Analyzing the impact of including listener perception annotations in RNN-based emotional speech synthesis

• Item type: SIG Technical Reports(1)
• 公開日: 2017-12-14
• タイトル: Analyzing the impact of including listener perception annotations in RNN-based emotional speech synthesis
• タイトル / 言語: en
• タイトル: Analyzing the impact of including listener perception annotations in RNN-based emotional speech synthesis
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: ポスターセッション
• 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
• 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
• 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; Gustav, Eje Henter; Shinji, Takaki; Junichi, Yamagishi
• 著者名(英): Jaime, Lorenzo-Trueba; Gustav, Eje Henter; Shinji, Takaki; Junichi, Yamagishi
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: This paper investigates simultaneous modeling of multiple emotions in DNN-based expressive speech synthesis, and how to represent the emotional labels, such as emotional class and strength, for this task. Our goal is to answer two questions: First, what is the best way to annotate speech data with multiple emotions? Second, how should the emotional information be represented as labels for supervised DNN training? We evaluate on a large-scale corpus of emotional speech from a professional actress, additionally annotated with perceived emotional labels from crowd-sourced listeners. By comparing DNN-based speech synthesizers that utilize different emotional representations, we assess the impact of these representations and design decisions on human emotion recognition rates.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: This paper investigates simultaneous modeling of multiple emotions in DNN-based expressive speech synthesis, and how to represent the emotional labels, such as emotional class and strength, for this task. Our goal is to answer two questions: First, what is the best way to annotate speech data with multiple emotions? Second, how should the emotional information be represented as labels for supervised DNN training? We evaluate on a large-scale corpus of emotional speech from a professional actress, additionally annotated with perceived emotional labels from crowd-sourced listeners. By comparing DNN-based speech synthesizers that utilize different emotional representations, we assess the impact of these representations and design decisions on human emotion recognition rates.
• 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 2017-SLP-119, 号 8, p. 1-2, 発行日 2017-12-14
• 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