{"id":9283,"date":"2021-08-03T03:03:46","date_gmt":"2021-08-02T19:03:46","guid":{"rendered":"https:\/\/qat-cde.nus.edu.sg\/ece\/?p=9283"},"modified":"2023-03-07T14:41:57","modified_gmt":"2023-03-07T06:41:57","slug":"resources-hlt","status":"publish","type":"post","link":"https:\/\/cde.nus.edu.sg\/ece\/resources-hlt\/","title":{"rendered":"Resources &#8211; HLT"},"content":{"rendered":"\n<h3>Tutorial<\/h3>\n<p style=\"text-align: justify\">Berrak Sisman (SUTD &amp; NUS, Singapore), Yu Tsao (Academia SINICA, Taiwan) and Haizhou Li (NUS, Singapore) gave a tutorial on\u00a0voice conversion\u00a0at Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2020, which was held in New Zealand. The recording of their tutorial can be found\u00a0<a href=\"https:\/\/drive.google.com\/file\/d\/1URqj8YJgWG7WaaCItMq_jp2QnR9idGNI\/view?usp=sharing\" target=\"_blank\" rel=\"noopener\">here<\/a>.<\/p>\n<h3>Workshop<\/h3>\n<p style=\"text-align: justify\">Voice Conversion Challenge 2020 workshop: Organizers: Tomoki Toda, Wen-Chin Huang, Junichi Yamagishi, Yi Zhao, Tomi Kinnunen, Zhenhua Ling, Rohan Kumar Das and Xiaohai Tian. The recording of the workshop video can be found\u00a0<a href=\"https:\/\/www.youtube.com\/watch?v=eDbfcFy1OEg&amp;t=25s\" target=\"_blank\" rel=\"noopener\">here<\/a>.<\/p>\n<h3>Code<\/h3>\n<ol>\n<li>\n<p>D-score: Holistic Dialogue Evaluation without Reference:\u00a0<a href=\"https:\/\/github.com\/e0397123\/D-score\">[https:\/\/github.com\/e0397123\/D-score<\/a>]<\/p>\n<\/li>\n<li>\n<p>DynaEval: Unifying Turn and Dialogue Level Evaluation:\u00a0[<a href=\"https:\/\/github.com\/e0397123\/DynaEval\">https:\/\/github.com\/e0397123\/DynaEval<\/a>]<\/p>\n<\/li>\n<li>\n<p>Unified framework for speaker and utterance verification: [<a href=\"https:\/\/github.com\/sn1ff1918\/SUV\" target=\"_blank\" rel=\"noopener noreferrer\" data-auth=\"NotApplicable\">https:\/\/github.com\/sn1ff1918\/SUV]<\/a><\/p>\n<\/li>\n<li>\n<p>Multi-level adaptive speech activity detector: [<a id=\"LPNoLP803273\" href=\"https:\/\/github.com\/bidishasharma\/MultiSAD\/\" target=\"_blank\" rel=\"noopener noreferrer\" data-auth=\"NotApplicable\">https:\/\/github.com\/bidishasharma\/MultiSAD\/]<\/a><\/p>\n<\/li>\n<li>\n<p>PESnQ: Perceptual evaluation of singing quality:\u00a0<a href=\"https:\/\/www.smcnus.org\/wp-content\/uploads\/2013\/09\/WP-P2.5.pdf\">[<\/a><a href=\"https:\/\/github.com\/chitralekha18\/PESnQ_APSIPA2017\">https:\/\/github.com\/chitralekha18\/PESnQ_APSIPA2017]\u00a0<\/a>[<a href=\"https:\/\/www.smcnus.org\/wp-content\/uploads\/2013\/09\/WP-P2.5.pdf\" target=\"_blank\" rel=\"noopener\">Paper<\/a>]<\/p>\n<\/li>\n<li>\n<p>Automatic sung-lyrics data annotation:\u00a0[<a href=\"https:\/\/github.com\/chitralekha18\/AutomaticSungLyricsAnnotation_ISMIR2018.git\">https:\/\/github.com\/chitralekha18\/AutomaticSungLyricsAnnotation_ISMIR2018.git]<\/a>\u00a0[<a href=\"http:\/\/ismir2018.ircam.fr\/doc\/pdfs\/30_Paper.pdf\" target=\"_blank\" rel=\"noopener\">Paper<\/a>]<\/p>\n<\/li>\n<li>\n<p>NUS