{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00215402","sets":["6504:10735:10810"]},"path":["10810"],"owner":"44499","recid":"215402","title":["Gesture-to-talkによるサイネージ端末用の音声区間検出の改善"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-03-04"},"_buckets":{"deposit":"5a0c9576-05a5-43c0-b83d-c4f15667a324"},"_deposit":{"id":"215402","pid":{"type":"depid","value":"215402","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Gesture-to-talkによるサイネージ端末用の音声区間検出の改善","author_link":["554592","554591","554593"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Gesture-to-talkによるサイネージ端末用の音声区間検出の改善"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"インタフェース","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2021-03-04","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"滋賀大"},{"subitem_text_value":"滋賀大"},{"subitem_text_value":"滋賀大"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/215402/files/IPSJ-Z83-4ZA-05.pdf","label":"IPSJ-Z83-4ZA-05.pdf"},"date":[{"dateType":"Available","dateValue":"2021-12-29"}],"format":"application/pdf","filename":"IPSJ-Z83-4ZA-05.pdf","filesize":[{"value":"359.9 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"0778aa71-017c-4d5b-95a1-12c78fbb30c4","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"藤岡, 和紘"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"小松, 美幸"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"市川, 治"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_22_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00349328","subitem_source_identifier_type":"NCID"}]},"item_22_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"大学に訪れる人を対象としているMMDAgentを用いたサイネージ端末を作成した。しかし何も音声区間検出が含まれていないサイネージ端末は、雑音に反応してしまいサイネージ端末がひとりでに話し始めてしまうという問題があった。そのため確実な音声入力を取得するために、push-to-talkや口唇画像で発話中かどうかの判別し音声区間を検出する手法が存在する。しかし今のマスクそして非接触の時代ではどちらも推奨されない。また非接触の発話区間検知としてAttention-wordを用いたものがあるが、その場合発話終了時点が分からないという問題があった。本報告では上記の問題点を解決する特定のポーズをトークスイッチとしたGesture-to-talk によるサイネージ端末用の音声区間検出の改善を示した。","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"146","bibliographic_titles":[{"bibliographic_title":"第83回全国大会講演論文集"}],"bibliographicPageStart":"145","bibliographicIssueDates":{"bibliographicIssueDate":"2021-03-04","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2021"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":215402,"updated":"2025-01-19T16:10:48.918341+00:00","links":{},"created":"2025-01-19T01:16:10.313574+00:00"}