Unpaired Image-to-Speech Synthesis with Multimodal Information Bottleneck.

Shuang Ma Daniel McDuff Yale Song Unpaired Image-to-Speech Synthesis with Multimodal Information Bottleneck. 2019 abs/1908.07094 CoRR http://arxiv.org/abs/1908.07094 db/journals/corr/corr1908.html#abs-1908-07094