{"id":398984,"date":"2017-07-11T12:35:03","date_gmt":"2017-07-11T19:35:03","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=398984"},"modified":"2018-10-16T20:15:46","modified_gmt":"2018-10-17T03:15:46","slug":"effect-reference-set-selection-speaker-dependent-speech-recognition","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/effect-reference-set-selection-speaker-dependent-speech-recognition\/","title":{"rendered":"Effect of reference set selection on speaker dependent speech recognition"},"content":{"rendered":"<div class=\"container-fluid body-content\">\n<article class=\"author-page\" data-bind=\"page: {\n         id: 'detail',\n         sourceCache: true,\n         sourceOnShow: 'app\/pages\/detail.cshtml',\n         params: { id: '' }\n     }\"><\/p>\n<div class=\"id-wrapper\" data-bind=\"page: { id: '?', beforeShow: detailPage.beforeDetailPageShown, params: ['jump'] }\">\n<div class=\"pure-g container entity-detail profile-page\">\n<article class=\"container profile-page detail\">\n<section class=\"left-right-comp detail-top\">\n<div class=\"profile-card card paper\">\n<div class=\"pure-g\">\n<div class=\"pure-u-1 pure-u-md-7-8 profile-content\">\n<div>\n<section class=\"paper-abstract\" data-bind=\"with: data.abstract\">\n<p data-bind=\"text: $data\">Presented here for a speaker dependent system, is an algorithm which chooses a reference template for each word in the vocabulary from a set of N exemplars. The goal of the algorithm is to produce a reference set that minimizes the worst matching behavior and total error over the N sets of exemplars. The results of the experiments presented here show a reduction in the average error rate from 16.4% to 10.2% over a set of 4 male speakers and 4 female speakers.<\/p>\n<\/section>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/section>\n<\/article>\n<\/div>\n<\/div>\n<\/article>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Presented here for a speaker dependent system, is an algorithm which chooses a reference template for each word in the vocabulary from a set of N exemplars. The goal of the algorithm is to produce a reference set that minimizes the worst matching behavior and total error over the N sets of exemplars. The results [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13545],"msr-publication-type":[193715],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-398984","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-human-language-technologies","msr-locale-en_us"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"1981-01-05","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"Journal of the Acoustical Society of America","msr_volume":"69","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"http:\/\/asa.scitation.org\/doi\/10.1121\/1.386265","msr_doi":"10.1121\/1.386265","msr_publication_uploader":[{"type":"url","title":"http:\/\/asa.scitation.org\/doi\/10.1121\/1.386265","viewUrl":false,"id":false,"label_id":0},{"type":"doi","title":"10.1121\/1.386265","viewUrl":false,"id":false,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":0,"url":"http:\/\/asa.scitation.org\/doi\/10.1121\/1.386265"}],"msr-author-ordering":[{"type":"text","value":"Zongge Li","user_id":0,"rest_url":false},{"type":"user_nicename","value":"fil","user_id":31811,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=fil"},{"type":"text","value":"Raj Reedy","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"download":[],"msr_publication_type":"article","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/398984"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/398984\/revisions"}],"predecessor-version":[{"id":398987,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/398984\/revisions\/398987"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=398984"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=398984"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=398984"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=398984"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=398984"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=398984"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=398984"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=398984"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=398984"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=398984"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=398984"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=398984"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=398984"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=398984"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=398984"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}