An Automatic Creation Method of the Query Vector for the Semantic Associative Search Corresponding to the Impression of Sound of Arbitrary Words

In this paper, we propose a new method of retrieval of media data by user´s impression which is extracted from the sound of the context words. Generally, a word and a phrase evoke various impressions. The impressions are evoked by not only its semantics but also its sound. Because of this, the sounds of words are important to understand mutual emotion effectively in our communication. In order to realize search functions based on the impressions of sounds of words, we have already realized the method of automatic metadata extraction corresponding to the impression by sound of the words. In this paper, we realize the semantic associative search for retrieving image data by applying the method to user´s query.