AutoLyrixAlign:\u00a0[<a id=\"LPlnk997025\" href=\"https:\/\/github.com\/chitralekha18\/AutoLyrixAlign.git\" target=\"_blank\" rel=\"noopener noreferrer\" data-auth=\"NotApplicable\">https:\/\/github.com\/chitralekha18\/AutoLyrixAlign.git<\/a>]<\/p>\n<\/li>\n<li>\n<p>Emotional voice conversion and\/or speaker identity conversion with non-parallel training data: [<a href=\"https:\/\/github.com\/KunZhou9646\/emotional-voice-conversion-with-CycleGAN-and-CWT-for-Spectrum-and-F0\">https:\/\/github.com\/KunZhou9646\/emotional-voice-conversion-with-CycleGAN-and-CWT-for-Spectrum-and-F0<\/a>]<\/p>\n<\/li>\n<li>\n<p>Speaker-independent emotional voice conversion based on conditional VAW-GAN and CWT: [<a href=\"https:\/\/github.com\/KunZhou9646\/Speaker-independent-emotional-voice-conversion-based-on-conditional-VAW-GAN-and-CWT\">https:\/\/github.com\/KunZhou9646\/Speaker-independent-emotional-voice-conversion-based-on-conditional-VAW-GAN-and-CWT<\/a>]<\/p>\n<\/li>\n<li>\n<p>Transformer-based dialect identification:\u00a0[<a href=\"https:\/\/github.com\/LIN-WANQIU\/ADI17\">https:\/\/github.com\/LIN-WANQIU\/ADI17<\/a>]<\/p>\n<\/li>\n<li>Multi-modal target speaker extraction with visual cues: [<a href=\"https:\/\/github.com\/zexupan\/MuSE\">https:\/\/github.com\/zexupan\/MuSE<\/a>]<\/li>\n<\/ol>\n<h3>Data Set<\/h3>\n<ol>\n<li>\n<p>NHSS: A speech and singing parallel database:\u00a0[<a href=\"https:\/\/hltnus.github.io\/NHSSDatabase\/index.html\">https:\/\/hltnus.github.io\/NHSSDatabase\/index.html<\/a>]<\/p>\n<\/li>\n<li>\n<p>Solo singing damp dataset with aligned lyrics: [<a href=\"https:\/\/github.com\/chitralekha18\/lyrics-aligned-solo-singing-dataset\">https:\/\/github.com\/chitralekha18\/lyrics-aligned-solo-singing-dataset]<\/a><\/p>\n<\/li>\n<li>\n<p>Pronunciation evaluation in singing: [<a href=\"https:\/\/github.com\/chitralekha18\/Dataset-for-pronunciation-evaluation-in-singing\">https:\/\/github.com\/chitralekha18\/Dataset-for-pronunciation-evaluation-in-singing<\/a>]<\/p>\n<\/li>\n<li>\n<p>RSL2019: A realistic speech localization corpus: [<a href=\"https:\/\/bidishasharma.github.io\/RSL2019\/\" data-auth=\"NotApplicable\">https:\/\/bidishasharma.github.io\/RSL2019\/]<\/a><\/p>\n<\/li>\n<li>\n<p>Voice conversion challenge (VCC) 2020 database:\u00a0[<a href=\"https:\/\/github.com\/nii-yamagishilab\/VCC2020-database\">https:\/\/github.com\/nii-yamagishilab\/VCC2020-database<\/a>]<\/p>\n<\/li>\n<li>Emotional Speech Dataset (ESD) for speech synthesis and voice conversion:\u00a0[<a href=\"https:\/\/github.com\/HLTSingapore\/Emotional-Speech-Data\">https:\/\/github.com\/HLTSingapore\/Emotional-Speech-Data<\/a>]<\/li>\n<\/ol>\n<h3 class=\"elementor-heading-title elementor-size-default\">Demo<\/h3>\n<ol>\n<li>\n<p>Robust sound recognition: A neuromorphic approach: [<a href=\"https:\/\/youtu.be\/MIVvNb0sWOM\">https:\/\/youtu.be\/MIVvNb0sWOM]<\/a><\/p>\n<\/li>\n<li>\n<p>Speak-to-Sing: <a