Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai. Real-Time Neural Text-to-Speech with Sequence-to-Sequence Acoustic Model and WaveGlow or Single Gaussian WaveRNN Vocoders. In Gernot Kubin, Zdravko Kacic, editors, Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019. pages 1308-1312, ISCA, 2019. [doi]
@inproceedings{OkamotoTSK19-1, title = {Real-Time Neural Text-to-Speech with Sequence-to-Sequence Acoustic Model and WaveGlow or Single Gaussian WaveRNN Vocoders}, author = {Takuma Okamoto and Tomoki Toda and Yoshinori Shiga and Hisashi Kawai}, year = {2019}, doi = {10.21437/Interspeech.2019-1288}, url = {https://doi.org/10.21437/Interspeech.2019-1288}, researchr = {https://researchr.org/publication/OkamotoTSK19-1}, cites = {0}, citedby = {0}, pages = {1308-1312}, booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019}, editor = {Gernot Kubin and Zdravko Kacic}, publisher = {ISCA}, }