{"id":480063,"date":"2018-04-16T16:55:25","date_gmt":"2018-04-16T23:55:25","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&p=480063"},"modified":"2018-10-16T22:27:40","modified_gmt":"2018-10-17T05:27:40","slug":"conference-paper-microsoft-2017-conversational-speech-recognition-system","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/conference-paper-microsoft-2017-conversational-speech-recognition-system\/","title":{"rendered":"The Microsoft 2017 Conversational Speech Recognition System"},"content":{"rendered":"

We describe the latest version of Microsoft’s conversational speech recognition system for the Switchboard and CallHome domains.\u00a0 The system adds a CNN-BLSTM acoustic model to the set of model architectures we combined previously, and includes character-based and dialog session aware LSTM language models in rescoring.\u00a0 For system combination we adopt a two-stage approach, whereby acoustic model posteriors are first combined at the senone\/frame level,followed by a word-level voting via confusion networks.\u00a0 We also added another language model rescoring step following the confusion network combination.\u00a0 The resulting system yields a 5.1% word error rate on the NIST 2000 Switchboard test set, and 9.8% on the CallHome subset.<\/p>\n","protected":false},"excerpt":{"rendered":"

We describe the latest version of Microsoft’s conversational speech recognition system for the Switchboard and CallHome domains.\u00a0 The system adds a CNN-BLSTM acoustic model to the set of model architectures we combined previously, and includes character-based and dialog session aware LSTM language models in rescoring.\u00a0 For system combination we adopt a two-stage approach, whereby acoustic […]<\/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":[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-480063","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-human-language-technologies","msr-locale-en_us"],"msr_publishername":"IEEE","msr_edition":"","msr_affiliation":"","msr_published_date":"2018-04-16","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"5934-5938","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":"480066","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"ms_swbd17_icassp18","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2018\/04\/ms_swbd17_icassp18.pdf","id":480066,"label_id":0}],"msr_related_uploader":"","msr_attachments":[],"msr-author-ordering":[{"type":"user_nicename","value":"Wayne Xiong","user_id":34811,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Wayne Xiong"},{"type":"user_nicename","value":"Lingfeng Wu","user_id":32687,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Lingfeng Wu"},{"type":"user_nicename","value":"Jasha Droppo","user_id":32211,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Jasha Droppo"},{"type":"user_nicename","value":"Xuedong Huang","user_id":34869,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Xuedong Huang"},{"type":"user_nicename","value":"Andreas Stolcke","user_id":31054,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Andreas Stolcke"}],"msr_impact_theme":[],"msr_research_lab":[199565],"msr_event":[],"msr_group":[664548],"msr_project":[350126],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/480063"}],"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":7,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/480063\/revisions"}],"predecessor-version":[{"id":480396,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/480063\/revisions\/480396"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=480063"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=480063"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=480063"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=480063"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=480063"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=480063"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=480063"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=480063"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=480063"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=480063"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=480063"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=480063"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=480063"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=480063"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=480063"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}