{"created":"2025-01-19T01:18:01.774058+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00217539","sets":["1164:5159:10869:10891"]},"path":["10891"],"owner":"44499","recid":"217539","title":["The VoiceMOS Challenge 2022"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-03-16"},"_buckets":{"deposit":"04566580-c0df-419c-befb-ddd7701b7533"},"_deposit":{"id":"217539","pid":{"type":"depid","value":"217539","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"The VoiceMOS Challenge 2022","author_link":["563803","563806","563809","563808","563802","563805","563807","563810","563800","563799","563801","563804"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"The VoiceMOS Challenge 2022"},{"subitem_title":"The VoiceMOS Challenge 2022","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"音声・対話コンペティション","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-03-16","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Nagoya University"},{"subitem_text_value":"National Institute of Informatics"},{"subitem_text_value":"Acadamia Sinica"},{"subitem_text_value":"Acadamia Sinica"},{"subitem_text_value":"Nagoya University"},{"subitem_text_value":"National Institute of Informatics"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Informatics","subitem_text_language":"en"},{"subitem_text_value":"Acadamia Sinica","subitem_text_language":"en"},{"subitem_text_value":"Acadamia Sinica","subitem_text_language":"en"},{"subitem_text_value":"Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Informatics","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"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/217539/files/IPSJ-SLP22141001.pdf","label":"IPSJ-SLP22141001.pdf"},"date":[{"dateType":"Available","dateValue":"2024-03-16"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP22141001.pdf","filesize":[{"value":"158.8 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"5"},{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"22"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"0188d59e-a800-43ea-84ed-e64f48313111","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Wen-Chin, Huang"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Erica, Cooper"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yu, Tsao"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hsin-Min, Wang"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tomoki, Toda"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Junichi, Yamagishi"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Wen-Chin, Huang","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Erica, Cooper","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yu, Tsao","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hsin-Min, Wang","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tomoki, Toda","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Junichi, Yamagishi","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10442647","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":"2188-8663","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"We present the VoiceMOS Challenge, a scientific event that aims to encourage research in automatic prediction of Mean Opinion Scores (MOS) for synthesized speech. While human listening tests have been the gold standard for evaluating synthesized speech, the high cost motivates the development of automatic objective measures. However, recent popular data-driven neural network-based models often have a low correlation with human ratings, and the generalization abilities of current data-driven quality prediction systems suffer significantly from domain mismatch. The focus of the VoiceMOS challenge is on understanding and comparing current MOS prediction techniques using a standardized dataset. It has been accepted as a special session at INTERSPEECH 2022 and has attracted attention from research teams worldwide. This talk introduces details of the VoiceMOS challenge, including the datasets, task designs, baseline systems, and the analyses of results. We also discuss future directions for the next version of the challenge.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"We present the VoiceMOS Challenge, a scientific event that aims to encourage research in automatic prediction of Mean Opinion Scores (MOS) for synthesized speech. While human listening tests have been the gold standard for evaluating synthesized speech, the high cost motivates the development of automatic objective measures. However, recent popular data-driven neural network-based models often have a low correlation with human ratings, and the generalization abilities of current data-driven quality prediction systems suffer significantly from domain mismatch. The focus of the VoiceMOS challenge is on understanding and comparing current MOS prediction techniques using a standardized dataset. It has been accepted as a special session at INTERSPEECH 2022 and has attracted attention from research teams worldwide. This talk introduces details of the VoiceMOS challenge, including the datasets, task designs, baseline systems, and the analyses of results. We also discuss future directions for the next version of the challenge.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"1","bibliographic_titles":[{"bibliographic_title":"研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2022-03-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2022-SLP-141"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":217539,"updated":"2025-01-19T15:27:39.878352+00:00","links":{}}