.12,0.27,0.24,0.28,0.06,0.14,0.16,0.07,0.42,0.26,0.32,0.12,0.22,0.33,0.46,0.23,0.17,0.63,0.48,0.41,0.03,0.16,0.22,0.45,0.69,0.16,0.37,0.4,0.45,0.48,0.02,0.45,0.28,0.1,0.55,0.15,0.28,0.13,0.06,0.49,0.12,0.19,0.32,0.38,0.04,0.13,0.25,0.42,0.15,0.06,0.22,0.32,0,0.09,0.33,0.13,0.36,0.13,0.47,0.34,0.3,0.09,0.04,0.48,0.03,0.17,0.19,0.22,0.48,0.39,0.48,0.42,0.21,0.2,0.18,0.47,0.02,0.17,0.28,0.22,0.48,0.27,0.26,0.17,0.26,0.18,0.53,0.27,0.6,0.15,0.62,0.37,0.6,0.42,0.05,0.16,0.42,0.14,0.26,0.5,0.03,0.34,0.29,0.29,0.65,0.41,0.05,0.07,0.04,0.09,0.34,0.3,0.24,0.07,0.61,0.41,0.08,0.19,0.32,0.69,0.08,0.09,0.35,0.18,0.43,0.21,0.06,0.39,0.26,0.13,0.49,0.36,0.06,0.24,0.55,0.08,0.15,0.33,0.64,0.32,0.05,0.25,0.46,0.46,0.4,0.27,0.1,0.6,0.41,0.15,0.12,0.34,0.25,0.46,0.1,0.41,0.07,0.27,0.66,0.31,0.23,0.31,0.61,0.11,0.62,0.42,0,0.14,0.32,0.22,0.07,0.52,0.4,0.24,0.07,0.2,0.11,0.32,0.02,0.22,0.35,0.39,0.31,0.14,0.11]' data-type=\"audio\" data-source=\"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2022\/09\/An-AI-Algorithm-Decodes-Speech-From-Brain-Activity-With-Surprisingly-High-Accuracy.mp3\" data-playfrom=\"off\"><div hidden class=\"feed-dzsap feed-artist-name\">Algorithmic BrAIn - An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy<\/div><div hidden class=\"feed-dzsap feed-song-name\">Tired of Reading? Listen Instead!<\/div><div class=\"meta-artist track-meta-for-dzsap\"><span class=\"the-artist first-line\"><span class=\"first-line-label\" >Algorithmic BrAIn - An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy<\/span><\/span><span class=\"the-name the-songname second-line\" >Tired of Reading? Listen Instead!<\/span><\/div><div class=\"menu-description\"><span class=\"the-artist\">Algorithmic BrAIn - An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy<\/span><span class=\"the-name\">Tired of Reading? Listen Instead!<\/span><\/div><div hidden class=\"feed-dzsap feed-dzsap--extra-html feed-dzsap--extra-html--bottom-left \"><span class=\"btn-zoomsounds btn-like\"><span class=\"the-icon\"><svg xmlns:svg=\"http:\/\/www.w3.org\/2000\/svg\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" version=\"1.0\" width=\"15\" height=\"15\"  viewBox=\"0 0 645 700\" id=\"svg2\"> <defs id=\"defs4\" \/> <g id=\"layer1\"> <path d=\"M 297.29747,550.86823 C 283.52243,535.43191 249.1268,505.33855 220.86277,483.99412 C 137.11867,420.75228 125.72108,411.5999 91.719238,380.29088 C 29.03471,322.57071 2.413622,264.58086 2.5048478,185.95124 C 2.5493594,147.56739 5.1656152,132.77929 15.914734,110.15398 C 34.151433,71.768267 61.014996,43.244667 95.360052,25.799457 C 119.68545,13.443675 131.6827,7.9542046 172.30448,7.7296236 C 214.79777,7.4947896 223.74311,12.449347 248.73919,26.181459 C 279.1637,42.895777 310.47909,78.617167 316.95242,103.99205 L 320.95052,119.66445 L 330.81015,98.079942 C 386.52632,-23.892986 564.40851,-22.06811 626.31244,101.11153 C 645.95011,140.18758 648.10608,223.6247 630.69256,270.6244 C 607.97729,331.93377 565.31255,378.67493 466.68622,450.30098 C 402.0054,497.27462 328.80148,568.34684 323.70555,578.32901 C 317.79007,589.91654 323.42339,580.14491 297.29747,550.86823 z\" id=\"path2417\" style=\"\" \/> <g transform=\"translate(129.28571,-64.285714)\" id=\"g2221\" \/> <\/g> <\/svg><\/span><span class=\"the-label hide-on-active\">Like<\/span><span class=\"the-label show-on-active\">Liked<\/span><\/span><\/div><div hidden class=\"feed-dzsap feed-dzsap--extra-html\" data-playerid=\"4937\" style=\"opacity:0;\"><div class=\"dzsap-counter counter-hits\"><i class=\"fa fa-play\"><\/i><span class=\"the-number\">4<\/span><\/div><div class=\"dzsap-counter counter-likes\"><i class=\"fa fa-heart\"><\/i><span class=\"the-number\">3<\/span><\/div><\/div><\/div>[\/vc_column_inner][vc_column_inner width=&#8221;1\/3&#8243; css=&#8221;.vc_custom_1668098446243{padding-top: 30px !important;padding-right: 30px !important;padding-bottom: 30px !important;padding-left: 30px !important;background: #153e4d url(https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2021\/06\/Website-Narration.jpg?id=4189) !important;background-position: center !important;background-repeat: no-repeat !important;background-size: cover !important;}&#8221; offset=&#8221;vc_hidden-xs&#8221;][vc_custom_heading icon=&#8221;fas fa-assistive-listening-systems&#8221; icon_size=&#8221;34&#8243; stm_title_font_weight=&#8221;700&#8243; text=&#8221;&#8221; font_container=&#8221;tag:h2|font_size:34|text_align:left|color:%23153e4d|line_height:0.8&#8243; use_theme_fonts=&#8221;yes&#8221; css_animation=&#8221;none&#8221; subtitle=&#8221;Prefer to listen?&#8221; subtitle_color=&#8221;#ffffff&#8221; css=&#8221;.vc_custom_1664325096040{margin-right: -10px !important;margin-left: -10px !important;}&#8221;][vc_empty_space height=&#8221;20px&#8221;][vc_column_text]<\/p>\r\n<p style=\"text-align: justify;\"><span style=\"color: #ffffff; font-size: 12pt; text-align: justify;\">If you prefer to listen to, instead of reading the text on this page, all you need to do is to put your device sound on, hit the play button on the left,\u00a0 sit back, relax and leave everything else to us.