@techreport{oai:ipsj.ixsq.nii.ac.jp:00185799,
 author = {Xin, Wang and Shinji, Takaki and Junichi, Yamagishi and Xin, Wang and Shinji, Takaki and Junichi, Yamagishi},
 issue = {6},
 month = {Feb},
 note = {WaveNet is a type of neural network that can be used to model speech waveforms. It has been used in text-to-speech synthesis systems to convert acoustic or linguistic features into waveforms. Despite the description in recent literatures and open-source implementation, the mechanism of WaveNet is still somewhat obscure. This work explains the authors' WaveNet implementation. It also introduces a one-best generation method that could be an alternative to the random-sampling-based generation method. Based on the implementation, this work shows observations inside the network. Interesting findings include the manifold of quantized waveforms learned by WaveNet and the gradually decreased data variance in WaveNet blocks. These results may be helpful for further investigation on WaveNet., WaveNet is a type of neural network that can be used to model speech waveforms. It has been used in text-to-speech synthesis systems to convert acoustic or linguistic features into waveforms. Despite the description in recent literatures and open-source implementation, the mechanism of WaveNet is still somewhat obscure. This work explains the authors' WaveNet implementation. It also introduces a one-best generation method that could be an alternative to the random-sampling-based generation method. Based on the implementation, this work shows observations inside the network. Interesting findings include the manifold of quantized waveforms learned by WaveNet and the gradually decreased data variance in WaveNet blocks. These results may be helpful for further investigation on WaveNet.},
 title = {Investigation of WaveNet for Text-to-Speech Synthesis},
 year = {2018}
}