Search Results

Natural speech contains a wide variety of expressions, making it much more difficult to recognize than specified verbal commands. We have developed a method using a language model template to generate language models capable of recognizing manifold expressions. This template method is designed on the basis of the modification structure of keywords. The evaluation results for a language model generated with this method showed that it allowed 630,000 command patterns with a high recognition rate of 96%. The results also revealed that the processing speed and memory used for speech recognition with this language model were at a practical level.

It is obvious that the quality of telematics services depends in particular on the radio wave environment of the cellular phones used as the communication infrastructure. There is a need to develop the technological capabilities for enabling users to enjoy stable communication without being conscious of changes in the surrounding radio wave environment. As one solution to this problem, this paper proposes a partial download function that divides the desired content data into smaller quantities for transmission and also selects areas with a good radio wave environment for downloading data while suspending communication in places where reception is poor. The results of driving tests are presented to demonstrate the effectiveness of this partial download function.

This paper describes an Expert System which can diagnose Nissan's Electronic Concentrated engine Control System (ECCS). This system employs the production system as its AI technique. The knowledge of expert mechanics on cause and effect relations is expressed in “problem - cause” pairs. The development of this prototype system for engine troubleshooting has confirmed that it is possible to systematize and store the knowledge of experts in a computer. Now by, adding more sophisticated expert knowledge, this system can be made an effecvtive tool in providing quick and accurate diagnosis.