<\/span><\/p>\r\n<p>[\/vc_column_text][\/vc_column_inner][\/vc_row_inner][vc_column_text css=&#8221;.vc_custom_1669234222487{margin-top: 32px !important;}&#8221;]<\/p>\r\n<p style=\"text-align: justify;\">An AI algorithm to decode speech from brain activity has resulted in remarkable precision. The study is however still a long way from being able to be deployed to assist individuals who cannot speak due to the exorbitant costs of the hardware required.<\/p>\r\n<p style=\"text-align: justify;\">The precision with which an artificial intelligence can decode words and phrases from brain activity is surprisingly high, but nevertheless not yet sufficiently high to enable the development of hardware and software for mass market use. The AI deduces what a person has heard using only a few seconds of brain activity data. 73% of the time, the right response is among the top 10 alternatives, according to a preliminary study.<\/p>\r\n<p style=\"text-align: justify;\">The AI&#8217;s performance is clearly beyond what many believed achievable at this level.<\/p>\r\n<p style=\"text-align: justify;\">Researchers on arXiv.org claimed, on August 25 2022, that an AI engine developed by Facebook&#8217;s parent company, Meta, might someday be used to assist thousands of individuals worldwide who are unable to communicate through speech, typing, or gestures. This includes a large number of individuals who are barely awake, locked-in, or in &#8220;vegetative states&#8221; \u2013 a condition often referred to as unresponsive wakefulness syndrome.<\/p>\r\n<p style=\"text-align: justify;\">The majority of present communication aids for such people require invasive brain surgery and ends up leaving installed electrodes as the brain-machine interface. This technology, for instance, was being championed by Elon Musk\u2019s, Max Hodak\u2019s and Paul Merolla\u2019s Neuralink project, which was recently surpassed by some less ceremonious and less-well-known startups that have achieved noteworthy results before Neuralink. Synchron, Neurable, Bitbrain, NextMind, Kernel and Emotiv are all examples of such tech startups.<\/p>\r\n<p style=\"text-align: justify;\">According to neurologists these new technologies provide plausible avenues to aid patients with communication difficulties without the use of intrusive procedures.<\/p>\r\n<p style=\"text-align: justify;\">Neuroscientist Jean-R\u00e9mi King, a Meta AI researcher currently at the \u00c9cole Normale Sup\u00e9rieure in Paris and his colleagues have created a computer algorithm to recognise words and phrases from 56,000 hours of audio recordings in 53 different languages. The tool, also known as a language model, learnt to detect certain elements of language at both a fine-grained level, such as letters or syllables, and a coarser one, such as a word or a phrase.<\/p>\r\n<p style=\"text-align: justify;\">The scientists deployed an AI equipped with this language model to databases from four universities, which contained the brain activity of 169 individuals. In these databases, participants listened to stories and lines from works such as The Old Man and the Sea and Alice&#8217;s Adventures in Wonderland while their brains were scanned using MagnEtoencephaloGraphy (MEG) or electroencephalography. These approaches detect the electrical or magnetic component of brain impulses.<\/p>\r\n<p style=\"text-align: justify;\">Using just three seconds of brain activity data from each participant and a computational technique that helps account for physical variances across actual brains, the researchers attempted to decipher what the individuals had heard. The scientists told the AI to connect the voice sounds from the tale recordings with patterns of brain activity that corresponded to what individuals were hearing, as computed by the AI. It then produced projections based on more than a thousand potential outcomes for what the individual may have heard during the brief interval.<\/p>\r\n<p style=\"text-align: justify;\">Using magnetoencephalography researchers discovered that the right response was among the AI&#8217;s top 10 estimates 73% of the time. With electroencephalography, this figure fell to 30% or less. While the 73% accuracy rate can be expected to improve significantly with bigger datasets, the real stumbling block for the evolution of this research into a mass product is the hardware required. Indeed, at the moment, MEG requires cumbersome and exorbitantly-priced equipment, putting it out of reach of the mass market. Bringing this technology to clinics and to the people who need it requires technological advancements that make the equipment significantly less costly and more user-friendly.