{"id":241032,"date":"2024-06-11T05:30:00","date_gmt":"2024-06-11T05:30:00","guid":{"rendered":"https:\/\/datascientest.com\/?p=241032"},"modified":"2024-06-13T09:55:33","modified_gmt":"2024-06-13T09:55:33","slug":"reconnaissance-vocale-tout-savoir","status":"publish","type":"post","link":"https:\/\/datascientest.com\/reconnaissance-vocale-tout-savoir","title":{"rendered":"Reconnaissance vocale : d\u00e9finition, origines et applications technologiques"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"241032\" class=\"elementor elementor-241032\" data-elementor-post-type=\"post\">\n\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-0cd96cf e-flex e-con-boxed e-con\" data-id=\"0cd96cf\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-3e1c613 elementor-widget elementor-widget-heading\" data-id=\"3e1c613\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.15.0 - 02-08-2023 *\/\n.elementor-heading-title{padding:0;margin:0;line-height:1}.elementor-widget-heading .elementor-heading-title[class*=elementor-size-]>a{color:inherit;font-size:inherit;line-height:inherit}.elementor-widget-heading .elementor-heading-title.elementor-size-small{font-size:15px}.elementor-widget-heading .elementor-heading-title.elementor-size-medium{font-size:19px}.elementor-widget-heading .elementor-heading-title.elementor-size-large{font-size:29px}.elementor-widget-heading .elementor-heading-title.elementor-size-xl{font-size:39px}.elementor-widget-heading .elementor-heading-title.elementor-size-xxl{font-size:59px}<\/style><h2 class=\"elementor-heading-title elementor-size-default\">Parler \u00e0 son smartphone est devenu une activit\u00e9 courante. Et un grand nombre de syst\u00e8mes de reconnaissance vocale se r\u00e9v\u00e8lent tr\u00e8s dou\u00e9s. Pourtant, le chemin qui a amen\u00e9 \u00e0 la compr\u00e9hension de la voix humaine s'est \u00e9tendu sur plusieurs d\u00e9cennies.<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-2a66e71 elementor-widget elementor-widget-text-editor\" data-id=\"2a66e71\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.15.0 - 02-08-2023 *\/\n.elementor-widget-text-editor.elementor-drop-cap-view-stacked .elementor-drop-cap{background-color:#69727d;color:#fff}.elementor-widget-text-editor.elementor-drop-cap-view-framed .elementor-drop-cap{color:#69727d;border:3px solid;background-color:transparent}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap{margin-top:8px}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap-letter{width:1em;height:1em}.elementor-widget-text-editor .elementor-drop-cap{float:left;text-align:center;line-height:1;font-size:50px}.elementor-widget-text-editor .elementor-drop-cap-letter{display:inline-block}<\/style>\t\t\t\t<p><span style=\"font-weight: 400;\">La reconnaissance vocale est devenue un service courant que l\u2019on <\/span><span style=\"font-weight: 400;\">retrouve dans de tr\u00e8s nombreux secteurs d\u2019activit\u00e9s :<\/span><\/p><ul><li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Chacun de nous l\u2019utilise couramment pour <strong>converser avec son smartphone ou avec des applications<\/strong> ;<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">\u00c0 la fin d\u2019une consultation m\u00e9dicale, habituellement le praticien utilise cette technologie pour <strong>dicter son compte-rendu<\/strong> ;<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">C\u2019est habituellement par ce biais que l\u2019on consulte le solde de son compte bancaire ;<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">etc.<\/span><\/li><\/ul>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-764fa03 elementor-widget elementor-widget-text-editor\" data-id=\"764fa03\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">Pourtant, si cette technologie est d\u00e9sormais entr\u00e9e dans les m\u0153urs, il a fallu plusieurs d\u00e9cennies avant qu\u2019elle n&rsquo;atteigne un niveau de qualit\u00e9 satisfaisant.