{"id":248,"date":"2026-06-29T09:34:31","date_gmt":"2026-06-29T13:34:31","guid":{"rendered":"https:\/\/carleton.ca\/richarddansereau\/?p=248"},"modified":"2026-06-30T11:16:48","modified_gmt":"2026-06-30T15:16:48","slug":"journal-paper-on-audio-visual-speech-enhancement-with-posterior-sampling-methods-in-recurrent-variational-autoencoders-2","status":"publish","type":"post","link":"https:\/\/carleton.ca\/richarddansereau\/2026\/journal-paper-on-audio-visual-speech-enhancement-with-posterior-sampling-methods-in-recurrent-variational-autoencoders-2\/","title":{"rendered":"Journal paper on audio-visual speech enhancement with posterior sampling methods in recurrent variational autoencoders"},"content":{"rendered":"<p><\/p>\n<table style=\"border-collapse: collapse; width: 100%;\">\n<tbody>\n<tr>\n<td style=\"width: 30%;\"><img decoding=\"async\" loading=\"lazy\" class=\"alignnone size-medium wp-image-222\" src=\"https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage-240x129.png\" alt=\"Audio-visual speech enhancement\" width=\"240\" height=\"129\" srcset=\"https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage-240x129.png 240w, https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage-400x215.png 400w, https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage-160x86.png 160w, https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage-360x194.png 360w, https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage.png 544w\" sizes=\"(max-width: 240px) 100vw, 240px\" \/><\/td>\n<td style=\"width: 70%;\">\n<h3>Journal paper in Computer Speech &amp; Language:<\/h3>\n<blockquote>\n<h4>Robust Audio\u2013Visual Speech Enhancement under Visual Occlusion using TITR\u2013CNN and Silence-Aware MALA\u2013EM.<\/h4>\n<\/blockquote>\n<p>Zohre Foroushi and Prof. Richard Dansereau present a new approach to improving speech quality in noisy environments using both audio and video information. Their work focuses on situations where the speaker\u2019s mouth may be partially blocked or difficult to see, and where background noise is strong.<\/p>\n<p>The proposed method reconstructs missing visual information from video, makes better use of quiet segments in the audio to reduce unwanted artifacts, and applies improved statistical techniques to produce clearer speech. Experiments show strong improvements in speech quality and intelligibility, even under challenging conditions.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Journal paper in Computer Speech &amp; Language: Robust Audio\u2013Visual Speech Enhancement under Visual Occlusion using TITR\u2013CNN and Silence-Aware MALA\u2013EM. Zohre Foroushi and Prof. Richard Dansereau present a new approach to improving speech quality in noisy environments using both audio and video information. Their work focuses on situations where the speaker\u2019s mouth may be partially blocked [&hellip;]<\/p>\n","protected":false},"author":6,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_relevanssi_hide_post":"","_relevanssi_hide_content":"","_relevanssi_pin_for_all":"","_relevanssi_pin_keywords":"","_relevanssi_unpin_keywords":"","_relevanssi_related_keywords":"","_relevanssi_related_include_ids":"","_relevanssi_related_exclude_ids":"","_relevanssi_related_no_append":"","_relevanssi_related_not_related":"","_relevanssi_related_posts":"","_relevanssi_noindex_reason":"","_mi_skip_tracking":false,"_exactmetrics_sitenote_active":false,"_exactmetrics_sitenote_note":"","_exactmetrics_sitenote_category":0,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":"","_links_to":"","_links_to_target":""},"categories":[1,24],"tags":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v21.2 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Journal paper on audio-visual speech enhancement with posterior sampling methods in recurrent variational autoencoders - Prof. Richard M. Dansereau<\/title>\n<meta name=\"description\" content=\"&nbsp; Journal paper in Computer Speech &amp; Language: Robust Audio\u2013Visual Speech Enhancement under Visual Occlusion using TITR\u2013CNN and Silence-Aware\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/carleton.ca\/richarddansereau\/2026\/journal-paper-on-audio-visual-speech-enhancement-with-posterior-sampling-methods-in-recurrent-variational-autoencoders-2\/\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Richard Dansereau\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/carleton.ca\/richarddansereau\/2026\/journal-paper-on-audio-visual-speech-enhancement-with-posterior-sampling-methods-in-recurrent-variational-autoencoders-2\/\",\"url\":\"https:\/\/carleton.ca\/richarddansereau\/2026\/journal-paper-on-audio-visual-speech-enhancement-with-posterior-sampling-methods-in-recurrent-variational-autoencoders-2\/\",\"name\":\"Journal paper on