<\/p>\r\n<p style=\"text-align: justify;\">It is also crucial to point out that what &#8220;decoding&#8221; refers to in this study is not what we generally mean by decoding. Typically, the term refers to the process of decoding information straight from its source, in this example, speech from brain activity. However, this was only achievable because the AI was given a finite set of potential accurate responses from which to make predictions. With language, this will not suffice if we wish this technology to scale to practical application, as language, while not being infinite gives rise to huge numbers of permutations, which thus would require an even larger training dataset. Additionally, the AI-deciphered information from people who passively listened to audio is not immediately applicable to nonverbal patients, and this possibly holds even at the level of principles.<\/p>\r\n<p style=\"text-align: justify;\">Thus, in order for this to become a useful communication tool, scientists will need to discover how to decipher what these patients wish to communicate, such as hunger, discomfort, or a simple &#8220;yes&#8221; or &#8220;no&#8221;, as well as to discover new ways of bringing down hardware equipment costs. This research involves decoding speech perception, not creation. The latter is the ultimate objective and even though we will eventually get there, we&#8217;re still some way off from achieving that.<\/p>\r\n<p>[\/vc_column_text]<div class=\"templatera_shortcode\"><style type=\"text\/css\" data-type=\"vc_shortcodes-default-css\">.vc_do_custom_heading{margin-bottom:0.625rem;margin-top:0;}.vc_do_custom_heading{margin-bottom:0.625rem;margin-top:0;}.vc_do_btn{margin-bottom:22px;}<\/style><style type=\"text\/css\" data-type=\"vc_shortcodes-custom-css\">.vc_custom_1667111652227{margin-top: 48px !important;}.vc_custom_1713917281413{margin-top: 14px !important;margin-bottom: 42px !important;padding-bottom: 12px !important;}.vc_custom_1667116849933{margin-top: 28px !important;margin-bottom: 28px !important;}.vc_custom_1713917315239{margin-top: 14px !important;margin-bottom: 42px !important;padding-bottom: 12px !important;}<\/style><div class=\"vc_row wpb_row vc_row-fluid vc_custom_1667111652227\"><div class=\"wpb_column vc_column_container vc_col-sm-12\"><div class=\"vc_column-inner \"><div class=\"wpb_wrapper\">\t<div class=\"vc_separator wpb_content_element vc_sep_width_100 vc_sep_border_width_3 type_1  vc_separator_no_text\">\n\t\t<span class=\"vc_sep_holder vc_sep_holder_l\"><span style=\"border-color:#fde952;\" class=\"vc_sep_line\"><\/span><\/span>\n\t\t\t\t<span class=\"vc_sep_holder vc_sep_holder_r\"><span style=\"border-color:#fde952;\" class=\"vc_sep_line\"><\/span><\/span>\n\t<\/div>\n\t\n<div class=\"vc_custom_heading vc_custom_1713917281413 text_align_left has_icon\" ><div class=\"icon\" style=\"font-size: 36px; line-height: 36px;\"><i class=\"far fa-newspaper\"><\/i><\/div><h2 style=\"font-size: 30px;text-align: left\" class=\"consulting-custom-title\">More Recent News Items<\/h2><\/div><div class=\"vc_empty_space\"   style=\"height: 24px\"><span class=\"vc_empty_space_inner\"><\/span><\/div>\n\n    <div class=\"stm_news \">\n        <ul class=\"news_list posts_per_row_4\">\n\n            \n                                <li class=\"view_style_3\">\n                    <div class=\"post_item\">\n                                                    <a href=\"https:\/\/equinoxgroup.eu\/how-claude-3-5-is-trying-to-revolutionise-automation-through-autonomous-ai-agents\/\" class=\"image\">\n                                <img decoding=\"async\" class=\"\" src=\"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2024\/10\/How-Claude-3.5-Is-Trying-to-Revolutionise-Automation-through-Autonomous-AI-agents-260x170.jpg\" width=\"260\" height=\"170\" alt=\"How Claude 3.5 Is Trying to Revolutionise Automation through Autonomous AI agents\" title=\"How Claude 3.5 Is Trying to Revolutionise Automation through Autonomous AI agents\" loading=\"lazy\" \/>                            <\/a>\n                                                <div class=\"content\">\n                            <a href=\"https:\/\/equinoxgroup.eu\/how-claude-3-5-is-trying-to-revolutionise-automation-through-autonomous-ai-agents\/\" class=\"title base_font_color\">\n                                <h5 class=\"secondary_font_color_hv\">How Claude 3.5 Is Trying to Revolutionise Automation through Autonomous AI agents<\/h5>\n                            <\/a>\n                            <div class=\"description\">\n                                                            <\/div>\n                            <a href=\"https:\/\/equinoxgroup.eu\/how-claude-3-5-is-trying-to-revolutionise-automation-through-autonomous-ai-agents\/\" class=\"read_more\">\n                                <i class=\"stm-lnr-arrow-right third_bg_color base_bg_color_hv\"><\/i>\n                                <span>\n                                Read more                                <\/span>\n                            <\/a>\n                        <\/div>\n                    <\/div>\n                <\/li>\n\n            \n                                <li class=\"view_style_3\">\n                    <div class=\"post_item\">\n                                                    <a