著者

Xin Wang Shinji Takaki Junichi Yamagishi

雑誌

研究報告音声言語情報処理(SLP) (ISSN:21888663)

巻号頁・発行日

vol.2017-SLP-115, no.2, pp.1-6, 2017-02-10

---

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.

著者

Junichi Yamagishi Christophe Veaux Simon King Steve Renals

出版者

ACOUSTICAL SOCIETY OF JAPAN

雑誌

Acoustical Science and Technology (ISSN:13463969)

巻号頁・発行日

vol.33, no.1, pp.1-5, 2012-01-01 (Released:2012-01-01)

参考文献数

23

被引用文献数

25 55