Investigation on an autoregressive recurrent mixture density network for parametric speech synthesis

• Item type: SIG Technical Reports(1)
• 公開日: 2017-02-10
• タイトル: Investigation on an autoregressive recurrent mixture density network for parametric speech synthesis
• タイトル / 言語: en
• タイトル: Investigation on an autoregressive recurrent mixture density network for parametric 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・応用
• 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(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
• 著者名: Xin, Wang; Shinji, Takaki; Junichi, Yamagishi
• 著者名(英): Xin, Wang; Shinji, Takaki; Junichi, Yamagishi
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Neural-network-based mixture density networks are important tools for acoustic modeling in statistical parametric speech synthesis. Recently we found that incorporating an autoregressive model in a recurrent mixture density network, which is referred to as AR-RMDN, enabled the network to generate quite smooth acoustic data trajectories without using the delta and delta-delta coefficients. More interestingly, the new model generated trajectories with a dynamic range similar to that of the natural data, thus alleviating over-smoothing effect. In this work, after explaining the AR-RMDN from the perspective of signal and filter, we compare one AR-RMDN with a modulation-spectrum-based post-filtering method that also eases the over-smoothing effect. It is demonstrated that the AR-RMDN also alters the modulation spectrum of the generated data trajectories but in a different way from the post-filtering method. The AR-RMDN also generates synthetic speech with better perceived quality. Based on the signal and filter interpretation, we further extend the AR-RMDN so that the inverse AR filter can acquire complex poles and stay stable.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Neural-network-based mixture density networks are important tools for acoustic modeling in statistical parametric speech synthesis. Recently we found that incorporating an autoregressive model in a recurrent mixture density network, which is referred to as AR-RMDN, enabled the network to generate quite smooth acoustic data trajectories without using the delta and delta-delta coefficients. More interestingly, the new model generated trajectories with a dynamic range similar to that of the natural data, thus alleviating over-smoothing effect. In this work, after explaining the AR-RMDN from the perspective of signal and filter, we compare one AR-RMDN with a modulation-spectrum-based post-filtering method that also eases the over-smoothing effect. It is demonstrated that the AR-RMDN also alters the modulation spectrum of the generated data trajectories but in a different way from the post-filtering method. The AR-RMDN also generates synthetic speech with better perceived quality. Based on the signal and filter interpretation, we further extend the AR-RMDN so that the inverse AR filter can acquire complex poles and stay stable.
• 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-115, 号 2, p. 1-6, 発行日 2017-02-10
• 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