Speaker detection is a very important task in distributed meeting applications. This paper discusses a number of challenges we met while designing a speaker detector for the Microsoft RoundTable distributed meeting device, and proposes a boosting-based multimodal speaker detection (BMSD) algorithm. Instead of performing sound source localization (SSL) and multi-person detection (MPD) separately and subsequently fusing their individual results, the proposed algorithm uses boosting to select features from a combined pool of both audio and visual features simultaneously. The result is a very accurate speaker detector with extremely high efficiency. The algorithm reduces the error rate of SSL-only approach by 47%, and the SSL and MPD fusion approach by 27%.<\/p>\n","protected":false},"excerpt":{"rendered":"
Speaker detection is a very important task in distributed meeting applications. This paper discusses a number of challenges we met while designing a speaker detector for the Microsoft RoundTable distributed meeting device, and proposes a boosting-based multimodal speaker detection (BMSD) algorithm. Instead of performing sound source localization (SSL) and multi-person detection (MPD) separately and subsequently […]<\/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":[13562,13551],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[262903,246694,252856,246691,246688,249991,247777,263074,263071,254353,247753,249895],"msr-conference":[263077],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-812641","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-computer-vision","msr-research-area-graphics-and-multimedia","msr-locale-en_us","msr-field-of-study-acoustic-source-localization","msr-field-of-study-artificial-intelligence","msr-field-of-study-boosting-machine-learning","msr-field-of-study-computer-science","msr-field-of-study-computer-vision","msr-field-of-study-detector","msr-field-of-study-feature-extraction","msr-field-of-study-speaker-detection","msr-field-of-study-speaker-diarisation","msr-field-of-study-speaker-recognition","msr-field-of-study-speech-recognition","msr-field-of-study-word-error-rate"],"msr_publishername":"IEEE","msr_edition":"","msr_affiliation":"","msr_published_date":"2006-9-30","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":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"doi","viewUrl":"false","id":"false","title":"10.1109\/MMSP.2006.285274","label_id":"243106","label":0},{"type":"url","viewUrl":"false","id":"false","title":"http:\/\/ieeexplore.ieee.org\/xpls\/abs_all.jsp?arnumber=4694847","label_id":"243109","label":0},{"type":"url","viewUrl":"false","id":"false","title":"http:\/\/yadda.icm.edu.pl\/yadda\/element\/bwmeta1.element.ieee-000004064524","label_id":"243109","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/research.microsoft.com\/en-us\/um\/people\/yongrui\/ps\/mmsp06.pdf","label_id":"243109","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/boosting-based-multimodal-speaker-detection-distributed-meeting-videos\/","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[],"msr-author-ordering":[{"type":"user_nicename","value":"Cha Zhang","user_id":31379,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Cha Zhang"},{"type":"guest","value":"pei-yin","user_id":812644,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=pei-yin"},{"type":"guest","value":"yong-rui","user_id":812647,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=yong-rui"},{"type":"user_nicename","value":"Ross Cutler","user_id":40660,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Ross Cutler"},{"type":"guest","value":"p-viola","user_id":812650,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=p-viola"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/812641"}],"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\/812641\/revisions"}],"predecessor-version":[{"id":812653,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/812641\/revisions\/812653"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=812641"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=812641"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=812641"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=812641"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=812641"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=812641"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=812641"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=812641"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=812641"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=812641"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=812641"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=812641"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=812641"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=812641"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=812641"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}