href=\"https:\/\/equinoxgroup.eu\/ai-achieves-major-milestone-in-aerial-combat-fuelling-debate-on-the-future-of-warfare\/\" class=\"image\">\n                                <img decoding=\"async\" class=\"\" src=\"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2024\/04\/Autonomous-Flight-260x170.jpg\" width=\"260\" height=\"170\" alt=\"Lethal Autonomous Weapon\" title=\"Lethal Autonomous Weapon\" loading=\"lazy\" \/>                            <\/a>\n                                                <div class=\"content\">\n                            <a href=\"https:\/\/equinoxgroup.eu\/ai-achieves-major-milestone-in-aerial-combat-fuelling-debate-on-the-future-of-warfare\/\" class=\"title base_font_color\">\n                                <h5 class=\"secondary_font_color_hv\">AI Achieves Major Milestone in Aerial Combat, Fuelling Debate on the Future of Warfare<\/h5>\n                            <\/a>\n                            <div class=\"description\">\n                                                            <\/div>\n                            <a href=\"https:\/\/equinoxgroup.eu\/ai-achieves-major-milestone-in-aerial-combat-fuelling-debate-on-the-future-of-warfare\/\" class=\"read_more\">\n                                <i class=\"stm-lnr-arrow-right third_bg_color base_bg_color_hv\"><\/i>\n                                <span>\n                                Read more                                <\/span>\n                            <\/a>\n                        <\/div>\n                    <\/div>\n                <\/li>\n\n            \n                                <li class=\"view_style_3\">\n                    <div class=\"post_item\">\n                                                    <a href=\"https:\/\/equinoxgroup.eu\/the-human-factor-in-ai-double-edged-sword\/\" class=\"image\">\n                                <img decoding=\"async\" class=\"\" src=\"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2023\/05\/Geoffrey-Hinton-260x170.jpg\" width=\"260\" height=\"170\" alt=\"Geoffrey Hinton\" title=\"Geoffrey Hinton\" loading=\"lazy\" \/>                            <\/a>\n                                                <div class=\"content\">\n                            <a href=\"https:\/\/equinoxgroup.eu\/the-human-factor-in-ai-double-edged-sword\/\" class=\"title base_font_color\">\n                                <h5 class=\"secondary_font_color_hv\">The Human Factor in AI: A Double-Edged Sword<\/h5>\n                            <\/a>\n                            <div class=\"description\">\n                                                            <\/div>\n                            <a href=\"https:\/\/equinoxgroup.eu\/the-human-factor-in-ai-double-edged-sword\/\" class=\"read_more\">\n                                <i class=\"stm-lnr-arrow-right third_bg_color base_bg_color_hv\"><\/i>\n                                <span>\n                                Read more                                <\/span>\n                            <\/a>\n                        <\/div>\n                    <\/div>\n                <\/li>\n\n            \n                                <li class=\"view_style_3\">\n                    <div class=\"post_item\">\n                                                    <a href=\"https:\/\/equinoxgroup.eu\/overcoming-data-limitations-for-ai-models-the-future-of-machine-learning-approaches\/\" class=\"image\">\n                                <img decoding=\"async\" class=\"\" src=\"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2023\/05\/Data-Limitations-AI-260x170.jpg\" width=\"260\" height=\"170\" alt=\"Data Limitations AI\" title=\"Data Limitations AI\" loading=\"lazy\" \/>                            <\/a>\n                                                <div class=\"content\">\n                            <a href=\"https:\/\/equinoxgroup.eu\/overcoming-data-limitations-for-ai-models-the-future-of-machine-learning-approaches\/\" class=\"title base_font_color\">\n                                <h5 class=\"secondary_font_color_hv\">Overcoming Data Limitations for AI Models: The Future of Machine Learning Approaches<\/h5>\n                            <\/a>\n                            <div class=\"description\">\n                                                            <\/div>\n                            <a href=\"https:\/\/equinoxgroup.eu\/overcoming-data-limitations-for-ai-models-the-future-of-machine-learning-approaches\/\" class=\"read_more\">\n                                <i class=\"stm-lnr-arrow-right third_bg_color base_bg_color_hv\"><\/i>\n                                <span>\n                                Read more                                <\/span>\n                            <\/a>\n                        <\/div>\n                    <\/div>\n                <\/li>\n\n                    <\/ul>\n    <\/div>\n<div class=\"vc_empty_space\"   style=\"height: 48px\"><span class=\"vc_empty_space_inner\"><\/span><\/div><div class=\"vc_row wpb_row vc_inner