This paper presents a multimodal learning system that can ground spoken names of objects
in their physical referents and learn to recognize those objects simultaneously from naturally
co-occurring multisensory input. There are two technical problems involved:(1) the
correspondence problem in symbol grounding–how to associate words (symbols) with their
perceptually grounded meanings from multiple cooccurrences between words and objects
in the physical environment.(2) object learning–how to recognize and categorize visual …

On the integration of grounding language and learning objects | CiNii Research … On the
integration of grounding language and learning objects …