METHOD AND DEVICE FOR RETRIEVING VOICE INFORMATION BY USING CONTENTS INFORMATION AND SPEAKER INFORMATION

摘要

PURPOSE: Voice information is retrieved according to voice contents and speaker discrimination by discriminating voice information matching a user inquiry by comparing the user inquiry with the contents index and speaker index of a voice source. CONSTITUTION: The user inquiry includes a text character string including one or more key words and given speaker discrimination. The restriction conditions of the inquiry are compared with an indexed voice or/and a video database to retrieve proper voice and video segments. A voice retrieval system (100) comprises an indexing system (500) which transcribes and indexes voice information and an voice retrieval system (600). The indexing system (500) processes a text outputted from a voice recognition system in the indexing stage to perform contents indexing and speaker indexing. In the retrieval stage, the contents and speaker voice retrieval system (600) matches an inquiry document according to the voice contents and speaker discrimination by using the contents indexes and speaker indexes in the indexing stage and returns a proper document to a user.