Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model.
Yuxuan WangR. J. Skerry-RyanDaisy StantonYonghui WuRon J. WeissNavdeep JaitlyZongheng YangYing XiaoZhifeng ChenSamy BengioQuoc V. LeYannis AgiomyrgiannakisRob ClarkRif A. SaurousPublished in: CoRR (2017)