vc_row-fluid vc_custom_1667116849933\"><div class=\"wpb_column vc_column_container vc_col-sm-4\"><div class=\"vc_column-inner\"><div class=\"wpb_wrapper\"><\/div><\/div><\/div><div class=\"wpb_column vc_column_container vc_col-sm-4\"><div class=\"vc_column-inner\"><div class=\"wpb_wrapper\"><div class=\"vc_btn3-container vc_btn3-inline vc_do_btn\" ><a class=\"vc_general vc_btn3 vc_btn3-size-md vc_btn3-shape-rounded vc_btn3-style-modern vc_btn3-color-primary\" href=\"https:\/\/equinoxgroup.eu\/news\" title=\"\">See All News Items<\/a><\/div><\/div><\/div><\/div><div class=\"wpb_column vc_column_container vc_col-sm-4\"><div class=\"vc_column-inner\"><div class=\"wpb_wrapper\"><\/div><\/div><\/div><\/div><div class=\"vc_empty_space\"   style=\"height: 48px\"><span class=\"vc_empty_space_inner\"><\/span><\/div>\t<div class=\"vc_separator wpb_content_element vc_sep_width_100 vc_sep_border_width_3 type_1  vc_separator_no_text\">\n\t\t<span class=\"vc_sep_holder vc_sep_holder_l\"><span style=\"border-color:#fde952;\" class=\"vc_sep_line\"><\/span><\/span>\n\t\t\t\t<span class=\"vc_sep_holder vc_sep_holder_r\"><span style=\"border-color:#fde952;\" class=\"vc_sep_line\"><\/span><\/span>\n\t<\/div>\n\t\n<div class=\"vc_empty_space\"   style=\"height: 48px\"><span class=\"vc_empty_space_inner\"><\/span><\/div><div class=\"vc_custom_heading vc_custom_1713917315239 text_align_left has_icon\" ><div class=\"icon\" style=\"font-size: 36px; line-height: 36px;\"><i class=\"fas fa-key\"><\/i><\/div><h2 style=\"font-size: 30px;text-align: left\" class=\"consulting-custom-title\">Article Keywords<\/h2><\/div><div class=\"vc_empty_space\"   style=\"height: 24px\"><span class=\"vc_empty_space_inner\"><\/span><\/div><div class=\"post_bottom_wr \">\n    <div class=\"post_bottom media\">\n\t<div class=\"tags media-body\"><a href=\"https:\/\/equinoxgroup.eu\/tag\/ai\/\" rel=\"tag\">AI<\/a> <a href=\"https:\/\/equinoxgroup.eu\/tag\/data-limitations\/\" rel=\"tag\">data limitations<\/a> <a href=\"https:\/\/equinoxgroup.eu\/tag\/machine-learning-approaches\/\" rel=\"tag\">machine learning approaches<\/a><\/div>\t<\/div><\/div><div class=\"about_author_wr \">\n    <\/div>\t<div class=\"vc_separator wpb_content_element vc_sep_width_100 vc_sep_border_width_3 type_1  vc_separator_no_text\">\n\t\t<span class=\"vc_sep_holder vc_sep_holder_l\"><span style=\"border-color:#fde952;\" class=\"vc_sep_line\"><\/span><\/span>\n\t\t\t\t<span class=\"vc_sep_holder vc_sep_holder_r\"><span style=\"border-color:#fde952;\" class=\"vc_sep_line\"><\/span><\/span>\n\t<\/div>\n\t\n    <div class=\"stm_post_comments\">\n            <\/div>\n<\/div><\/div><\/div><\/div><\/div>[\/vc_column][vc_column width=&#8221;1\/4&#8243; offset=&#8221;vc_hidden-sm vc_hidden-xs&#8221;]<div class=\"ult_row_spacer\"><div class=\"ult-sticky-anchor\"><div class=\"ult-sticky-section ult-sticky \"  data-gutter= '-20' data-stick_behaviour= 'stick_with_scroll_row'  data-sticky_position= 'top' data-mobile='no' data-support='no'><\/div><div class=\"ult-space\"><\/div><\/div><\/div>[\/vc_column][\/vc_row][vc_row full_width=&#8221;stretch_row&#8221; el_class=&#8221;third_bg_color&#8221; css=&#8221;.vc_custom_1451889219674{margin-bottom: -60px !important;}&#8221;][vc_column][vc_cta h2=&#8221;Looking for assistance with AI?&#8221; h2_font_container=&#8221;tag:h2|font_size:20px|text_align:left|color:%23000000|line_height:24px&#8221; h2_use_theme_fonts=&#8221;yes&#8221; shape=&#8221;square&#8221; style=&#8221;flat&#8221; add_button=&#8221;right&#8221; btn_title=&#8221;get in touch&#8221; btn_style=&#8221;flat&#8221; btn_color=&#8221;theme_style_2&#8243; btn_align=&#8221;right&#8221; btn_i_align=&#8221;right&#8221; btn_i_icon_fontawesome=&#8221;fas fa-chevron-right&#8221; btn_css_animation=&#8221;slideInRight&#8221; particles=&#8221;yes&#8221; use_custom_fonts_h2=&#8221;true&#8221; btn_button_block=&#8221;true&#8221; btn_add_icon=&#8221;true&#8221; el_class=&#8221;third_bg_color&#8221; css=&#8221;.vc_custom_1664408138628{margin-bottom: 0px !important;}&#8221; btn_link=&#8221;url:http%3A%2F%2Fequinoxgroup.eu%2Fcontact-us%2F|title:Get%20in%20touch&#8221;][\/vc_cta][\/vc_column][\/vc_row]<\/p><\/div>","protected":false},"excerpt":{"rendered":"Potential data limitations (in the form of scarcity) for AI models is around the corner and alternative machine learning approaches to sustain performance are becoming essential. From redefining data quality, to methods like JEPA, data augmentation and transfer learning, our future with AI holds promising solutions. The limitations of scaling AI and the importance of","protected":false},"author":1,"featured_media":4935,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[21,19],"tags":[249,322,318,321,320,319],"insights_perspectives":[],"class_list":{"0":"post-4932","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-algorithmic-brain","8":"category-artificial-intelligence-ai","9":"tag-ai","10":"tag-brain-machine-interface","11":"tag-brain-to-computer-interface","12":"tag-electroencephalography","13":"tag-magnetoencephalography","14":"tag-neurology"},"yoast_head":"\n<title>An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy - equinoxgroup.eu<\/title>\n<meta name=\"description\" content=\"An AI algorithm to decode speech from brain activity has resulted in remarkable precision but hardware costs remain prohibitive.