{"id":167583,"date":"2014-12-01T00:00:00","date_gmt":"2014-12-01T00:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/msr-research-item\/artificial-neural-network-features-for-speaker-diarization\/"},"modified":"2018-10-16T22:00:23","modified_gmt":"2018-10-17T05:00:23","slug":"artificial-neural-network-features-for-speaker-diarization","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/artificial-neural-network-features-for-speaker-diarization\/","title":{"rendered":"Artificial Neural Network Features for Speaker Diarization"},"content":{"rendered":"<div class=\"asset-content\">\n<p>Speaker diarization finds contiguous speaker segments in an audio recording and clusters them by speaker identity, without any a-priori knowledge. Diarization is typically based on short-term spectral features such as Mel-frequency cepstral coefficients (MFCCs). Though these features carry average information about the vocal tract characteristics of a speaker, they are also susceptible to factors unrelated to the speaker identity. In this study, we propose an artificial neural netw ork (ANN) architecture to learn a feature transform that is optimized for speaker diarization. We train a multi-hidden-layer ANN to judge whether two given speech segments came from the same or different speakers, using a shared transform of the input features that feeds into a bottleneck layer. We then use the bottleneck layer activations as features, either alone or in combination with baseline MFCC features in a multistream mode, for speaker diarization on test data. The resulting system is evaluated on various corpora of multi-party meetings. A combination of MFCC and ANN features gives up to 14% relative reduction in diarization error, demonstrating that these features are providing an additional independent source of knowledge.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Speaker diarization finds contiguous speaker segments in an audio recording and clusters them by speaker identity, without any a-priori knowledge. Diarization is typically based on short-term spectral features such as Mel-frequency cepstral coefficients (MFCCs). Though these features carry average information about the vocal tract characteristics of a speaker, they are also susceptible to factors unrelated [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":null,"msr_publishername":"IEEE - Institute of Electrical and Electronics Engineers","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"Proc. IEEE Spoken Language Technology Workshop","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"402-406","msr_page_range_start":"402","msr_page_range_end":"406","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"Proc. IEEE Spoken Language Technology Workshop","msr_doi":"","msr_arxiv_id":"","msr_s2_paper_id":"","msr_mag_id":"","msr_pubmed_id":"","msr_other_authors":"Sree Harsha Yella","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_original_fields_of_study":"","msr_release_tracker_id":"","msr_s2_match_type":"","msr_citation_count_updated":"","msr_published_date":"2014-12-01","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_s2_pdf_url":"","msr_year":2014,"msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_match_confidence":0,"msr_microsoftintellectualproperty":true,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13545],"msr-publication-type":[193716],"msr-publisher":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-167583","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-human-language-technologies","msr-locale-en_us"],"msr_publishername":"IEEE - Institute of Electrical and Electronics Engineers","msr_edition":"Proc. IEEE Spoken Language Technology Workshop","msr_affiliation":"","msr_published_date":"2014-12-01","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"402-406","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":"204563","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"ann-diar.pdf","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/ann-diar.pdf","id":204563,"label_id":0}],"msr_related_uploader":"","msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[{"id":204563,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/ann-diar.pdf"}],"msr-author-ordering":[{"type":"text","value":"Sree Harsha Yella","user_id":0,"rest_url":false},{"type":"user_nicename","value":"anstolck","user_id":31054,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=anstolck"},{"type":"user_nicename","value":"mslaney","user_id":33020,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=mslaney"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[171185],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":171185,"post_title":"Meeting Recognition and Understanding","post_name":"meeting-recognition-and-understanding","post_type":"msr-project","post_date":"2013-07-30 14:28:35","post_modified":"2023-08-12 21:11:41","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/meeting-recognition-and-understanding\/","post_excerpt":"In most organizations, staff spend many hours in meetings. This project addresses all levels of analysis and understanding, from speaker tracking and robust speech transcription to meaning extraction and summarization, with the goal of increasing productivity both during the meeting and after, for both participants and nonparticipants. The Meeting Recognition and Understanding project is a collection of online and offline spoken language understanding tasks. The following functions could be performed both on- and offline, but&hellip;","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/171185"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/167583","targetHints":{"allow":["GET"]}}],"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\/167583\/revisions"}],"predecessor-version":[{"id":541131,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/167583\/revisions\/541131"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=167583"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=167583"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=167583"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=167583"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=167583"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=167583"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=167583"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=167583"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=167583"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=167583"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=167583"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=167583"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=167583"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}