{"id":165468,"date":"2013-05-26T00:00:00","date_gmt":"2013-05-26T00:00:00","guid":{"rendered":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/msr-research-item\/tied-state-based-discriminative-training-of-context-expanded-region-dependent-feature-transforms-for-lvcsr\/"},"modified":"2018-10-16T22:04:55","modified_gmt":"2018-10-17T05:04:55","slug":"tied-state-based-discriminative-training-of-context-expanded-region-dependent-feature-transforms-for-lvcsr","status":"publish","type":"msr-research-item","link":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/publication\/tied-state-based-discriminative-training-of-context-expanded-region-dependent-feature-transforms-for-lvcsr\/","title":{"rendered":"Tied-State Based Discriminative Training of Context-Expanded Region-Dependent Feature Transforms for LVCSR"},"content":{"rendered":"<div class=\"asset-content\">\n<p>We present a new discriminative feature transform approach to large vocabulary continuous speech recognition (LVCSR) using Gaussian mixture density hidden Markov models (GMM-HMMs) for acoustic modeling. The feature transform is formulated with a set of context-expanded region-dependent linear transforms (RDLTs) utilizing both long-span features and contextual weight expansion. The RDLTs are estimated by lattice-free, tied-state based discriminative training using maximum mutual information (MMI) criterion, while the GMM-HMMs are trained by conventional lattice-based, boosted MMI training. Compared with two baseline systems, which use RDLTs with either long-span features or weight expansion only and are trained using the conventional lattice-based discriminative training for both RDLTs and HMMs, the proposed approach achieves a relative word error rate reduction of 10% and 6% respectively on Switchboard-1 conversational telephone speech transcription task.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>We present a new discriminative feature transform approach to large vocabulary continuous speech recognition (LVCSR) using Gaussian mixture density hidden Markov models (GMM-HMMs) for acoustic modeling. The feature transform is formulated with a set of context-expanded region-dependent linear transforms (RDLTs) utilizing both long-span features and contextual weight expansion. The RDLTs are estimated by lattice-free, tied-state [&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":[{"type":"user_nicename","value":"qianghuo"},{"type":"user_nicename","value":"zhijiey"}],"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"IEEE International Conference on Acoustics, Speech and Signal Processing, 2013, ICASSP 2013","msr_chapter":"","msr_edition":"IEEE International Conference on Acoustics, Speech and Signal Processing, 2013, ICASSP 2013","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"IEEE International Conference on Acoustics, Speech and Signal Processing, 2013, ICASSP 2013","msr_doi":"","msr_arxiv_id":"","msr_s2_paper_id":"","msr_mag_id":"","msr_pubmed_id":"","msr_other_authors":"","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":"2013-05-26","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":2013,"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":[],"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-165468","msr-research-item","type-msr-research-item","status-publish","hentry","msr-locale-en_us"],"msr_publishername":"","msr_edition":"IEEE International Conference on Acoustics, Speech and Signal Processing, 2013, ICASSP 2013","msr_affiliation":"","msr_published_date":"2013-05-26","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"IEEE International Conference on Acoustics, Speech and Signal Processing, 2013, ICASSP 2013","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":"218473","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"TiedStateRDLT-ICASSP2013-revised.pdf","viewUrl":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2013\/05\/TiedStateRDLT-ICASSP2013-revised.pdf","id":218473,"label_id":0},{"type":"file","title":"Poster_ICASSP2013_zhijiey.pdf","viewUrl":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2013\/05\/Poster_ICASSP2013_zhijiey.pdf","id":218470,"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":218473,"url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2013\/05\/TiedStateRDLT-ICASSP2013-revised.pdf"},{"id":218470,"url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2013\/05\/Poster_ICASSP2013_zhijiey.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"qianghuo","user_id":33297,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=qianghuo"},{"type":"user_nicename","value":"zhijiey","user_id":35122,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=zhijiey"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"inproceedings","related_content":[],"_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/165468","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":2,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/165468\/revisions"}],"predecessor-version":[{"id":541911,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/165468\/revisions\/541911"}],"wp:attachment":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=165468"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=165468"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=165468"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=165468"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=165468"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=165468"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=165468"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=165468"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=165468"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=165468"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=165468"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=165468"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=165468"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}