A comparative study on modeling and controlling emotional acoustic parameters in neural networks based Japanese and Spanish speech synthesis

• Item type: SIG Technical Reports(1)
• 公開日: 2016-12-13
• タイトル: A comparative study on modeling and controlling emotional acoustic parameters in neural networks based Japanese and Spanish speech synthesis
• タイトル / 言語: en
• タイトル: A comparative study on modeling and controlling emotional acoustic parameters in neural networks based Japanese and Spanish speech synthesis
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: 音声合成
• 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; Shinji, Takaki; Junichi, Yamagishi
• 著者名(英): Jaime, Lorenzo-Trueba; Shinji, Takaki; Junichi, Yamagishi
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: In neural network based speech synthesis, adding a one-hot vector to the input is an easy, intuitive but useful way to model multiple speakers or multiple language. In this paper, we use the one-hot vector for modeling and controlling emotional acoustic parameters. We have used Spanish and Japanese databases having the multiple acted emotional speech uttered by professional speakers in our experiment and will show the performance of the one-hot vector approach.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: In neural network based speech synthesis, adding a one-hot vector to the input is an easy, intuitive but useful way to model multiple speakers or multiple language. In this paper, we use the one-hot vector for modeling and controlling emotional acoustic parameters. We have used Spanish and Japanese databases having the multiple acted emotional speech uttered by professional speakers in our experiment and will show the performance of the one-hot vector approach.
• 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: AN10442647
• 書誌情報: 研究報告音声言語情報処理（SLP）; 巻 2016-SLP-114, 号 22, p. 1-6, 発行日 2016-12-13
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8663
• 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