Catplayinginthesnow: Impact of Prior Segmentation on a Model of Visually Grounded Speech

We investigate the effect of introducing phone, syllable, or word boundaries on the performance of a Model of Visually Grounded Speech and compare the results with a model that does not use any boundary information and with a model that uses random boundaries. We introduce a simple way to introduce such information in an RNN-based model and investigate which type of boundary enables a better mapping between an image and its spoken description. We also explore where, that is, at which level of the network's architecture such information should be introduced. We show that using a segmentation that results in syllable-like or word-like segments and that respects word boundaries are the most efficient. Also, we show that a linguistically informed subsampling is more efficient than a random subsampling. Finally, we show that using a hierarchical segmentation, by first using a phone segmentation and recomposing words from the phone units yields better results than either using a phone or word segmentation in isolation.