{"id":164888,"date":"1998-01-01T00:00:00","date_gmt":"1998-01-01T00:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/msr-research-item\/nonlinear-discriminant-feature-extraction-for-robust-text-independent-speaker-recognition\/"},"modified":"2018-10-16T21:09:50","modified_gmt":"2018-10-17T04:09:50","slug":"nonlinear-discriminant-feature-extraction-for-robust-text-independent-speaker-recognition","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/nonlinear-discriminant-feature-extraction-for-robust-text-independent-speaker-recognition\/","title":{"rendered":"Nonlinear Discriminant Feature Extraction for Robust Text-Independent Speaker Recognition"},"content":{"rendered":"<div class=\"asset-content\">\n<p>We study a deep neural network (deep learning) nonlinear discriminant analysis (NLDA) technique that extracts a speaker discriminant feature set. Our approach is to train a multilayer perceptron (MLP) to maximize the separation between speakers by nonlinearly projecting a large set of acoustic features (e.g., several frames) to a lower-dimensional feature set. The extracted features are optimized to discriminate between speakers and to be robust to mismatched training and testing conditions. We train the MLP on a development set and apply it to the training and testing utterances. Our results show that by combining the NLDA-based system with a state of the art cepstrum-based system we improve the speaker verification performance on the 1997 NIST Speaker Recognition Evaluation set by 15% in average compared with our cepstrum only system.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>We study a deep neural network (deep learning) nonlinear discriminant analysis (NLDA) technique that extracts a speaker discriminant feature set. Our approach is to train a multilayer perceptron (MLP) to maximize the separation between speakers by nonlinearly projecting a large set of acoustic features (e.g., several frames) to a lower-dimensional feature set. The extracted features [&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":[13554],"msr-publication-type":[193716],"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-164888","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-human-computer-interaction","msr-locale-en_us"],"msr_publishername":"","msr_edition":"RLA2C","msr_affiliation":"","msr_published_date":"1998-01-01","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","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":"224629","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"konig_heck_DNN.pdf","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/1998\/01\/konig_heck_DNN.pdf","id":224629,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":224629,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/1998\/01\/konig_heck_DNN.pdf"}],"msr-author-ordering":[{"type":"text","value":"Yochai Konig","user_id":0,"rest_url":false},{"type":"user_nicename","value":"lheck","user_id":32659,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=lheck"},{"type":"text","value":"Mitch Weintraub","user_id":0,"rest_url":false},{"type":"text","value":"Kemal Sonmez","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[169832,169434,169715],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/164888"}],"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":2,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/164888\/revisions"}],"predecessor-version":[{"id":533418,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/164888\/revisions\/533418"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=164888"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=164888"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=164888"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=164888"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=164888"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=164888"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=164888"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=164888"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=164888"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=164888"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=164888"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=164888"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=164888"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=164888"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=164888"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}