audio-visual speech enhancement with posterior sampling methods in recurrent variational autoencoders - Prof. Richard M. Dansereau\",\"isPartOf\":{\"@id\":\"https:\/\/carleton.ca\/richarddansereau\/#website\"},\"datePublished\":\"2026-06-29T13:34:31+00:00\",\"dateModified\":\"2026-06-30T15:16:48+00:00\",\"author\":{\"@id\":\"https:\/\/carleton.ca\/richarddansereau\/#\/schema\/person\/1b1e2d29b50d062db194d12ede69fd83\"},\"description\":\"&nbsp; Journal paper in Computer Speech &amp; Language: Robust Audio\u2013Visual Speech Enhancement under Visual Occlusion using TITR\u2013CNN and Silence-Aware\",\"breadcrumb\":{\"@id\":\"https:\/\/carleton.ca\/richarddansereau\/2026\/journal-paper-on-audio-visual-speech-enhancement-with-posterior-sampling-methods-in-recurrent-variational-autoencoders-2\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/carleton.ca\/richarddansereau\/2026\/journal-paper-on-audio-visual-speech-enhancement-with-posterior-sampling-methods-in-recurrent-variational-autoencoders-2\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/carleton.ca\/richarddansereau\/2026\/journal-paper-on-audio-visual-speech-enhancement-with-posterior-sampling-methods-in-recurrent-variational-autoencoders-2\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/carleton.ca\/richarddansereau\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"News\",\"item\":\"https:\/\/carleton.ca\/richarddansereau\/category\/news\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Publications\",\"item\":\"https:\/\/carleton.ca\/richarddansereau\/category\/news\/publications\/\"},{\"@type\":\"ListItem\",\"position\":4,\"name\":\"Journal paper on audio-visual speech enhancement with posterior sampling methods in recurrent variational autoencoders\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/carleton.ca\/richarddansereau\/#website\",\"url\":\"https:\/\/carleton.ca\/richarddansereau\/\",\"name\":\"Prof. Richard M. Dansereau\",\"description\":\"Carleton University\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/carleton.ca\/richarddansereau\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/carleton.ca\/richarddansereau\/#\/schema\/person\/1b1e2d29b50d062db194d12ede69fd83\",\"name\":\"Richard Dansereau\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/carleton.ca\/richarddansereau\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/e4fa210bdc9f4594b3bb27aa3996d03e?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/e4fa210bdc9f4594b3bb27aa3996d03e?s=96&d=mm&r=g\",\"caption\":\"Richard Dansereau\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Journal paper on audio-visual speech enhancement with posterior sampling methods in recurrent variational autoencoders - Prof. Richard M. Dansereau","description":"&nbsp; Journal paper in Computer Speech &amp; Language: Robust Audio\u2013Visual Speech Enhancement under Visual Occlusion using TITR\u2013CNN and Silence-Aware","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:\/\/carleton.ca\/richarddansereau\/2026\/journal-paper-on-audio-visual-speech-enhancement-with-posterior-sampling-methods-in-recurrent-variational-autoencoders-2\/","twitter_misc":{"Written by":"Richard Dansereau","Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/carleton.ca\/richarddansereau\/2026\/journal-paper-on-audio-visual-speech-enhancement-with-posterior-sampling-methods-in-recurrent-variational-autoencoders-2\/","url":"https:\/\/carleton.ca\/richarddansereau\/2026\/journal-paper-on-audio-visual-speech-enhancement-with-posterior-sampling-methods-in-recurrent-variational-autoencoders-2\/","name":"Journal paper on audio-visual speech enhancement with posterior sampling methods in recurrent variational autoencoders - Prof. Richard M. Dansereau","isPartOf":{"@id":"https:\/\/carleton.ca\/richarddansereau\/#website"},"datePublished":"2026-06-29T13:34:31+00:00","dateModified":"2026-06-30T15:16:48+00:00","author":{"@id":"https:\/\/carleton.ca\/richarddansereau\/#\/schema\/person\/1b1e2d29b50d062db194d12ede69fd83"},"description":"&nbsp; Journal paper in Computer Speech &amp; Language: Robust Audio\u2013Visual Speech Enhancement under Visual Occlusion using TITR\u2013CNN and Silence-Aware","breadcrumb":{"@id":"https:\/\/carleton.ca\/richarddansereau\/2026\/journal-paper-on-audio-visual-speech-enhancement-with-posterior-sampling-methods-in-recurrent-variational-autoencoders-2\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/carleton.ca\/richarddansereau\/2026\/journal-paper-on-audio-visual-speech-enhancement-with-posterior-sampling-methods-in-recurrent-variational-autoencoders-2\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/carleton.ca\/richarddansereau\/2026\/journal-paper-on-audio-visual-speech-enhancement-with-posterior-sampling-methods-in-recurrent-variational-autoencoders-2\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/carleton.ca\/richarddansereau\/"},{"@type":"ListItem","position":2,"name":"News","item":"https:\/\/carleton.ca\/richarddansereau\/category\/news\/"},{"@type":"ListItem","position":3,"name":"Publications","item":"https:\/\/carleton.ca\/richarddansereau\/category\/news\/publications\/"},{"@type":"ListItem","position":4,"name":"Journal