{"created":"2023-07-25T10:25:28.791659+00:00","id":3831,"links":{},"metadata":{"_buckets":{"deposit":"27c5d769-64f4-4bcc-a715-37041e9afb5c"},"_deposit":{"created_by":4,"id":"3831","owners":[4],"pid":{"revision_id":0,"type":"depid","value":"3831"},"status":"published"},"_oai":{"id":"oai:naist.repo.nii.ac.jp:00003831","sets":["34:35"]},"author_link":["6342","341","6343","6344"],"item_7_biblio_info_9":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2007-02","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2","bibliographicPageEnd":"561","bibliographicPageStart":"554","bibliographicVolumeNumber":"E90-D","bibliographic_titles":[{"bibliographic_title":"IEICE Transactions on Information and Systems","bibliographic_titleLang":"en"}]}]},"item_7_description_7":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"In real-time speech recognition applications, there is a need to implement a fast and reliable adaptation algorithm. We propose a method to reduce adaptation time of the rapid unsupervised speaker adaptation based on HMM-Sufficient Statistics. We use only a single arbitrary utterance without transcriptions in selecting the N-best speakers' Sufficient Statistics created offline to provide data for adaptation to a target speaker. Further reduction of N-best implies a reduction in adaptation time. However, it degrades recognition performance due to insufficiency of data needed to robustly adapt the model. Linear interpolation of the global HMM-Sufficient Statistics offsets this negative effect and achieves a 50% reduction in adaptation time without compromising the recognition performance. Furthermore, we compared our method with Vocal Tract Length Normalization (VTLN), Maximum A Posteriori (MAP) and Maximum Likelihood Linear Regression (MLLR). Moreover, we tested in office, car, crowd and booth noise environments in 10dB, 15dB, 20dB and 25dB SNRs.","subitem_description_language":"en","subitem_description_type":"Abstract"}]},"item_7_publisher_10":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"電子情報通信学会","subitem_publisher_language":"ja"}]},"item_7_relation_17":{"attribute_name":"DOI","attribute_value_mlt":[{"subitem_relation_type":"isIdenticalTo","subitem_relation_type_id":{"subitem_relation_type_id_text":"https://doi.org/10.1093/ietisy/e90-d.2.554","subitem_relation_type_select":"DOI"}}]},"item_7_rights_18":{"attribute_name":"権利","attribute_value_mlt":[{"subitem_rights":"Copyright (C) 2007 電子情報通信学会.","subitem_rights_language":"ja"}]},"item_7_source_id_12":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"0916-8532","subitem_source_identifier_type":"ISSN"}]},"item_7_source_id_14":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA10826272","subitem_source_identifier_type":"NCID"}]},"item_7_version_type_20":{"attribute_name":"著者版フラグ","attribute_value_mlt":[{"subitem_version_resource":"http://purl.org/coar/version/c_970fb48d4fbd8a85","subitem_version_type":"VoR"}]},"item_access_right":{"attribute_name":"アクセス権","attribute_value_mlt":[{"subitem_access_right":"open access","subitem_access_right_uri":"http://purl.org/coar/access_right/c_abf2"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Gomez, Randy","creatorNameLang":"en"}],"nameIdentifiers":[{"nameIdentifier":"6342","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"Toda, Tomoki","creatorNameLang":"en"}],"nameIdentifiers":[{"nameIdentifier":"341","nameIdentifierScheme":"WEKO"},{"nameIdentifier":"90403328","nameIdentifierScheme":"e-Rad","nameIdentifierURI":"https://kaken.nii.ac.jp/ja/search/?qm=90403328"}]},{"creatorNames":[{"creatorName":"Saruwatari, Hiroshi","creatorNameLang":"en"}],"nameIdentifiers":[{"nameIdentifier":"6343","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"Shikano, Kiyohiro","creatorNameLang":"en"}],"nameIdentifiers":[{"nameIdentifier":"6344","nameIdentifierScheme":"WEKO"}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2023-03-02"}],"displaytype":"detail","filename":"IEICETransInfoSys_E90D_2_554.pdf","filesize":[{"value":"6.0 MB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"fulltext","objectType":"fulltext","url":"https://naist.repo.nii.ac.jp/record/3831/files/IEICETransInfoSys_E90D_2_554.pdf"},"version_id":"3c7a97af-9d13-4811-bc70-2f731fe9a527"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"HMM-sufficient statistics","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"unsupervised","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"rapid adaptation","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"speech recognition","subitem_subject_language":"en","subitem_subject_scheme":"Other"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourcetype":"journal article","resourceuri":"http://purl.org/coar/resource_type/c_6501"}]},"item_title":"Reducing Computation Time of the Rapid Unsupervised Speaker Adaptation based on HMM-Sufficient Statistics","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Reducing Computation Time of the Rapid Unsupervised Speaker Adaptation based on HMM-Sufficient Statistics","subitem_title_language":"en"}]},"item_type_id":"7","owner":"4","path":["35"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2012-07-05"},"publish_date":"2012-07-05","publish_status":"0","recid":"3831","relation_version_is_last":true,"title":["Reducing Computation Time of the Rapid Unsupervised Speaker Adaptation based on HMM-Sufficient Statistics"],"weko_creator_id":"4","weko_shared_id":-1},"updated":"2023-11-17T01:59:17.828418+00:00"}