Unpaired Image-to-Speech Synthesis with

Multimodal Information Bottleneck

Shuang Ma, Daniel McDuff, Yale Song

ICCV 2019

This website provides audio samples for our ICCV 2019 paper. We organized the results into four tabs (shown in top right), each corresponding to each figure we've included in either the main paper (Figure 5 and Figure 6) and the supplementary material (Figure 1 and Figure 2). Please visit each tab to listen to audio samples.