<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-d735e5c e-flex e-con-boxed e-con\" data-id=\"d735e5c\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-447552c elementor-widget elementor-widget-heading\" data-id=\"447552c\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Petite histoire de la reconnaissance vocale<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-43e5e19 elementor-widget elementor-widget-text-editor\" data-id=\"43e5e19\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\"><strong>La reconnaissance vocale repose sur plus de 70 ans de recherches scientifiques !<\/strong> Les premiers travaux sur le domaine remontent au d\u00e9but des ann\u00e9es 50.<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3aae7b0 elementor-widget elementor-widget-heading\" data-id=\"3aae7b0\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-medium\">Audrey<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-c8bb905 elementor-widget elementor-widget-image\" data-id=\"c8bb905\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.15.0 - 02-08-2023 *\/\n.elementor-widget-image{text-align:center}.elementor-widget-image a{display:inline-block}.elementor-widget-image a img[src$=\".svg\"]{width:48px}.elementor-widget-image img{vertical-align:middle;display:inline-block}<\/style>\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"1000\" height=\"523\" src=\"https:\/\/datascientest.com\/wp-content\/uploads\/2024\/05\/audrey-speech-recognition.jpeg\" class=\"attachment-full size-full wp-image-241067\" alt=\"\" srcset=\"https:\/\/datascientest.com\/wp-content\/uploads\/2024\/05\/audrey-speech-recognition.jpeg 1000w, https:\/\/datascientest.com\/wp-content\/uploads\/2024\/05\/audrey-speech-recognition-300x157.jpeg 300w, https:\/\/datascientest.com\/wp-content\/uploads\/2024\/05\/audrey-speech-recognition-768x402.jpeg 768w\" sizes=\"(max-width: 1000px) 100vw, 1000px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-7c91609 elementor-widget elementor-widget-text-editor\" data-id=\"7c91609\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">C\u2019est en <strong>1952<\/strong> qu\u2019appara\u00eet Audrey, le tout premier syst\u00e8me de reconnaissance vocale au sein des laboratoires Bell. Il est en mesure d\u2019identifier les chiffres de 0 \u00e0 9, prononc\u00e9s s\u00e9par\u00e9ment, avec <strong>un taux de r\u00e9ussite de 99 %<\/strong>. Toutefois, ce taux de 99 % n\u2019est rencontr\u00e9 que lorsque l\u2019inventeur de Audrey lui parle. Avec d\u2019autres interlocuteurs, le taux est plus proche de 70 \u00e0 80 %. Ainsi, d\u00e8s l\u2019origine, un aspect fondamental du probl\u00e8me est \u00e9nonc\u00e9 : la voix humaine est vari\u00e9e. Chacun a une fa\u00e7on de s\u2019exprimer qui lui est propre et le probl\u00e8me de la reconnaissance vocale est donc complexe.<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-a0db81e elementor-widget elementor-widget-heading\" data-id=\"a0db81e\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-medium\">Shoebox<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-1ad1dcc elementor-widget elementor-widget-text-editor\" data-id=\"1ad1dcc\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">Dix ans plus tard, la calculatrice \u00e0 commande vocale Shoebox est pr\u00e9sent\u00e9e par <strong>IBM<\/strong> en avril 1962 lors d\u2019une exposition universelle. Cet appareil cr\u00e9\u00e9 par William C. Dersch \u00e0 San Jose (Californie) reconna\u00eet les chiffres de 0 \u00e0 9 tout comme Audrey mais aussi seize mots de base en anglais correspondant \u00e0 des termes arithm\u00e9tiques simples : \u00ab plus \u00bb, \u00ab moins \u00bb, \u00ab total \u00bb&#8230;<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-50f3250 elementor-widget elementor-widget-heading\" data-id=\"50f3250\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-medium\">Harpy<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3211928 elementor-widget elementor-widget-image\" data-id=\"3211928\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"320\" height=\"231\" src=\"https:\/\/datascientest.com\/wp-content\/uploads\/2024\/05\/harpy-speech-recognition.jpg\" class=\"attachment-full size-full