{"created":"2023-05-15T14:21:31.286962+00:00","id":3202,"links":{},"metadata":{"_buckets":{"deposit":"4c7de4da-bb4d-4927-8450-1e5d57fba8b1"},"_deposit":{"created_by":3,"id":"3202","owners":[3],"pid":{"revision_id":0,"type":"depid","value":"3202"},"status":"published"},"_oai":{"id":"oai:bunkyo.repo.nii.ac.jp:00003202","sets":["1:26:204"]},"author_link":["4146","4145"],"item_5_alternative_title_1":{"attribute_name":"タイトル カナ","attribute_value_mlt":[{"subitem_alternative_title":"ユウセイ ハレツオン ノ ダイヒョウ パターン ノ ガクシュウ ケッテイ ト ソノ ケイサンキ シミュレーション"}]},"item_5_biblio_info_13":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"1998-01-01","bibliographicIssueDateType":"Issued"},"bibliographicPageEnd":"95","bibliographicPageStart":"77","bibliographicVolumeNumber":"20","bibliographic_titles":[{"bibliographic_title":"情報研究"},{"bibliographic_title":"Information and Communication Studies","bibliographic_titleLang":"en"}]}]},"item_5_date_43":{"attribute_name":"作成日","attribute_value_mlt":[{"subitem_date_issued_datetime":"2011-02-22","subitem_date_issued_type":"Created"}]},"item_5_description_12":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"　最小距離分類器、最大相関分類器、最近近傍分類器、不動点探索形構造受精多段階帰納推理の働きでパターン認識を行うシステムRECOGNITRONなどでは、典型としての代表パターンを中心とした緩やかなカテゴリを想定している。本研究では、9つの有声破裂音\n/ba/, /be/, /bo/, /da/, /de/, /do/, /ga/, /ge/, /go/を全カテゴリ集合とする場合を想定し、この場合の代表パターンの集合Ωが、Kohonenの学習ベクトル量子化法を多少簡単化して得られたアルゴリズムを用いて決定されている。このアルゴリズムで使われる減少関数α(t)が新しく提案されている。得られた結果は人の耳で聞く限り、大旨良好である。\n\\n　A minimum-distance classifier, a maximum-correlation classifier, a nearest neighbor classifier and RECOGNITRON (multi-stage inductive-inference recognition-system using structural fertilization transformations of fixed-point searching type) must postulate a gentle definition of each category having a prototypical pattern as a centroid.\n　We adopt nine voiced affricates (/ba/, /be/, /bo/, /da/, /de/, do/, /ga/, /ge/, /go/) as a whole set of categories, and prototypical patterns in this case were determined by a simplified algorithm of the learning vector quantization LVQ proposed by Kohonen. A new decreasing function α (t) needed in this algorithm was used here. Its simulation result which reproduced the obtained voices by means of a speaker of personal computer Macintosh IIcx was to some extent satisfactory as long as we listened to them.","subitem_description_type":"Abstract"}]},"item_5_publisher_16":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"文教大学"}]},"item_5_source_id_19":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"03893367","subitem_source_identifier_type":"ISSN"}]},"item_5_text_39":{"attribute_name":"本文言語","attribute_value_mlt":[{"subitem_text_value":"日本語"}]},"item_5_text_42":{"attribute_name":"ID","attribute_value_mlt":[{"subitem_text_value":"BKSJ200005"}]},"item_5_text_7":{"attribute_name":"Author","attribute_value_mlt":[{"subitem_text_value":"Suzuki, Shoichi"},{"subitem_text_value":"Maeda, Hideaki"}]},"item_5_text_8":{"attribute_name":"所属機関","attribute_value_mlt":[{"subitem_text_value":"文教大学情報学部"},{"subitem_text_value":"文教大学情報学部"}]},"item_5_version_type_35":{"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":"鈴木, 昇一"}],"nameIdentifiers":[{"nameIdentifier":"4145","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"前田, 英明"}],"nameIdentifiers":[{"nameIdentifier":"4146","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":"2018-03-24"}],"displaytype":"detail","filename":"BKSJ200005.pdf","filesize":[{"value":"1.2 MB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"BKSJ200005.pdf","url":"https://bunkyo.repo.nii.ac.jp/record/3202/files/BKSJ200005.pdf"},"version_id":"cb70b81b-8dc5-4015-afa2-c654cebd1202"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"有声破裂音","subitem_subject_scheme":"Other"},{"subitem_subject":"学習ベクトル量子化","subitem_subject_scheme":"Other"},{"subitem_subject":"代表パターン","subitem_subject_scheme":"Other"},{"subitem_subject":"知覚","subitem_subject_scheme":"Other"},{"subitem_subject":"パターンモデル","subitem_subject_scheme":"Other"},{"subitem_subject":"再帰領域方程式","subitem_subject_scheme":"Other"},{"subitem_subject":"不動点探索形認識","subitem_subject_scheme":"Other"},{"subitem_subject":"voiced affricates","subitem_subject_scheme":"Other"},{"subitem_subject":"learning vector quantization","subitem_subject_scheme":"Other"},{"subitem_subject":"prototypical pattern","subitem_subject_scheme":"Other"},{"subitem_subject":"perception","subitem_subject_scheme":"Other"},{"subitem_subject":"pattern-model","subitem_subject_scheme":"Other"},{"subitem_subject":"reflective domain equation","subitem_subject_scheme":"Other"},{"subitem_subject":"recognition of fixed-point searching type","subitem_subject_scheme":"Other"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourcetype":"departmental bulletin paper","resourceuri":"http://purl.org/coar/resource_type/c_6501"}]},"item_title":"有声破裂音の代表パターンの学習的決定と、その計算機シミュレーション","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"有声破裂音の代表パターンの学習的決定と、その計算機シミュレーション"},{"subitem_title":"A Learning Method for the Determination of Prototypical Patterns of Voiced Affricates and its Computer Simulation","subitem_title_language":"en"}]},"item_type_id":"5","owner":"3","path":["204"],"pubdate":{"attribute_name":"公開日","attribute_value":"2011-02-22"},"publish_date":"2011-02-22","publish_status":"0","recid":"3202","relation_version_is_last":true,"title":["有声破裂音の代表パターンの学習的決定と、その計算機シミュレーション"],"weko_creator_id":"3","weko_shared_id":-1},"updated":"2024-08-08T01:10:23.083446+00:00"}