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/\" \/>\n<meta property=\"og:locale\" content=\"en_GB\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy\" \/>\n<meta property=\"og:description\" content=\"An AI algorithm to decode speech from brain activity has resulted in remarkable precision but hardware costs remain prohibitive.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/\" \/>\n<meta property=\"og:site_name\" content=\"equinoxgroup.eu\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/EquinoxGroupMalta\" \/>\n<meta property=\"article:author\" content=\"https:\/\/www.facebook.com\/bernard.mallia\" \/>\n<meta property=\"article:published_time\" content=\"2022-09-28T23:34:16+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2022-11-23T20:10:25+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2022\/09\/MEG_Brain.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"800\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Bernard Mallia\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@https:\/\/twitter.com\/BernardMallia\" \/>\n<meta name=\"twitter:site\" content=\"@equinox_group\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Bernard Mallia\" \/>\n\t<meta name=\"twitter:label2\" content=\"Estimated reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"TechArticle\",\"@id\":\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/\"},\"author\":{\"name\":\"Bernard Mallia\",\"@id\":\"https:\/\/equinoxgroup.eu\/#\/schema\/person\/d064b4896bdf813365507c3573e1c735\"},\"headline\":\"An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy\",\"datePublished\":\"2022-09-28T23:34:16+00:00\",\"dateModified\":\"2022-11-23T20:10:25+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/\"},\"wordCount\":1766,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/equinoxgroup.eu\/#organization\"},\"image\":{\"@id\":\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2022\/09\/MEG_Brain.png\",\"keywords\":[\"AI\",\"brain-machine interface\",\"Brain-to-computer interface\",\"electroencephalography\",\"MagnEtoencephaloGraphy\",\"neurology\"],\"articleSection\":[\"Algorithmic Brain\",\"Artificial Intelligence (AI)\"],\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#respond\"]}],\"copyrightYear\":\"2022\",\"copyrightHolder\":{\"@id\":\"https:\/\/equinoxgroup.eu\/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/\",\"url\":\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/\",\"name\":\"An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy - equinoxgroup.eu\",\"isPartOf\":{\"@id\":\"https:\/\/equinoxgroup.eu\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2022\/09\/MEG_Brain.png\",\"datePublished\":\"2022-09-28T23:34:16+00:00\",\"dateModified\":\"2022-11-23T20:10:25+00:00\",\"description\":\"An AI algorithm to decode speech from brain activity has resulted in remarkable precision but hardware costs remain prohibitive.\",\"breadcrumb\":{\"@id\":\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#breadcrumb\"},\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#primaryimage\",\"url\":\"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2022\/09\/MEG_Brain.png\",\"contentUrl\":\"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2022\/09\/MEG_Brain.png\",\"width\":1200,\"height\":800,\"caption\":\"An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/equinoxgroup.eu\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/equinoxgroup.eu\/#website\",\"url\":\"https:\/\/equinoxgroup.eu\/\",\"name\":\"equinoxgroup.eu\",\"description\":\"Equinox Group\",\"publisher\":{\"@id\":\"https:\/\/equinoxgroup.eu\/#organization\"},\"alternateName\":\"Equinox Group\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/equinoxgroup.eu\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-GB\"},{\"@type\":[\"Organization\",\"Place\"],\"@id\":\"https:\/\/equinoxgroup.eu\/#organization\",\"name\":\"Equinox Group\",\"alternateName\":\"Equinox\",\"url\":\"https:\/\/equinoxgroup.eu\/\",\"logo\":{\"@id\":\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#local-main-organization-logo\"},\"image\":{\"@id\":\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#local-main-organization-logo\"},\"sameAs\":[\"https:\/\/www.facebook.com\/EquinoxGroupMalta\",\"https:\/\/x.com\/equinox_group\",\"https:\/\/www.linkedin.com\/groups\/9010639\/\"],\"address\":{\"@id\":\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#local-main-place-address\"},\"geo\":{\"@type\":\"GeoCoordinates\",\"latitude\":\"35.91732299444383\",\"longitude\":\"14.49995422728913\"},\"telephone\":[\"+35699800001\"],\"openingHoursSpecification\":[{\"@type\":\"OpeningHoursSpecification\",\"dayOfWeek\":[\"Monday\",\"Tuesday\",\"Wednesday\",\"Thursday\",\"Friday\"],\"opens\":\"10:00\",\"closes\":\"19:00\"},{\"@type\":\"OpeningHoursSpecification\",\"dayOfWeek\":[\"Saturday\",\"Sunday\"],\"opens\":\"00:00\",\"closes\":\"00:00\"}],\"email\":\"info@equinoxadvisory.com\",\"areaServed\":\"EU, USA, Middle East, Africa, Asia\",\"vatID\":\"MT 21316028\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/equinoxgroup.eu\/#\/schema\/person\/d064b4896bdf813365507c3573e1c735\",\"name\":\"Bernard Mallia\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/equinoxgroup.eu\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/9f7782f39c6906e28fd98c397dc1f29be402dedd353fd82192af03461fc04cc7?