{"id":241662,"updated":"2025-01-19T07:35:16.103042+00:00","links":{},"created":"2025-01-19T01:46:23.890215+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00241662","sets":["1164:5159:11541:11870"]},"path":["11870"],"owner":"44499","recid":"241662","title":["Simulating Native Speaker Shadowing for Non-Native Speech Assessment with Latent Speech Representation"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-12-05"},"_buckets":{"deposit":"fc6b250e-3b69-450b-b61c-bb2208580b76"},"_deposit":{"id":"241662","pid":{"type":"depid","value":"241662","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Simulating Native Speaker Shadowing for Non-Native Speech Assessment with Latent Speech Representation","author_link":["665701","665699","665700","665697","665698","665696"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Simulating Native Speaker Shadowing for Non-Native Speech Assessment with Latent Speech Representation"},{"subitem_title":"Simulating Native Speaker Shadowing for Non-Native Speech Assessment with Latent Speech Representation","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"話者認識・音声分析","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2024-12-05","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo"},{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo"},{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo","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/241662/files/IPSJ-SLP24154042.pdf","label":"IPSJ-SLP24154042.pdf"},"date":[{"dateType":"Available","dateValue":"2026-12-05"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP24154042.pdf","filesize":[{"value":"3.6 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":"22"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"acc72336-2db7-45ea-95ef-201345190900","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Haopeng, Geng"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Daisuke, Saito"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Nobuaki, Minematsu"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Haopeng, Geng","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Daisuke, Saito","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Nobuaki, Minematsu","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":"Evaluating non-native speakers' speech intelligibility is essential in computer-assisted language learning (CALL). Conventional methods, such as using word error rates (WER) from automatic speech recognition (ASR), often lack pedagogical validity due to differences from human speech recognition (HSR). A more effective approach involves native (L1) speakers shadowing non-native (L2) speech, where breakdowns in L1 shadowing indicate unintelligible segments in L2 speech. In this study, we propose a speech generation system that simulates L1 shadowing of L2 speech using seq2seq voice conversion (VC) with latent speech representations. Our experimental results demonstrate that this method effectively replicates the L1 shadowing process, offering a novel tool for evaluating L2 speech intelligibility.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Evaluating non-native speakers' speech intelligibility is essential in computer-assisted language learning (CALL). Conventional methods, such as using word error rates (WER) from automatic speech recognition (ASR), often lack pedagogical validity due to differences from human speech recognition (HSR). A more effective approach involves native (L1) speakers shadowing non-native (L2) speech, where breakdowns in L1 shadowing indicate unintelligible segments in L2 speech. In this study, we propose a speech generation system that simulates L1 shadowing of L2 speech using seq2seq voice conversion (VC) with latent speech representations. Our experimental results demonstrate that this method effectively replicates the L1 shadowing process, offering a novel tool for evaluating L2 speech intelligibility.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2024-12-05","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"42","bibliographicVolumeNumber":"2024-SLP-154"}]},"relation_version_is_last":true,"weko_creator_id":"44499"}}