{"links":{},"id":194518,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00194518","sets":["1164:5159:9712:9713"]},"path":["9713"],"owner":"44499","recid":"194518","title":["Investigating neural source-filter waveform model for statistical parametric speech synthesis"],"pubdate":{"attribute_name":"公開日","attribute_value":"2019-02-20"},"_buckets":{"deposit":"5a6f6876-e8e6-4e2b-8287-58e5236df90a"},"_deposit":{"id":"194518","pid":{"type":"depid","value":"194518","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Investigating neural source-filter waveform model for statistical parametric speech synthesis","author_link":["460569","460565","460567","460566","460564","460568"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Investigating neural source-filter waveform model for statistical parametric speech synthesis"},{"subitem_title":"Investigating neural source-filter waveform model for statistical parametric speech synthesis","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2019-02-20","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"}]},"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"}]},"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/194518/files/IPSJ-SLP19126003.pdf","label":"IPSJ-SLP19126003.pdf"},"date":[{"dateType":"Available","dateValue":"2021-02-20"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP19126003.pdf","filesize":[{"value":"2.6 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":"86f8f5a6-87b7-4708-9ec4-58ac88b3b8f5","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2019 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Xin, Wang"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shinji, Takaki"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Junichi, Yamagishi"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Xin, Wang","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shinji, Takaki","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":"Recently we proposed the neural source-filter model (NSF) that converts a sequence of acoustic features into a speech waveform. Similar to other recent neural waveform models, the NSF is a non-autogressive model powered by dilated CNN; however, the NSF uses the sine waveform instead of the random noise as the excitation. Furthermore, without using the normalizing flow, the NSF simply optimizes the network parameters by minimizing a spectral amplitude distance. In this work, we further investigated the three issues: whether the network structure can be further simplified; whether the NSF can be applied to multi-speaker speech synthesis; whether the NSF can be directly applied to convert the linguistic features into the speech waveforms. Our experiments showed positive results on all the three points. Particularly, we found that the WaveNet-style gated activation can be safely removed, and the NSF performs quite well as a pure dilated-CONV-based network.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Recently we proposed the neural source-filter model (NSF) that converts a sequence of acoustic features into a speech waveform. Similar to other recent neural waveform models, the NSF is a non-autogressive model powered by dilated CNN; however, the NSF uses the sine waveform instead of the random noise as the excitation. Furthermore, without using the normalizing flow, the NSF simply optimizes the network parameters by minimizing a spectral amplitude distance. In this work, we further investigated the three issues: whether the network structure can be further simplified; whether the NSF can be applied to multi-speaker speech synthesis; whether the NSF can be directly applied to convert the linguistic features into the speech waveforms. Our experiments showed positive results on all the three points. Particularly, we found that the WaveNet-style gated activation can be safely removed, and the NSF performs quite well as a pure dilated-CONV-based network.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"5","bibliographic_titles":[{"bibliographic_title":"研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2019-02-20","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"3","bibliographicVolumeNumber":"2019-SLP-126"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T00:59:33.997582+00:00","updated":"2025-01-19T23:27:18.280099+00:00"}