{"created":"2025-01-19T01:37:50.842375+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00236021","sets":["6504:11678:11689"]},"path":["11689"],"owner":"44499","recid":"236021","title":["声質変換を用いたデータ拡張に基づく咽喉マイク音声認識"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-03-01"},"_buckets":{"deposit":"e2340310-2d8a-475d-b9fd-7ab5e6169f6e"},"_deposit":{"id":"236021","pid":{"type":"depid","value":"236021","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"声質変換を用いたデータ拡張に基づく咽喉マイク音声認識","author_link":["645006","645007","645008"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"声質変換を用いたデータ拡張に基づく咽喉マイク音声認識"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"人工知能と認知科学","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2024-03-01","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":"静岡大"},{"subitem_text_value":"静岡大"},{"subitem_text_value":"愛知産大"}]},"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/236021/files/IPSJ-Z86-1R-02.pdf","label":"IPSJ-Z86-1R-02.pdf"},"date":[{"dateType":"Available","dateValue":"2024-07-03"}],"format":"application/pdf","filename":"IPSJ-Z86-1R-02.pdf","filesize":[{"value":"830.7 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"a61549c1-e2b3-4fa6-a250-da62be1c7aa3","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"塚越, 駿大"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"西田, 昌史"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"西村, 雅史"}],"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":"近年、雑音環境下における音声認識の需要が高まっている。咽喉マイクは外部雑音の影響を抑制するが、一般的な接話型マイクとは音響特性が異なるため既存の音声認識モデルでは認識精度が著しく低下する。また、咽喉マイク用の音声認識モデルを学習するだけの大規模な咽喉マイク音声のコーパスは存在しない。そこで本研究ではDNNに基づく声質変換技術を利用し、既存の大規模な音声コーパスを咽喉マイク音声に変換することを試みた。これを少量の咽喉マイク収録音声とともに事前学習された自己教師あり学習モデルのFine tuningに利用することで認識率の改善が得られたので報告する。","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"358","bibliographic_titles":[{"bibliographic_title":"第86回全国大会講演論文集"}],"bibliographicPageStart":"357","bibliographicIssueDates":{"bibliographicIssueDate":"2024-03-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2024"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":236021,"updated":"2025-01-19T09:25:34.390159+00:00","links":{}}