Learning Physically Grounded Lexicons from Spoken Utterances

Abstract

Service robots must understand correspondence relationships between things in the real world and words in order to communicate with humans. For example, to understand the utterance, Bring me an the robot requires knowledge about the relationship between the word apple and visual features of the apple, such as color and shape. Robots perceive object features with physical sensors. However, developers of service robots cannot describe all knowledge in advance because such robots may be used in situations other than those the developers assumed. In particular, household robots have many opportunities to encounter unknown objects. Therefore, it is preferable that robots automatically learn physically grounded lexicons, which consist of phoneme sequences and meanings of words, through interactions with users.