wp-image-241068\" alt=\"\" srcset=\"https:\/\/datascientest.com\/wp-content\/uploads\/2024\/05\/harpy-speech-recognition.jpg 320w, https:\/\/datascientest.com\/wp-content\/uploads\/2024\/05\/harpy-speech-recognition-300x217.jpg 300w\" sizes=\"(max-width: 320px) 100vw, 320px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3907def elementor-widget elementor-widget-text-editor\" data-id=\"3907def\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">Au d\u00e9but des <strong>ann\u00e9es 70<\/strong>, sous l\u2019impulsion de l\u2019agence de d\u00e9fense am\u00e9ricaine DARPA, le<strong> syst\u00e8me Harpy de l\u2019universit\u00e9 Carnegie Mellon<\/strong> est mis en oeuvre. Harpy parvient \u00e0 identifier tr\u00e8s pr\u00e9cis\u00e9ment 1011 mots, soit une capacit\u00e9 comparable \u00e0 celle d\u2019un enfant de trois ans. Il y a l\u00e0 une petite victoire et il s\u2019ensuit une vague d\u2019enthousiasme pour la recherche en reconnaissance vocale. <\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-81de748 elementor-align-center button-principale elementor-widget elementor-widget-button\" data-id=\"81de748\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-button-wrapper\">\n\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm elementor-animation-grow\" href=\"https:\/\/datascientest.com\/formation-intelligence-artificielle\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t<span class=\"elementor-button-text\">Apprendre \u00e0 d\u00e9velopper une reconnaissance vocale<\/span>\n\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-d86cc79 elementor-widget elementor-widget-heading\" data-id=\"d86cc79\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-medium\">Tangora<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-f2e5e4b elementor-widget elementor-widget-text-editor\" data-id=\"f2e5e4b\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">Jusqu\u2019\u00e0 pr\u00e9sent, c\u2019est la d\u00e9tection des phon\u00e8mes (unit\u00e9s sonores) qui a \u00e9t\u00e9 mise \u00e0 contribution pour reconstituer des mots. \u00c0 partir des <strong>ann\u00e9es 80<\/strong>, la reconnaissance vocale adopte de nouvelles approches notamment les mod\u00e8les statistiques. C\u2019est sur cette base qu\u2019a \u00e9t\u00e9 con\u00e7u <strong>Tangora d\u2019IBM<\/strong>, qui tente de pr\u00e9dire les mots qui devraient suivre en fonction de ce qui a d\u00e9j\u00e0 \u00e9t\u00e9 analys\u00e9. Tangora n\u00e9cessite une vingtaine de minutes d\u2019entra\u00eenement, suite \u00e0 quoi, il est capable de reconna\u00eetre 20 000 mots et aussi des phrases compl\u00e8tes. <\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-7b4b1c0 elementor-widget elementor-widget-heading\" data-id=\"7b4b1c0\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-medium\">Dragon Naturally Speaking<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-5220676 elementor-widget elementor-widget-image\" data-id=\"5220676\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"800\" height=\"413\" src=\"https:\/\/datascientest.com\/wp-content\/uploads\/2024\/05\/Dragon-Naturally-Speaking-voice-recognition.jpg\" class=\"attachment-full size-full wp-image-241072\" alt=\"\" srcset=\"https:\/\/datascientest.com\/wp-content\/uploads\/2024\/05\/Dragon-Naturally-Speaking-voice-recognition.jpg 800w, https:\/\/datascientest.com\/wp-content\/uploads\/2024\/05\/Dragon-Naturally-Speaking-voice-recognition-300x155.jpg 300w, https:\/\/datascientest.com\/wp-content\/uploads\/2024\/05\/Dragon-Naturally-Speaking-voice-recognition-768x396.jpg 768w\" sizes=\"(max-width: 800px) 100vw, 800px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-41bc8a7 elementor-widget elementor-widget-text-editor\" data-id=\"41bc8a7\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">En 1997, la soci\u00e9t\u00e9 Nuance pr\u00e9sente son logiciel <strong>Dragon Professional<\/strong> et il y a l\u00e0 une avanc\u00e9e majeure. Cet outil n\u00e9cessite plusieurs heures d\u2019apprentissage, mais une fois l\u2019entra\u00eenement achev\u00e9, un individu peut s\u2019exprimer librement et ne plus avoir \u00e0 taper ses textes. Dragon est capable de d\u00e9tecter 100 mots \u00e0 la minute.