@techreport{oai:ipsj.ixsq.nii.ac.jp:00177376,
 author = {Xin, Wang and Shinji, Takaki and Junichi, Yamagishi and Xin, Wang and Shinji, Takaki and Junichi, Yamagishi},
 issue = {2},
 month = {Feb},
 note = {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., 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.},
 title = {Investigation on an autoregressive recurrent mixture density network for parametric speech synthesis},
 year = {2017}
}