{"id":224399,"updated":"2025-01-19T13:10:01.125781+00:00","links":{},"created":"2025-01-19T01:23:59.433847+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00224399","sets":["1164:5159:11151:11203"]},"path":["11203"],"owner":"44499","recid":"224399","title":["MS-FC-HiFiGAN : 学習可能な軽量アップサンプリングを用いた高速ニューラル波形生成モデル"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-02-21"},"_buckets":{"deposit":"6b550509-c2c0-40a2-bb51-b11627d54ccc"},"_deposit":{"id":"224399","pid":{"type":"depid","value":"224399","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"MS-FC-HiFiGAN : 学習可能な軽量アップサンプリングを用いた高速ニューラル波形生成モデル","author_link":["591649","591648","591656","591655","591646","591652","591650","591647","591651","591657","591654","591653"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"MS-FC-HiFiGAN : 学習可能な軽量アップサンプリングを用いた高速ニューラル波形生成モデル"},{"subitem_title":"MS-FC-HiFiGAN : Fast Neural Waveform Generation Model With Learnable Lightweight Upsampling","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"SP1:音声合成","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2023-02-21","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"神戸大学／情報通信研究機構"},{"subitem_text_value":"情報通信研究機構"},{"subitem_text_value":"神戸大学"},{"subitem_text_value":"神戸大学"},{"subitem_text_value":"名古屋大学"},{"subitem_text_value":"情報通信研究機構"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"MS-FC-HiFiGAN : Fast Neural Waveform Generation Model With Learnable Lightweight Upsampling","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/224399/files/IPSJ-SLP23146002.pdf","label":"IPSJ-SLP23146002.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP23146002.pdf","filesize":[{"value":"1.5 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"22"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"820341a9-e158-4324-941d-b22fbc9daaed","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"山下, 陽生"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"岡本, 拓磨"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"高島, 遼一"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"滝口, 哲也"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"戸田, 智基"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"河井, 恒"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Haruki, Yamashita","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takuma, Okamoto","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Ryoichi, Takashima","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tetsuya, Takiguchi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tomoki, Toda","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hisashi, Kawai","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":"近年テキスト音声合成 (Text-to-Speech: TTS) では品質を保ったまま推論速度を向上することが求められており，そのためニューラルボコーダの高速化が研究されている．Multi-Stream (MS) iSTFT-HiFi-GAN は 1CPU でも音声波形を推論可能なボコーダである HiFi-GAN の高速モデルとして提案され，VITS を用いた TTS タスクにおいて若干の音質の劣化があったものの約 4 倍の高速化がなされた．そこで本稿では，MS-iSTFT-HiFiGAN の合成品質向上を目的として逆短時間フーリエ変換 (iSTFT) 部を学習可能な全結合層へと変更した MS-FC-HiFi-GAN を提案する．このモデルについて，分析合成タスクとテキスト音声合成タスクの 2 つのタスクにおいて推論速度，合成品質を既存のHiFi-GAN の高速モデルと比較を行った．実験の結果，分析合成タスクにおける提案モデルの推論速度は 1CPU において 0.15 の Real Time Factor となり，MS-iSTFT-HiFiGAN と同程度であることが確認された．また提案モデルの合成品質は，TTS タスクではMS-iSTFT-HiFiGAN に劣ったものの分析合成では上回る結果となった．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In recent years, in text-to-speech synthesis, it is required to improve the inference speed while keeping the quality. Multi-stream(MS) iSTFT-HiFiGAN was proposed as a high-speed model of HiFi-GAN, a vocoder capable of inferring waveforms on single CPU. In the TTS task using VITS, although there was some deterioration in sound quality, the speed was increased by about 4 times. In this paper, we propose a MS-FC-HiFi-GAN in which the inverse short-time Fourier transform (iSTFT) part is changed to trainable fully connected layer for the purpose of improving the synthesis quality of the MS-iSTFT-HiFiGAN. As for the inference speed, RTF was 0.15 on 1 CPU, which is the same as MS-iSTFT-HiFiGAN. Synthesis quality was inferior to that of MS-iSTFT-HiFiGAN in TTS task, but was superior to thatin analysis/synthesis task. ","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":"2023-02-21","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2","bibliographicVolumeNumber":"2023-SLP-146"}]},"relation_version_is_last":true,"weko_creator_id":"44499"}}