paper on audio-visual speech enhancement with posterior sampling methods in recurrent variational autoencoders"}]},{"@type":"WebSite","@id":"https:\/\/carleton.ca\/richarddansereau\/#website","url":"https:\/\/carleton.ca\/richarddansereau\/","name":"Prof. Richard M. Dansereau","description":"Carleton University","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/carleton.ca\/richarddansereau\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/carleton.ca\/richarddansereau\/#\/schema\/person\/1b1e2d29b50d062db194d12ede69fd83","name":"Richard Dansereau","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/carleton.ca\/richarddansereau\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/e4fa210bdc9f4594b3bb27aa3996d03e?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/e4fa210bdc9f4594b3bb27aa3996d03e?s=96&d=mm&r=g","caption":"Richard Dansereau"}}]}},"acf":{"Post Thumbnail Icon":"","Post Thumbnail":{"ID":222,"id":222,"title":"Zohre-Fig1-ComputerSpeechAndLanguage","filename":"Zohre-Fig1-ComputerSpeechAndLanguage.png","filesize":60908,"url":"https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage.png","link":"https:\/\/carleton.ca\/richarddansereau\/2025\/journal-paper-on-audio-visual-speech-enhancement-with-posterior-sampling-methods-in-recurrent-variational-autoencoders\/zohre-fig1-computerspeechandlanguage\/","alt":"Audio-visual speech enhancement","author":"6","description":"","caption":"","name":"zohre-fig1-computerspeechandlanguage","status":"inherit","uploaded_to":219,"date":"2025-12-08 16:16:34","modified":"2025-12-08 16:16:52","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/carleton.ca\/richarddansereau\/wp\/wp-includes\/images\/media\/default.png","width":544,"height":293,"sizes":{"thumbnail":"https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage-160x86.png","thumbnail-width":160,"thumbnail-height":86,"medium":"https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage-240x129.png","medium-width":240,"medium-height":129,"medium_large":"https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage.png","medium_large-width":544,"medium_large-height":293,"large":"https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage-400x215.png","large-width":400,"large-height":215,"gallery-thumb":"https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage-300x230.png","gallery-thumb-width":300,"gallery-thumb-height":230,"1536x1536":"https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage.png","1536x1536-width":544,"1536x1536-height":293,"2048x2048":"https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage.png","2048x2048-width":544,"2048x2048-height":293,"banner":"https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage.png","banner-width":544,"banner-height":293,"people":"https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage-200x200.png","people-width":200,"people-height":200,"post-thumb":"https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage-300x230.png","post-thumb-width":300,"post-thumb-height":230,"rotator-image":"https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage.png","rotator-image-width":544,"rotator-image-height":293,"video-thumb":"https:\/\/carleton.ca\/richarddansereau\/wp-content\/uploads\/Zohre-Fig1-ComputerSpeechAndLanguage-360x194.png","video-thumb-width":360,"video-thumb-height":194}}},"_links":{"self":[{"href":"https:\/\/carleton.ca\/richarddansereau\/wp-json\/wp\/v2\/posts\/248"}],"collection":[{"href":"https:\/\/carleton.ca\/richarddansereau\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/carleton.ca\/richarddansereau\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/carleton.ca\/richarddansereau\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/carleton.ca\/richarddansereau\/wp-json\/wp\/v2\/comments?post=248"}],"version-history":[{"count":1,"href":"https:\/\/carleton.ca\/richarddansereau\/wp-json\/wp\/v2\/posts\/248\/revisions"}],"predecessor-version":[{"id":249,"href":"https:\/\/carleton.ca\/richarddansereau\/wp-json\/wp\/v2\/posts\/248\/revisions\/249"}],"wp:attachment":[{"href":"https:\/\/carleton.ca\/richarddansereau\/wp-json\/wp\/v2\/media?parent=248"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/carleton.ca\/richarddansereau\/wp-json\/wp\/v2\/categories?post=248"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/carleton.ca\/richarddansereau\/wp-json\/wp\/v2\/tags?post=248"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}