{"created":"2025-01-19T00:52:52.429374+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00185799","sets":["1164:5159:9402:9403"]},"path":["9403"],"owner":"11","recid":"185799","title":["Investigation of WaveNet for Text-to-Speech Synthesis"],"pubdate":{"attribute_name":"公開日","attribute_value":"2018-02-13"},"_buckets":{"deposit":"9bd34eb2-7bd2-498d-9089-dd8ece2e12bf"},"_deposit":{"id":"185799","pid":{"type":"depid","value":"185799","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"Investigation of WaveNet for Text-to-Speech Synthesis","author_link":["414271","414272","414274","414273","414269","414270"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Investigation of WaveNet for Text-to-Speech Synthesis"},{"subitem_title":"Investigation of WaveNet for Text-to-Speech Synthesis","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／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 / 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/185799/files/IPSJ-SLP18120006.pdf","label":"IPSJ-SLP18120006.pdf"},"date":[{"dateType":"Available","dateValue":"2020-02-13"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP18120006.pdf","filesize":[{"value":"1.2 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":"18f5954e-8070-4552-85ad-4bb711541c30","displaytype":"detail","licensetype":"license_note"}]},"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":"WaveNet is a type of neural network that can be used to model speech waveforms. It has been used in text-to-speech synthesis systems to convert acoustic or linguistic features into waveforms. Despite the description in recent literatures and open-source implementation, the mechanism of WaveNet is still somewhat obscure. This work explains the authors' WaveNet implementation. It also introduces a one-best generation method that could be an alternative to the random-sampling-based generation method. Based on the implementation, this work shows observations inside the network. Interesting findings include the manifold of quantized waveforms learned by WaveNet and the gradually decreased data variance in WaveNet blocks. These results may be helpful for further investigation on WaveNet.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"WaveNet is a type of neural network that can be used to model speech waveforms. It has been used in text-to-speech synthesis systems to convert acoustic or linguistic features into waveforms. Despite the description in recent literatures and open-source implementation, the mechanism of WaveNet is still somewhat obscure. This work explains the authors' WaveNet implementation. It also introduces a one-best generation method that could be an alternative to the random-sampling-based generation method. Based on the implementation, this work shows observations inside the network. Interesting findings include the manifold of quantized waveforms learned by WaveNet and the gradually decreased data variance in WaveNet blocks. These results may be helpful for further investigation on WaveNet.","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":"2018-02-13","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"6","bibliographicVolumeNumber":"2018-SLP-120"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"id":185799,"updated":"2025-01-20T02:49:42.209608+00:00","links":{}}