{"updated":"2025-01-19T15:47:15.728313+00:00","links":{},"created":"2025-01-19T01:17:09.377835+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00216633","sets":["1164:5159:10869:10870"]},"path":["10870"],"owner":"44499","recid":"216633","title":["Speaking Rate Control by HiFi-GAN using Feature Interpolation"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-02-22"},"_buckets":{"deposit":"f43b2e21-4a56-4491-a0bc-daea9d4f50be"},"_deposit":{"id":"216633","pid":{"type":"depid","value":"216633","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Speaking Rate Control by HiFi-GAN using Feature Interpolation","author_link":["559418","559424","559422","559423","559419","559415","559416","559421","559420","559417"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Speaking Rate Control by HiFi-GAN using Feature Interpolation"},{"subitem_title":"Speaking Rate Control by HiFi-GAN using Feature Interpolation","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"ポスターセッション2","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-02-22","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"The University of Tokyo"},{"subitem_text_value":"The University of Tokyo"},{"subitem_text_value":"National Institute of Information and Communications Technology"},{"subitem_text_value":"National Institute of Information and Communications Technology"},{"subitem_text_value":"The University of Tokyo"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Information and Communications Technology","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Information and Communications Technology","subitem_text_language":"en"},{"subitem_text_value":"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/216633/files/IPSJ-SLP22140032.pdf","label":"IPSJ-SLP22140032.pdf"},"date":[{"dateType":"Available","dateValue":"2024-02-22"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP22140032.pdf","filesize":[{"value":"1.7 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":"5d05be61-6e2b-41e0-b745-8357785772ee","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":"Detai, Xin"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shinnosuke, Takamichi"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takuma, Okamoto"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hisashi, Kawai"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroshi, Saruwatari"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Detai, Xin","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shinnosuke, Takamichi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takuma, Okamoto","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hisashi, Kawai","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroshi, Saruwatari","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 investigate the possibility of controlling speaking rate by using the HiFi-GAN neural vocoder. Although traditional time-scale modification (TSM) algorithms have been widely applied in real-world applications, their performance and efficiency are relatively low. Recent work of neural vocoder has shown the possibility of synthesizing speech with high fidelity and efficiency. The proposed method inserts an interpolation layer into the HiFi-GAN to control the speaking rate. A signal resampling method and an image scaling method are implemented in the proposed method to warp the mel-spectrogram or hidden features of the neural vocoder. We also design a Japanese speech corpus to evaluate the proposed speaking rate control method. Experimental results of comprehensive objective and subjective evaluations demonstrate that the proposed method can control speaking rate with higher quality and efficiency than a baseline TSM algorithm. We open-source the corpus and give future directions of speaking rate control by a neural vocoder.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"We investigate the possibility of controlling speaking rate by using the HiFi-GAN neural vocoder. Although traditional time-scale modification (TSM) algorithms have been widely applied in real-world applications, their performance and efficiency are relatively low. Recent work of neural vocoder has shown the possibility of synthesizing speech with high fidelity and efficiency. The proposed method inserts an interpolation layer into the HiFi-GAN to control the speaking rate. A signal resampling method and an image scaling method are implemented in the proposed method to warp the mel-spectrogram or hidden features of the neural vocoder. We also design a Japanese speech corpus to evaluate the proposed speaking rate control method. Experimental results of comprehensive objective and subjective evaluations demonstrate that the proposed method can control speaking rate with higher quality and efficiency than a baseline TSM algorithm. We open-source the corpus and give future directions of speaking rate control by a neural vocoder.","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":"2022-02-22","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"32","bibliographicVolumeNumber":"2022-SLP-140"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":216633}