@techreport{oai:ipsj.ixsq.nii.ac.jp:00194518,
 author = {Xin, Wang and Shinji, Takaki and Junichi, Yamagishi and Xin, Wang and Shinji, Takaki and Junichi, Yamagishi},
 issue = {3},
 month = {Feb},
 note = {Recently we proposed the neural source-filter model (NSF) that converts a sequence of acoustic features into a speech waveform. Similar to other recent neural waveform models, the NSF is a non-autogressive model powered by dilated CNN; however, the NSF uses the sine waveform instead of the random noise as the excitation. Furthermore, without using the normalizing flow, the NSF simply optimizes the network parameters by minimizing a spectral amplitude distance. In this work, we further investigated the three issues: whether the network structure can be further simplified; whether the NSF can be applied to multi-speaker speech synthesis; whether the NSF can be directly applied to convert the linguistic features into the speech waveforms. Our experiments showed positive results on all the three points. Particularly, we found that the WaveNet-style gated activation can be safely removed, and the NSF performs quite well as a pure dilated-CONV-based network., Recently we proposed the neural source-filter model (NSF) that converts a sequence of acoustic features into a speech waveform. Similar to other recent neural waveform models, the NSF is a non-autogressive model powered by dilated CNN; however, the NSF uses the sine waveform instead of the random noise as the excitation. Furthermore, without using the normalizing flow, the NSF simply optimizes the network parameters by minimizing a spectral amplitude distance. In this work, we further investigated the three issues: whether the network structure can be further simplified; whether the NSF can be applied to multi-speaker speech synthesis; whether the NSF can be directly applied to convert the linguistic features into the speech waveforms. Our experiments showed positive results on all the three points. Particularly, we found that the WaveNet-style gated activation can be safely removed, and the NSF performs quite well as a pure dilated-CONV-based network.},
 title = {Investigating neural source-filter waveform model for statistical parametric speech synthesis},
 year = {2019}
}