Generating Segment-Level Foreign-Accented Synthetic Speech with Natural Speech Prosody

• Item type: SIG Technical Reports(1)
• 公開日: 2018-02-13
• タイトル: Generating Segment-Level Foreign-Accented Synthetic Speech with Natural Speech Prosody
• タイトル / 言語: en
• タイトル: Generating Segment-Level Foreign-Accented Synthetic Speech with Natural Speech Prosody
• 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
• 著者所属: Waseda University
• 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): Waseda University
• 著者所属(英): en
• 著者所属(英): National Institute of Informatics / The University of Edinburgh
• 著者名: Gustav, Eje Henter; Jaime, Lorenzo-Trueba; Xin, Wang; Mariko, Kondo; Junichi, Yamagishi
• 著者名(英): Gustav, Eje Henter; Jaime, Lorenzo-Trueba; Xin, Wang; Mariko, Kondo; Junichi, Yamagishi
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: We present a new application of deep-learning-based TTS, namely multilingual speech synthesis for generating controllable foreign accent. We train an acoustic model on non-accented multilingual speech recordings from the same speaker and interpolate quinphone linguistic features between languages to generate microscopic foreign accent. By copying pitch and durations from a pre-recorded utterance of the desired prompt, natural prosody is achieved. We call this paradigm “cyborg speech” as it combines human and machine speech parameters. Experiments on synthetic American-English-accented Japanese confirm the success of the approach.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: We present a new application of deep-learning-based TTS, namely multilingual speech synthesis for generating controllable foreign accent. We train an acoustic model on non-accented multilingual speech recordings from the same speaker and interpolate quinphone linguistic features between languages to generate microscopic foreign accent. By copying pitch and durations from a pre-recorded utterance of the desired prompt, natural prosody is achieved. We call this paradigm “cyborg speech” as it combines human and machine speech parameters. Experiments on synthetic American-English-accented Japanese confirm the success of the 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 2018-SLP-120, 号 8, p. 1-3, 発行日 2018-02-13
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8663
• 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