Next week, we will present our paper Learning Multimodal Semantic Components from Subsymbolic Perception Using NMF at the third joint ICDL-EpiRob conference in Osaka, Japan. In that article we demonstrate that it is possible to learn semantic concepts, each of which is both associated to a word in spoken utterances and a gesture, by only looking at correlations between subsymbolic representations of two modalities.
More details about the work can be found on that page.
Mangin O., Oudeyer P.Y., Learning semantic components from sub-symbolic multi-modal perception. to appear in the third Joint IEEE International Conference on Development and Learning an on Epigenetic Robotics (ICDL-EpiRob 2013), Osaka (Japan). [bibtex] [poster][code] [details]