Stealing your vocal identity from the internet: cloning Obama's voice from found data using GAN and Wavenet

• Item type: SIG Technical Reports(1)
• 公開日: 2018-02-13
• タイトル: Stealing your vocal identity from the internet: cloning Obama's voice from found data using GAN and Wavenet
• タイトル / 言語: en
• タイトル: Stealing your vocal identity from the internet: cloning Obama's voice from found data using GAN and Wavenet
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: National Institute of Informatics
• 著者所属: National Institute of Informatics
• 著者所属: National Institute of Informatics／The University of Edinburgh
• 著者所属(英): en
• 著者所属(英): National Institute of Informatics
• 著者所属(英): en
• 著者所属(英): National Institute of Informatics
• 著者所属(英): en
• 著者所属(英): National Institute of Informatics / The University of Edinburgh
• 著者名: Jaime, Lorenzo-Trueba; Xin, Wang; Junichi, Yamagishi
• 著者名(英): Jaime, Lorenzo-Trueba; Xin, Wang; Junichi, Yamagishi
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: With the rise of machine-learning speech processing techniques, the risk of having your vocal identity stolen from online audio clips has risen considerably. In this research we study how GAN-based technologies can allow us to significantly improve the vocal quality of found audios that suffer from noise or reverberation, and the consequences that processing has from the speech generation point of view when using state-of-the-art Wavenet-based voice generation techniques.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: With the rise of machine-learning speech processing techniques, the risk of having your vocal identity stolen from online audio clips has risen considerably. In this research we study how GAN-based technologies can allow us to significantly improve the vocal quality of found audios that suffer from noise or reverberation, and the consequences that processing has from the speech generation point of view when using state-of-the-art Wavenet-based voice generation techniques.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN10438388
• 書誌情報: 研究報告音楽情報科学（MUS）; 巻 2018-MUS-118, 号 7, p. 1-5, 発行日 2018-02-13
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8752
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会