\u00a0 Il va \u00eatre adopt\u00e9 par de nombreux docteurs et avocats. Dans la foul\u00e9e, l\u2019\u00e9dition XP de Windows qui appara\u00eet en 2001 int\u00e8gre un outil de reconnaissance vocale.<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-f160624 elementor-widget elementor-widget-heading\" data-id=\"f160624\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-medium\">Google Voice Search \/ Google Assistant<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-77e3f79 elementor-widget elementor-widget-text-editor\" data-id=\"77e3f79\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">Durant les ann\u00e9es 2000, le <strong>traitement informatis\u00e9 de la voix<\/strong> se voit second\u00e9 par l\u2019intelligence artificielle. Google Voice Search a ainsi choisi de combiner des <a href=\"https:\/\/datascientest.com\/3-algorithmes-de-machine-learning-utiles-pour-votre-business\">algorithmes de machine learning<\/a> avec l\u2019usage de serveurs \u00e0 tr\u00e8s haute capacit\u00e9. L\u2019application est lanc\u00e9e en 2008 et marque des progr\u00e8s \u00e9normes. Ce produit, qui va devenir <strong>Google Assistant<\/strong>, n\u2019est pas mis en avant comme il se doit et c\u2019est un autre service qui va lui voler la vedette.<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-010c896 elementor-widget elementor-widget-heading\" data-id=\"010c896\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-medium\">Siri<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-52e7fcc elementor-widget elementor-widget-image\" data-id=\"52e7fcc\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"700\" height=\"385\" src=\"https:\/\/datascientest.com\/wp-content\/uploads\/2024\/05\/apple-siri-voice-recognition.jpg\" class=\"attachment-full size-full wp-image-241073\" alt=\"\" srcset=\"https:\/\/datascientest.com\/wp-content\/uploads\/2024\/05\/apple-siri-voice-recognition.jpg 700w, https:\/\/datascientest.com\/wp-content\/uploads\/2024\/05\/apple-siri-voice-recognition-300x165.jpg 300w\" sizes=\"(max-width: 700px) 100vw, 700px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-a61fd54 elementor-widget elementor-widget-text-editor\" data-id=\"a61fd54\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">En <strong>2011<\/strong>, Apple fait sensation en annon\u00e7ant que Siri, un assistant virtuel capable de comprendre ce que nous lui disons, va \u00eatre disponible sur tous les nouveaux <strong>iPhone<\/strong>. Il s\u2019agit d\u2019une \u00e9tape majeure car d\u00e9sormais la reconnaissance vocale devient un outil d\u2019usage courant. Dans la foul\u00e9e, Alexa d&rsquo; Amazon et Cortana de Microsoft font leur apparition en 2014.<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-8d00ee2 e-flex e-con-boxed e-con\" data-id=\"8d00ee2\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-76b4013 elementor-widget elementor-widget-heading\" data-id=\"76b4013\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Comment fonctionne la reconnaissance vocale ?<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-833409a elementor-widget elementor-widget-text-editor\" data-id=\"833409a\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">Mais alors, comment proc\u00e8de une application de reconnaissance vocale de nos jours ?<\/span><\/p><p><span style=\"font-weight: 400;\">La <strong>collecte du mat\u00e9riau sonore<\/strong> est effectu\u00e9e \u00e0 l\u2019aide d\u2019un microphone qui transforme les signaux\u00a0 en impulsions \u00e9lectriques, lesquelles se voient converties en un signal analogique lui-m\u00eame traduit sous une num\u00e9rique.