href=\"https:\/\/drive.google.com\/open?id=1KKURwKQAQbEOPwufHOkrBFguVQk-ElOg\">[Poster]<\/a><\/p>\n<\/li>\n<li>\n<p>MuSigPro: Automatic leaderboard generation of singers using reference-Independent singing quality evaluation Methods:<a href=\"https:\/\/youtu.be\/IAlsECqd9IE\">\u00a0[https:\/\/youtu.be\/IAlsECqd9IE]<\/a><\/p>\n<\/li>\n<li>\n<p>AutoLyrixAlign: Automatic lyrics-to-audio alignment system for polyphonic music audio<\/p>\n<\/li>\n<li>\n<p>Demo video: [<a href=\"https:\/\/drive.google.com\/file\/d\/1oGdXQ9d3SfecPu8R3TBhY8kufFfXsd8_\/view\" target=\"_blank\" rel=\"noopener noreferrer\" data-auth=\"NotApplicable\">https:\/\/drive.google.com\/file\/d\/1oGdXQ9d3SfecPu8R3TBhY8kufFfXsd8_\/view]<\/a><\/p>\n<\/li>\n<li>\n<p>Webpage link: [<a id=\"LPlnk333462\" href=\"https:\/\/autolyrixalign.hltnus.org\/\" target=\"_blank\" rel=\"noopener noreferrer\" data-auth=\"NotApplicable\">https:\/\/autolyrixalign.hltnus.org<\/a>]<\/p>\n<\/li>\n<li>\n<p>MuSigPro demo video\u00a0[<a href=\"https:\/\/www.youtube.com\/watch?v=E0wwwpxaUOM\">https:\/\/www.youtube.com\/watch?v=E0wwwpxaUOM<\/a>] Webpage link: [<a id=\"LPlnk333462\" href=\"https:\/\/musigpro.com\/\" target=\"_blank\" rel=\"noopener noreferrer\" data-auth=\"NotApplicable\">https:\/\/musigpro.com\/<\/a>]\u00a0Google play store link: [<a id=\"LPlnk333462\" href=\"https:\/\/play.google.com\/store\/apps\/details?id=com.musigpro.app\" target=\"_blank\" rel=\"noopener noreferrer\" data-auth=\"NotApplicable\">https:\/\/play.google.com\/store\/apps\/details?id=com.musigpro.app<\/a>]<\/p>\n<\/li>\n<li>\n<p>Multi-modal target speaker extraction with visual cues: [<a href=\"https:\/\/github.com\/zexupan\/MuSE\">https:\/\/github.com\/zexupan\/MuSE<\/a>]<\/p>\n<\/li>\n<\/ol>\n<h3 class=\"elementor-heading-title elementor-size-default\">Poster<\/h3>\n<ol>\n<li>\n<p>HLT Lab research areas <a href=\"\/ece\/wp-content\/uploads\/sites\/3\/2021\/08\/HLT-Lab-research-areas.pdf\" target=\"_blank\" rel=\"noopener\">[Pdf \u2013 download] <\/a><a href=\"\/ece\/wp-content\/uploads\/sites\/3\/2021\/08\/HLT-Lab-research-areas.png\" target=\"_blank\" rel=\"noopener\">[Image\/png\u00a0\u2013 download]<\/a><\/p>\n<\/li>\n<li>\n<p>Automatic speech recognition for code-mixed singaporean languages\u00a0<a href=\"\/ece\/wp-content\/uploads\/sites\/3\/2021\/08\/Automatic-Speech-Recognition-for-Code-Mixed-Singaporean-Languages-1.pdf\" target=\"_blank\" rel=\"noopener\">[Pdf \u2013 download] <\/a><a href=\"\/ece\/wp-content\/uploads\/sites\/3\/2021\/08\/Automatic-Speech-Recognition-for-Code-Mixed-Singaporean-Languages.png\" target=\"_blank\" rel=\"noopener\">[Image\/png\u00a0\u2013 download]<\/a><\/p>\n<\/li>\n<li>\n<p>Neuromorphic computing\u00a0<a href=\"\/ece\/wp-content\/uploads\/sites\/3\/2021\/08\/Neuromorphic-Computing-1.pdf\" target=\"_blank\" rel=\"noopener\">[Pdf \u2013 download] <\/a><a href=\"\/ece\/wp-content\/uploads\/sites\/3\/2021\/08\/Neuromorphic-Computing.png\" target=\"_blank\" rel=\"noopener\">[Image\/png\u00a0\u2013 download]<\/a><\/p>\n<\/li>\n<li>\n<p>Let\u2019s