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/9f7782f39c6906e28fd98c397dc1f29be402dedd353fd82192af03461fc04cc7?s=96&d=mm&r=g\",\"caption\":\"Bernard Mallia\"},\"sameAs\":[\"http:\/\/equinoxgroup.eu\",\"https:\/\/www.facebook.com\/bernard.mallia\",\"https:\/\/www.linkedin.com\/in\/bernardmallia\/\",\"https:\/\/x.com\/https:\/\/twitter.com\/BernardMallia\"],\"url\":\"https:\/\/equinoxgroup.eu\/author\/wpx_bm_grp_admin\/\"},{\"@type\":\"PostalAddress\",\"@id\":\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#local-main-place-address\",\"streetAddress\":\"Suite 1, 208,, Tower Road\",\"addressLocality\":\"Sliema\",\"postalCode\":\"SLM 1602\",\"addressCountry\":\"MT\"},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#local-main-organization-logo\",\"url\":\"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2021\/06\/Equinox-Group-Black.png\",\"contentUrl\":\"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2021\/06\/Equinox-Group-Black.png\",\"width\":425,\"height\":140,\"caption\":\"Equinox Group\"}]}<\/script>\n<meta name=\"geo.placename\" content=\"Sliema\" \/>\n<meta name=\"geo.position\" content=\"35.91732299444383;14.49995422728913\" \/>\n<meta name=\"geo.region\" content=\"Malta\" \/>\n","yoast_head_json":{"title":"An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy - equinoxgroup.eu","description":"An AI algorithm to decode speech from brain activity has resulted in remarkable precision but hardware costs remain prohibitive.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/","og_locale":"en_GB","og_type":"article","og_title":"An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy","og_description":"An AI algorithm to decode speech from brain activity has resulted in remarkable precision but hardware costs remain prohibitive.","og_url":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/","og_site_name":"equinoxgroup.eu","article_publisher":"https:\/\/www.facebook.com\/EquinoxGroupMalta","article_author":"https:\/\/www.facebook.com\/bernard.mallia","article_published_time":"2022-09-28T23:34:16+00:00","article_modified_time":"2022-11-23T20:10:25+00:00","og_image":[{"width":1200,"height":800,"url":"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2022\/09\/MEG_Brain.png","type":"image\/png"}],"author":"Bernard Mallia","twitter_card":"summary_large_image","twitter_creator":"@https:\/\/twitter.com\/BernardMallia","twitter_site":"@equinox_group","twitter_misc":{"Written by":"Bernard Mallia","Estimated reading time":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"TechArticle","@id":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#article","isPartOf":{"@id":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/"},"author":{"name":"Bernard Mallia","@id":"https:\/\/equinoxgroup.eu\/#\/schema\/person\/d064b4896bdf813365507c3573e1c735"},"headline":"An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy","datePublished":"2022-09-28T23:34:16+00:00","dateModified":"2022-11-23T20:10:25+00:00","mainEntityOfPage":{"@id":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/"},"wordCount":1766,"commentCount":0,"publisher":{"@id":"https:\/\/equinoxgroup.eu\/#organization"},"image":{"@id":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#primaryimage"},"thumbnailUrl":"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2022\/09\/MEG_Brain.png","keywords":["AI","brain-machine interface","Brain-to-computer interface","electroencephalography","MagnEtoencephaloGraphy","neurology"],"articleSection":["Algorithmic Brain","Artificial Intelligence (AI)"],"inLanguage":"en-GB","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#respond"]}],"copyrightYear":"2022","copyrightHolder":{"@id":"https:\/\/equinoxgroup.eu\/#organization"}},{"@type":"WebPage","@id":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/","url":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/","name":"An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy - equinoxgroup.eu","isPartOf":{"@id":"https:\/\/equinoxgroup.eu\/#website"},"primaryImageOfPage":{"@id":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#primaryimage"},"image":{"@id":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#primaryimage"},"thumbnailUrl":"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2022\/09\/MEG_Brain.png","datePublished":"2022-09-28T23:34:16+00:00","dateModified":"2022-11-23T20:10:25+00:00","description":"An AI algorithm to