<\/span><\/p><p><span style=\"font-weight: 400;\">\u00c0 partir de l\u00e0, <strong>le machine learning entre en jeu<\/strong>. Il fait correspondre les phon\u00e8mes \u00e0 des unit\u00e9s syntaxiques, <\/span><span style=\"font-weight: 400;\">associe les fr\u00e9quences sonores d\u00e9cod\u00e9es \u00e0 des mots, puis <\/span><span style=\"font-weight: 400;\">d\u00e9duit la s\u00e9quence de mots la plus appropri\u00e9e. Le syst\u00e8me met \u00e0 profit des mod\u00e8les de r\u00e9f\u00e9rence pour l\u2019aider dans cette d\u00e9marche consistant \u00e0 <\/span><span style=\"font-weight: 400;\">identifier les suites de mots les plus probables. <\/span><span style=\"font-weight: 400;\">Les <a href=\"https:\/\/datascientest.com\/formation-nlp\">techniques du traitement du langage naturel<\/a> veillent \u00e0 <strong>extraire de la s\u00e9mantique<\/strong> : le programme de reconnaissance vocale s\u2019acharne \u00e0 comprendre le sens de ce qui y est exprim\u00e9.\u00a0<\/span><\/p><p><span style=\"font-weight: 400;\">C\u2019est ainsi que l\u2019on peut obtenir des applications de dict\u00e9e vocale ou de conversation de plus en plus plus proches de ce que l\u2019on obtiendrait dans la r\u00e9alit\u00e9 humaine.<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-0418c1a elementor-align-center button-principale elementor-widget elementor-widget-button\" data-id=\"0418c1a\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-button-wrapper\">\n\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm elementor-animation-grow\" href=\"https:\/\/datascientest.com\/formation-intelligence-artificielle\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t<span class=\"elementor-button-text\">Se former aux IA de reconnaissance vocale<\/span>\n\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-53c5bd7 elementor-widget elementor-widget-html\" data-id=\"53c5bd7\" data-element_type=\"widget\" data-widget_type=\"html.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<script type=\"application\/ld+json\">\r\n{\r\n  \"@context\": \"https:\/\/schema.org\",\r\n  \"@type\": \"FAQPage\",\r\n  \"mainEntity\": [{\r\n    \"@type\": \"Question\",\r\n    \"name\": \"Qu'est-ce que la reconnaissance vocale ?\",\r\n    \"acceptedAnswer\": {\r\n      \"@type\": \"Answer\",\r\n      \"text\": \"La reconnaissance vocale est une technologie qui permet aux ordinateurs et autres appareils de comprendre et de traiter la parole humaine. Elle convertit les mots parl\u00e9s en texte ou en actions.\"\r\n    }\r\n  },{\r\n    \"@type\": \"Question\",\r\n    \"name\": \"Comment fonctionne la reconnaissance vocale ?\",\r\n    \"acceptedAnswer\": {\r\n      \"@type\": \"Answer\",\r\n      \"text\": \"La reconnaissance vocale utilise des algorithmes d'apprentissage automatique pour analyser les sons, les fr\u00e9quences et les mod\u00e8les de la parole humaine. Elle compare ces sons \u00e0 une base de donn\u00e9es de mots et de phrases pour identifier ce qui est dit.\"\r\n    }\r\n  },{\r\n    \"@type\": \"Question\",\r\n    \"name\": \"Quelles sont les applications courantes de la reconnaissance vocale ?\",\r\n    \"acceptedAnswer\": {\r\n      \"@type\": \"Answer\",\r\n      \"text\": \"\\n - Assistants virtuels (comme Siri, Google Assistant, Alexa) \\n - Transcription automatique \\n - Commandes vocales pour contr\u00f4ler des appareils \\n - Services clients automatis\u00e9s \\n - Accessibilit\u00e9 pour les personnes handicap\u00e9es\"\r\n    }\r\n  },{\r\n    \"@type\": \"Question\",\r\n    \"name\": \"Quels sont les principaux fournisseurs de technologies de reconnaissance vocale ?\",\r\n    \"acceptedAnswer\": {\r\n      \"@type\": \"Answer\",\r\n      \"text\": \"\\n - Google (Google Cloud Speech-to-Text) \\n - Apple (Siri) \\n - Amazon (Alexa) \\n - Microsoft (Cortana, Azure Speech Services) \\n - IBM (Watson Speech to Text)\"\r\n    }\r\n  }]\r\n}\r\n<\/script>\r\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>Parler \u00e0 son smartphone est devenu une activit\u00e9 courante. Et un grand nombre de syst\u00e8mes de reconnaissance vocale se r\u00e9v\u00e8lent tr\u00e8s dou\u00e9s. Pourtant, le chemin qui a amen\u00e9 \u00e0 la compr\u00e9hension de la voix humaine s&rsquo;est \u00e9tendu sur plusieurs d\u00e9cennies. La reconnaissance vocale est devenue un service courant que l\u2019on retrouve dans de tr\u00e8s nombreux [&hellip;]<\/p>\n","protected":false},"author":77,"featured_media":241035,"comment_status":"open","ping_status":"open","sticky":false,"template":"elementor_theme","format":"standard","meta":{"content-type":"","inline_featured_image":false},"categories":[2500],"tags":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v21.7 (Yoast SEO v21.7) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Reconnaissance vocale : d\u00e9finition, origines et applications technologiques<\/title>\n<meta name=\"description\" content=\"D\u00e9couvrez les applications innovantes dans divers secteurs de la reconnaissance vocale et comment cette technologie transforme notre interaction avec les appareils num\u00e9riques.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/datascientest.com\/reconnaissance-vocale-tout-savoir\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Reconnaissance vocale : d\u00e9finition, origines et applications technologiques\" \/>\n<meta property=\"og:url\" content=\"https:\/\/datascientest.com\/reconnaissance-vocale-tout-savoir\" \/>\n<meta property=\"og:site_name\" content=\"Formation Data Science | DataScientest.com\" \/>\n<meta property=\"article:published_time\" content=\"2024-06-11T05:30:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-06-13T09:55:33+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/datascientest.com\/wp-content\/uploads\/2024\/05\/reconnaissance-vocale-datascientest.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"686\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Raphael Kassel\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u00c9crit par\" \/>\n\t<meta name=\"twitter:data1\" content=\"Raphael Kassel\" \/>\n\t<meta name=\"twitter:label2\" content=\"Dur\u00e9e de lecture estim\u00e9e\" \/>\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\":\"WebPage\",\"@id\":\"https:\/\/datascientest.com\/reconnaissance-vocale-tout-savoir\",\"url\":\"https:\/\/datascientest.com\/reconnaissance-vocale-tout-savoir\",\"name\":\"Reconnaissance vocale : d\u00e9finition, origines et applications technologiques\",\"isPartOf\":{\"@id\":\"https:\/\/datascientest.com\/#website\"},\"datePublished\":\"2024-06-11T05:30:00+00:00\",\"dateModified\":\"2024-06-13T09:55:33+00:00\",\"author\":{\"@id\":\"https:\/\/datascientest.com\/#\/schema\/person\/6eca16f63daaafcbc96e15549b9d4ee1\"},\"description\":\"D\u00e9couvrez les applications innovantes dans divers secteurs de la reconnaissance vocale et comment cette technologie transforme notre interaction avec les appareils num\u00e9riques.\",\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/datascientest.com\/reconnaissance-vocale-tout-savoir\"]}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/datascientest.com\/#website\",\"url\":\"https:\/\/datascientest.com\/\",\"name\":\"Formation Data Science | DataScientest.com\",\"description\":\"Leader de la formation en Data Science\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/datascientest.com\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"fr-FR\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/datascientest.com\/#\/schema\/person\/6eca16f63daaafcbc96e15549b9d4ee1\",\"name\":\"Raphael Kassel\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\/\/datascientest.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/datascientest.com\/wp-content\/uploads\/2023\/11\/raph.jpeg\",\"contentUrl\":\"https:\/\/datascientest.com\/wp-content\/uploads\/2023\/11\/raph.jpeg\",\"caption\":\"Raphael Kassel\"},\"description\":\"Raphael Kassel est le Head of Data Programs chez DataScientest. Il supervise une \u00e9quipe Data, impl\u00e9mente de nouveaux parcours comme \\\"Chef de projet IA\\\" et \\\"Data Product Manager\\\", et contribue \u00e0 la modernisation des op\u00e9rations du groupe. En collaboration \u00e9troite avec l'\u00e9quipe de d\u00e9veloppement, il adapte l'accompagnement acad\u00e9mique aux \u00e9volutions de l'\u00e9quipe data et \u00e0 l'internationalisation.