{"updated":"2025-01-19T16:39:55.483523+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00214323","sets":["1164:2836:10501:10733"]},"path":["10733"],"owner":"44499","recid":"214323","title":["AutoVCを用いたゼロショットリアルタイム声質変換手法の提案"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-12-13"},"_buckets":{"deposit":"e6b9835c-dbc1-4b39-a9e2-3c093fc7bf79"},"_deposit":{"id":"214323","pid":{"type":"depid","value":"214323","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"AutoVCを用いたゼロショットリアルタイム声質変換手法の提案","author_link":["549936","549937","549935"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"AutoVCを用いたゼロショットリアルタイム声質変換手法の提案"},{"subitem_title":"A Study of Zero-Shot Real-Time Voice Conversion Method Using AutoVC","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"農業・音声・ゲーム","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2021-12-13","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"現在，金沢工業大学"},{"subitem_text_value":"現在，金沢工業大学"},{"subitem_text_value":"現在，金沢工業大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Presently with Kanazawa Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Presently with Kanazawa Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Presently with Kanazawa Institute of Technology","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/214323/files/IPSJ-DPS21189005.pdf","label":"IPSJ-DPS21189005.pdf"},"date":[{"dateType":"Available","dateValue":"2023-12-13"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DPS21189005.pdf","filesize":[{"value":"2.1 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"34"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"acdd9791-21a8-4f64-958f-c24c018edcfd","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"鈴木, 大志"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"鷹合, 大輔"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中沢, 実"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10116224","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8906","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"声質変換とは，人物の声の声質のみを別人の声質に変換する技術である．その中でも，ゼロショット声質変換は，変換モデルの学習した音声にない声質間での変換が可能な手法である．AutoVC は，ゼロショット声質変換モデルで，入力話者の声のメルスペクトログラムと入出力話者の話者埋め込みベクトルを入力する事で，話者らの声を学習しているか否か関わらず，出力話者の声質のメルスペクトログラムを出力する．これを，音声波形に復元する際に，音既存手法では WaveNet や Griffin-Lim などの多くの計算時間を要する手法を用いておりリアルタイムな声質変換の弊害となっている．そこで，本研究ではメルスペクトログラムに代えて，スペクトル包絡を用いた．そして，波形の復元は WORLD を用いる事でリアルタイムな声質変換を実現した．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告マルチメディア通信と分散処理（DPS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2021-12-13","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"5","bibliographicVolumeNumber":"2021-DPS-189"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T01:15:08.728659+00:00","id":214323,"links":{}}