perfect everyone\u2019s singing\u00a0<a href=\"\/ece\/wp-content\/uploads\/sites\/3\/2021\/08\/Lets-Perfect-Everyones-Singing-1.pdf\" target=\"_blank\" rel=\"noopener\">[Pdf \u2013 download] <\/a><a href=\"\/ece\/wp-content\/uploads\/sites\/3\/2021\/08\/Lets-Perfect-Everyones-Singing.png\" target=\"_blank\" rel=\"noopener\">[Image\/png\u00a0\u2013 download]<\/a><\/p>\n<\/li>\n<li>\n<p>Recognize speakers from their voice\u00a0<a href=\"\/ece\/wp-content\/uploads\/sites\/3\/2021\/08\/Recognize-Speakers-from-their-Voice-1.pdf\" target=\"_blank\" rel=\"noopener\">[Pdf \u2013 download] <\/a><a href=\"\/ece\/wp-content\/uploads\/sites\/3\/2021\/08\/Recognize-Speakers-from-their-Voice.png\" target=\"_blank\" rel=\"noopener\">[Image\/png\u00a0\u2013 download]<\/a><\/p>\n<\/li>\n<li>\n<p>Voice conversion <a href=\"\/ece\/wp-content\/uploads\/sites\/3\/2021\/08\/Voice-Conversion-1.pdf\">[Pdf \u2013 download] <\/a><a href=\"\/ece\/wp-content\/uploads\/sites\/3\/2021\/08\/Voice-Conversion.png\" target=\"_blank\" rel=\"noopener\">[Image\/png\u00a0\u2013 download]<\/a><\/p>\n<\/li>\n<\/ol>\n<h3 class=\"elementor-heading-title elementor-size-default\">HLT Logo<\/h3>\n<ol>\n<li>\n<p>HLT Logo\u00a0<a href=\"\/ece\/wp-content\/uploads\/sites\/3\/2021\/08\/HLT-logo.pdf\" target=\"_blank\" rel=\"noopener\">[Pdf \u2013 download]<\/a><\/p>\n<\/li>\n<li>HLT Logo\u00a0<a href=\"\/ece\/wp-content\/uploads\/sites\/3\/2021\/08\/HLT-logo-1.png\" target=\"_blank\" rel=\"noopener\">[Image\/png\u00a0\u2013 download]<\/a><\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"<p>Tutorial Berrak Sisman (SUTD &amp; NUS, Singapore), Yu Tsao (Academia SINICA, Taiwan) and Haizhou Li (NUS, Singapore) gave a tutorial on\u00a0voice conversion\u00a0at Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2020, which was held in New Zealand. The recording of their tutorial can be found\u00a0here. Workshop Voice Conversion Challenge 2020 workshop: Organizers: Tomoki [&hellip;]<\/p>\n","protected":false},"author":31,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""}},"footnotes":""},"categories":[1],"tags":[],"class_list":["post-9283","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"acf":[],"_links":{"self":[{"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/posts\/9283","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/users\/31"}],"replies":[{"embeddable":true,"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/comments?post=9283"}],"version-history":[{"count":1,"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/posts\/9283\/revisions"}],"predecessor-version":[{"id":17082,"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/posts\/9283\/revisions\/17082"}],"wp:attachment":[{"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/media?parent=9283"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/categories?post=9283"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/tags?post=9283"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}