\",\"sameAs\":[\"https:\/\/www.linkedin.com\/in\/raphaelkassel\/\",\"Data Science\"],\"url\":\"https:\/\/datascientest.com\/author\/raphaelkassel\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Reconnaissance vocale : d\u00e9finition, origines et applications technologiques","description":"D\u00e9couvrez les applications innovantes dans divers secteurs de la reconnaissance vocale et comment cette technologie transforme notre interaction avec les appareils num\u00e9riques.","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:\/\/datascientest.com\/reconnaissance-vocale-tout-savoir","og_locale":"fr_FR","og_type":"article","og_title":"Reconnaissance vocale : d\u00e9finition, origines et applications technologiques","og_url":"https:\/\/datascientest.com\/reconnaissance-vocale-tout-savoir","og_site_name":"Formation Data Science | DataScientest.com","article_published_time":"2024-06-11T05:30:00+00:00","article_modified_time":"2024-06-13T09:55:33+00:00","og_image":[{"width":1200,"height":686,"url":"https:\/\/datascientest.com\/wp-content\/uploads\/2024\/05\/reconnaissance-vocale-datascientest.jpg","type":"image\/jpeg"}],"author":"Raphael Kassel","twitter_card":"summary_large_image","twitter_misc":{"\u00c9crit par":"Raphael Kassel","Dur\u00e9e de lecture estim\u00e9e":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/datascientest.com\/reconnaissance-vocale-tout-savoir","url":"https:\/\/datascientest.com\/reconnaissance-vocale-tout-savoir","name":"Reconnaissance vocale : d\u00e9finition, origines et applications technologiques","isPartOf":{"@id":"https:\/\/datascientest.com\/#website"},"datePublished":"2024-06-11T05:30:00+00:00","dateModified":"2024-06-13T09:55:33+00:00","author":{"@id":"https:\/\/datascientest.com\/#\/schema\/person\/6eca16f63daaafcbc96e15549b9d4ee1"},"description":"D\u00e9couvrez les applications innovantes dans divers secteurs de la reconnaissance vocale et comment cette technologie transforme notre interaction avec les appareils num\u00e9riques.","inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/datascientest.com\/reconnaissance-vocale-tout-savoir"]}]},{"@type":"WebSite","@id":"https:\/\/datascientest.com\/#website","url":"https:\/\/datascientest.com\/","name":"Formation Data Science | DataScientest.com","description":"Leader de la formation en Data Science","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/datascientest.com\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"fr-FR"},{"@type":"Person","@id":"https:\/\/datascientest.com\/#\/schema\/person\/6eca16f63daaafcbc96e15549b9d4ee1","name":"Raphael Kassel","image":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/datascientest.com\/#\/schema\/person\/image\/","url":"https:\/\/datascientest.com\/wp-content\/uploads\/2023\/11\/raph.jpeg","contentUrl":"https:\/\/datascientest.com\/wp-content\/uploads\/2023\/11\/raph.jpeg","caption":"Raphael Kassel"},"description":"Raphael Kassel est le Head of Data Programs chez DataScientest. Il supervise une \u00e9quipe Data, impl\u00e9mente de nouveaux parcours comme \"Chef de projet IA\" et \"Data Product Manager\", et contribue \u00e0 la modernisation des op\u00e9rations du groupe. En collaboration \u00e9troite avec l'\u00e9quipe de d\u00e9veloppement, il adapte l'accompagnement acad\u00e9mique aux \u00e9volutions de l'\u00e9quipe data et \u00e0 l'internationalisation.","sameAs":["https:\/\/www.linkedin.com\/in\/raphaelkassel\/","Data Science"],"url":"https:\/\/datascientest.com\/author\/raphaelkassel"}]}},"_links":{"self":[{"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/posts\/241032"}],"collection":[{"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/users\/77"}],"replies":[{"embeddable":true,"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/comments?post=241032"}],"version-history":[{"count":0,"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/posts\/241032\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/media\/241035"}],"wp:attachment":[{"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/media?parent=241032"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/categories?post=241032"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/tags?post=241032"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}