{"created":"2023-05-15T12:36:03.838775+00:00","id":5233,"links":{},"metadata":{"_buckets":{"deposit":"f2d6b5e2-7032-4416-b343-031efea52c77"},"_deposit":{"created_by":3,"id":"5233","owners":[3],"pid":{"revision_id":0,"type":"depid","value":"5233"},"status":"published"},"_oai":{"id":"oai:nitech.repo.nii.ac.jp:00005233","sets":["31"]},"author_link":["8555","3028","464","17805","17808","8864"],"item_10001_biblio_info_28":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2005-03-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"3","bibliographicPageEnd":"417","bibliographicPageStart":"410","bibliographicVolumeNumber":"E88-D","bibliographic_titles":[{"bibliographic_title":"IEICE transactions on information and systems"}]}]},"item_10001_description_36":{"attribute_name":"内容記述","attribute_value_mlt":[{"subitem_description":"This paper describes continuous speech recognition incorporating the additional complement information, e.g., voice characteristics, speaking styles, linguistic information and noise environment, into HMM-based acoustic modeling. In speech recognition systems, context-dependent HMMs, i.e., triphone, and the tree-based context clustering have commonly been used. Several attempts to utilize not only phonetic contexts, but additional complement information based on context (factor) dependent HMMs have been made in recent years. However, when the additional factors for testing data are unobserved, methods for obtaining factor labels is required before decoding. In this paper, we propose a model integration technique based on general factor dependent HMMs for decoding. The integrated HMMs can be used by a conventional decoder as standard triphone HMMs with Gaussian mixture densities. Moreover, by using the results of context clustering, the proposed method can determine an optimal number of mixture components for each state dependently of the degree of influence from additional factors. Phoneme recognition experiments using voice characteristic labels show significant improvements with a small number of model parameters, and a 19.3% error reduction was obtained in noise environment experiments.","subitem_description_type":"Other"}]},"item_10001_description_38":{"attribute_name":"フォーマット","attribute_value_mlt":[{"subitem_description":"application/pdf","subitem_description_type":"Other"}]},"item_10001_full_name_27":{"attribute_name":"著者別名","attribute_value_mlt":[{"affiliations":[{"affiliationNames":[{"affiliationName":"","lang":"ja"}],"nameIdentifiers":[{"nameIdentifier":"","nameIdentifierScheme":"ISNI","nameIdentifierURI":"http://www.isni.org/isni/"}]}],"familyNames":[{},{},{}],"givenNames":[{},{},{}],"nameIdentifiers":[{},{}],"names":[{"name":"Nankaku, Yoshihiko","nameLang":"en"},{"name":"南角, 吉彦","nameLang":"ja"},{"name":"ナンカク, ヨシヒコ","nameLang":"ja-Kana"}]},{"affiliations":[{"affiliationNames":[{"affiliationName":"","lang":"ja"}],"nameIdentifiers":[{"nameIdentifier":"","nameIdentifierScheme":"ISNI","nameIdentifierURI":"http://www.isni.org/isni/"}]}],"familyNames":[{},{},{}],"givenNames":[{},{},{}],"nameIdentifiers":[{},{}],"names":[{"name":"Tokuda, Keiichi","nameLang":"en"},{"name":"徳田, 恵一","nameLang":"ja"},{"name":"トクダ, ケイイチ","nameLang":"ja-Kana"}]},{"nameIdentifiers":[{}],"names":[{"name":"北村, 正"}]}]},"item_10001_publisher_29":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"Institute of Electronics, Information and Communication Engineers"}]},"item_10001_source_id_30":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"09168532","subitem_source_identifier_type":"ISSN"}]},"item_10001_source_id_32":{"attribute_name":"書誌レコードID（NCID）","attribute_value_mlt":[{"subitem_source_identifier":"AA10826272","subitem_source_identifier_type":"NCID"}]},"item_10001_version_type_33":{"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_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Suzuki, Hiroyuki","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Zen, Heiga","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorAffiliations":[{"affiliationNameIdentifiers":[{"affiliationNameIdentifier":"","affiliationNameIdentifierScheme":"ISNI","affiliationNameIdentifierURI":"http://www.isni.org/isni/"}],"affiliationNames":[{"affiliationName":"","affiliationNameLang":"ja"}]}],"creatorNames":[{"creatorName":"Nankaku, Yoshihiko","creatorNameLang":"en"},{"creatorName":"南角, 吉彦","creatorNameLang":"ja"},{"creatorName":"ナンカク, ヨシヒコ","creatorNameLang":"ja-Kana"}],"familyNames":[{},{},{}],"givenNames":[{},{},{}],"nameIdentifiers":[{},{}]},{"creatorNames":[{"creatorName":"Miyajima, Chiyomi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorAffiliations":[{"affiliationNameIdentifiers":[{"affiliationNameIdentifier":"","affiliationNameIdentifierScheme":"ISNI","affiliationNameIdentifierURI":"http://www.isni.org/isni/"}],"affiliationNames":[{"affiliationName":"","affiliationNameLang":"ja"}]}],"creatorNames":[{"creatorName":"Tokuda, Keiichi","creatorNameLang":"en"},{"creatorName":"徳田, 恵一","creatorNameLang":"ja"},{"creatorName":"トクダ, ケイイチ","creatorNameLang":"ja-Kana"}],"familyNames":[{},{},{}],"givenNames":[{},{},{}],"nameIdentifiers":[{},{}]},{"creatorNames":[{"creatorName":"Kitamura, Tadashi","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2017-01-25"}],"displaytype":"detail","filename":"E88-D_410.pdf","filesize":[{"value":"496.9 kB"}],"format":"application/pdf","license_note":"Copyright(c)2005 IEICE　http://search.ieice.org/index.html","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"本文_fulltext","url":"https://nitech.repo.nii.ac.jp/record/5233/files/E88-D_410.pdf"},"version_id":"3300d995-7d0a-46eb-a6e2-8eeebf631bb6"}]},"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":"Continuous Speech Recognition Based on General Factor Dependent Acoustic Models","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Continuous Speech Recognition Based on General Factor Dependent Acoustic Models","subitem_title_language":"en"}]},"item_type_id":"10001","owner":"3","path":["31"],"pubdate":{"attribute_name":"公開日","attribute_value":"2012-11-07"},"publish_date":"2012-11-07","publish_status":"0","recid":"5233","relation_version_is_last":true,"title":["Continuous Speech Recognition Based on General Factor Dependent Acoustic Models"],"weko_creator_id":"3","weko_shared_id":3},"updated":"2023-07-10T05:30:57.267998+00:00"}