{"id":185801,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00185801","sets":["1164:5159:9402:9403"]},"path":["9403"],"owner":"11","recid":"185801","title":["Generating Segment-Level Foreign-Accented Synthetic Speech with Natural Speech Prosody"],"pubdate":{"attribute_name":"公開日","attribute_value":"2018-02-13"},"_buckets":{"deposit":"2a46339e-ec54-45fe-a0e4-9e18c8075801"},"_deposit":{"id":"185801","pid":{"type":"depid","value":"185801","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"Generating Segment-Level Foreign-Accented Synthetic Speech with Natural Speech Prosody","author_link":["414281","414286","414284","414288","414283","414289","414282","414287","414290","414285"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Generating Segment-Level Foreign-Accented Synthetic Speech with Natural Speech Prosody"},{"subitem_title":"Generating Segment-Level Foreign-Accented Synthetic Speech with Natural Speech Prosody","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2018-02-13","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"National Institute of Informatics"},{"subitem_text_value":"National Institute of Informatics"},{"subitem_text_value":"National Institute of Informatics"},{"subitem_text_value":"Waseda University"},{"subitem_text_value":"National Institute of Informatics／The University of Edinburgh"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"National Institute of Informatics","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Informatics","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Informatics","subitem_text_language":"en"},{"subitem_text_value":"Waseda University","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Informatics / The University of Edinburgh","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/185801/files/IPSJ-SLP18120008.pdf","label":"IPSJ-SLP18120008.pdf"},"date":[{"dateType":"Available","dateValue":"2020-02-13"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP18120008.pdf","filesize":[{"value":"639.7 kB"}],"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":"ac095b9f-1dc5-4a69-8b53-0ee99e318ff8","displaytype":"detail","licensetype":"license_note"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Gustav, Eje Henter"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Jaime, Lorenzo-Trueba"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Xin, Wang"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Mariko, Kondo"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Junichi, Yamagishi"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Gustav, Eje Henter","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Jaime, Lorenzo-Trueba","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Xin, Wang","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Mariko, Kondo","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 a new application of deep-learning-based TTS, namely multilingual speech synthesis for generating controllable foreign accent. We train an acoustic model on non-accented multilingual speech recordings from the same speaker and interpolate quinphone linguistic features between languages to generate microscopic foreign accent. By copying pitch and durations from a pre-recorded utterance of the desired prompt, natural prosody is achieved. We call this paradigm “cyborg speech” as it combines human and machine speech parameters. Experiments on synthetic American-English-accented Japanese confirm the success of the approach.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"We present a new application of deep-learning-based TTS, namely multilingual speech synthesis for generating controllable foreign accent. We train an acoustic model on non-accented multilingual speech recordings from the same speaker and interpolate quinphone linguistic features between languages to generate microscopic foreign accent. By copying pitch and durations from a pre-recorded utterance of the desired prompt, natural prosody is achieved. We call this paradigm “cyborg speech” as it combines human and machine speech parameters. Experiments on synthetic American-English-accented Japanese confirm the success of the approach.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"3","bibliographic_titles":[{"bibliographic_title":"研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2018-02-13","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"8","bibliographicVolumeNumber":"2018-SLP-120"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"updated":"2025-01-20T02:49:45.861149+00:00","created":"2025-01-19T00:52:52.539517+00:00","links":{}}