We propose a concept search system called Kanshinji Antenna that searches for documents with semantic content similar to that of the input text. In this system, concept vectors are statistically generated as the semantic expressions of words, and the similarities between documents are judged based on these concept vectors. This makes it possible to provide search functions that cannot be implemented in ordinary keyword search systems. In this article we discuss the system configuration and useful functions of the Kanshinji Antenna and discuss its effectiveness based on the results of an accuracy evaluation and an online questionnaire.

This paper describes a system that automatically generates meeting minutes by extracting a topic hierarchy from a meeting’s speech. The topic hierarchy is a tree structure whose nodes comprise a topic summary. The topic structure extraction process converts speech recognition results into a word conceptual vector sequence and divides the sequence into the topic segments (topic segmentation). It classifies the topic segments hierarchically (segment clustering). Experimental results show that for the transcription of a meeting, the proposed algorithm is useful. Experiments on the transcription of a televised debate showed that the proposed topic segmentation algorithm is superior to the conventional method using local word frequency vectors. We also discuss experiments on the speech recognition results for the televised debate.

This paper describes an automatic content indexing system for news programs, with a special emphasis on its segmentation process. The process can successfully segment an entire news program into topic-centered news stories; the primary tool is a linguistic topic segmentation algorithm. Experiments show that the resulting speech-based segments are fairly accurate, and scene change points supplied by an external video processor can be of help in improving segmentation effectiveness.