METHOD AND APPARATUS FOR RETRIEVING DESIRED VIDEO AND AUDIO SCENE USING VOICE RECOGNITION

摘要

This video retrieval apparatus is comprised of a retrieval data generation section that extracts a characteristic pattern from a voice signal synchronous with a video signal contained in a video to be retrieved to generate an index for video retrieval, and a retrieval processing section that collates a key word input from a retriever with the index to retrieve a desired scene. <IMAGE>