decode speech from brain activity has resulted in remarkable precision but hardware costs remain prohibitive.","breadcrumb":{"@id":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#breadcrumb"},"inLanguage":"en-GB","potentialAction":[{"@type":"ReadAction","target":["https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/"]}]},{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#primaryimage","url":"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2022\/09\/MEG_Brain.png","contentUrl":"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2022\/09\/MEG_Brain.png","width":1200,"height":800,"caption":"An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy"},{"@type":"BreadcrumbList","@id":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/equinoxgroup.eu\/"},{"@type":"ListItem","position":2,"name":"An AI Algorithm Decodes Speech From Brain Activity With Surprisingly High Accuracy"}]},{"@type":"WebSite","@id":"https:\/\/equinoxgroup.eu\/#website","url":"https:\/\/equinoxgroup.eu\/","name":"equinoxgroup.eu","description":"Equinox Group","publisher":{"@id":"https:\/\/equinoxgroup.eu\/#organization"},"alternateName":"Equinox Group","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/equinoxgroup.eu\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-GB"},{"@type":["Organization","Place"],"@id":"https:\/\/equinoxgroup.eu\/#organization","name":"Equinox Group","alternateName":"Equinox","url":"https:\/\/equinoxgroup.eu\/","logo":{"@id":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#local-main-organization-logo"},"image":{"@id":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#local-main-organization-logo"},"sameAs":["https:\/\/www.facebook.com\/EquinoxGroupMalta","https:\/\/x.com\/equinox_group","https:\/\/www.linkedin.com\/groups\/9010639\/"],"address":{"@id":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#local-main-place-address"},"geo":{"@type":"GeoCoordinates","latitude":"35.91732299444383","longitude":"14.49995422728913"},"telephone":["+35699800001"],"openingHoursSpecification":[{"@type":"OpeningHoursSpecification","dayOfWeek":["Monday","Tuesday","Wednesday","Thursday","Friday"],"opens":"10:00","closes":"19:00"},{"@type":"OpeningHoursSpecification","dayOfWeek":["Saturday","Sunday"],"opens":"00:00","closes":"00:00"}],"email":"info@equinoxadvisory.com","areaServed":"EU, USA, Middle East, Africa, Asia","vatID":"MT 21316028"},{"@type":"Person","@id":"https:\/\/equinoxgroup.eu\/#\/schema\/person\/d064b4896bdf813365507c3573e1c735","name":"Bernard Mallia","image":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/equinoxgroup.eu\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/9f7782f39c6906e28fd98c397dc1f29be402dedd353fd82192af03461fc04cc7?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/9f7782f39c6906e28fd98c397dc1f29be402dedd353fd82192af03461fc04cc7?s=96&d=mm&r=g","caption":"Bernard Mallia"},"sameAs":["http:\/\/equinoxgroup.eu","https:\/\/www.facebook.com\/bernard.mallia","https:\/\/www.linkedin.com\/in\/bernardmallia\/","https:\/\/x.com\/https:\/\/twitter.com\/BernardMallia"],"url":"https:\/\/equinoxgroup.eu\/author\/wpx_bm_grp_admin\/"},{"@type":"PostalAddress","@id":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#local-main-place-address","streetAddress":"Suite 1, 208,, Tower Road","addressLocality":"Sliema","postalCode":"SLM 1602","addressCountry":"MT"},{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/equinoxgroup.eu\/an-ai-algorithm-decodes-speech-from-brain-activity-with-surprisingly-high-accuracy\/#local-main-organization-logo","url":"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2021\/06\/Equinox-Group-Black.png","contentUrl":"https:\/\/equinoxgroup.eu\/wp-content\/uploads\/2021\/06\/Equinox-Group-Black.png","width":425,"height":140,"caption":"Equinox Group"}]},"geo.placename":"Sliema","geo.position":{"lat":"35.91732299444383","long":"14.49995422728913"},"geo.region":"Malta"},"_links":{"self":[{"href":"https:\/\/equinoxgroup.eu\/apps-api\/wp\/v2\/posts\/4932","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/equinoxgroup.eu\/apps-api\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/equinoxgroup.eu\/apps-api\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/equinoxgroup.eu\/apps-api\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/equinoxgroup.eu\/apps-api\/wp\/v2\/comments?post=4932"}],"version-history":[{"count":0,"href":"https:\/\/equinoxgroup.eu\/apps-api\/wp\/v2\/posts\/4932\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/equinoxgroup.eu\/apps-api\/wp\/v2\/media\/4935"}],"wp:attachment":[{"href":"https:\/\/equinoxgroup.eu\/apps-api\/wp\/v2\/media?parent=4932"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/equinoxgroup.eu\/apps-api\/wp\/v2\/categories?post=4932"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/equinoxgroup.eu\/apps-api\/wp\/v2\/tags?post=4932"},{"taxonomy":"insights_perspectives","embeddable":true,"href":"https:\/\/equinoxgroup.eu\/apps-api\/wp\/v2\/insights_perspectives?post=4932"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}