Shunsuke Goto, Kotaro Onishi, Yuki Saito, Kentaro Tachibana, Koichiro Mori. Face2Speech: Towards Multi-Speaker Text-to-Speech Synthesis Using an Embedding Vector Predicted from a Face Image. In Helen Meng, Bo Xu 0011, Thomas Fang Zheng, editors, Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020. pages 1321-1325, ISCA, 2020. [doi]
@inproceedings{GotoOSTM20,
title = {Face2Speech: Towards Multi-Speaker Text-to-Speech Synthesis Using an Embedding Vector Predicted from a Face Image},
author = {Shunsuke Goto and Kotaro Onishi and Yuki Saito and Kentaro Tachibana and Koichiro Mori},
year = {2020},
doi = {10.21437/Interspeech.2020-2136},
url = {https://doi.org/10.21437/Interspeech.2020-2136},
researchr = {https://researchr.org/publication/GotoOSTM20},
cites = {0},
citedby = {0},
pages = {1321-1325},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020},
editor = {Helen Meng and Bo Xu 0011 and Thomas Fang Zheng},
publisher = {ISCA},
}