DCTTS is comparable to Tacotron, but is faster because it uses non-recurrent architectures for the encoder and decoder.
Hideyuki Tachibana, Katsuya Uenoyama, Shunsuke Aihara. “Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention” in Proc. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4784-4788.
in Proc. 9th ISCA Workshop on Speech Synthesis Workshop (SSW 9), 202–207 DOI: 10.1109/ICASSP.2018.8461829
Publisher’s version (preferred for Edinburgh University students)
CSTR’s Ophelia is one of several Open Source implementations of DCTTS
