Hiroki Kondo’s research while affiliated with Saga University and other places

We have designed and implemented a PC operation support system for a physically disabled person with a speech impediment via voice. Voice operation is an effective method for a physically disabled person with involuntary movement of the limbs and the head. We have applied a commercial speech recognition engine to develop our system for practical purposes. Adoption of a commercial engine reduces development cost and will contribute to make our system useful to another speech impediment people. We have customized commercial speech recognition engine so that it can recognize the utterance of a person with a speech impediment. We have restricted the words that the recognition engine recognizes and separated a target words from similar words in pronunciation to avoid misrecognition. Huge number of words registered in commercial speech recognition engines cause frequent misrecognition for speech impediments' utterance, because their utterance is not clear and unstable. We have solved this problem by narrowing the choice of input down in a small number and also by registering their ambiguous pronunciations in addition to the original ones. To realize all character inputs and all PC operation with a small number of words, we have designed multiple input modes with categorized dictionaries and have introduced two-step input in each mode except numeral input to enable correct operation with small number of words. The system we have developed is in practical level. The first author of this paper is physically disabled with a speech impediment. He has been able not only character input into PC but also to operate Windows system smoothly by using this system. He uses this system in his daily life. This paper is written by him with this system. At present, the speech recognition is customized to him. It is, however, possible to customize for other users by changing words and registering new pronunciation according to each user's utterance.

This paper describes design and implementation of multiplication table learning support system with spoken dialogue. Our system provides multi-modal interface for learning. It has speech synthesis engine for speaking to a child (learner) and speech recognition engine to recognize learner's voice responses. Multiple sensitive organs are used in learning, looking at the display (by eyes), listening the voice of the system and their own (by ears) and speaking (by mouth). Our system is designed in investigating learning activities in an elementary school and implemented in accordance with the progress (phase of comprehension) of each study. We define the following three modes according to learning phases. They are a memorize mode, a practice mode and a test mode. To achieve quick recognition and high recognition rate, we constrain vocabulary and syntax the system accepts, and we also extend vocabulary to recognize multiplication table specific numeration.

Recently, the ubiquitous network attracts a great deal of attention. The ubiquitous network is an environment from which all information instruments and computers are connected with the network anytime and anywhere. IPv6 (next generation Internet protocol) is core technique for achieving the ubiquitous network. The IPv6 network also brings an integrated environment to ubiquitous instruments, that is, all media information, not only control signal but also multimedia information can be sent thought the network. IPv6 network is expected to be a powerful tool for a remote control system. However, it is not evident how to implement actually the integrated environment to a remote control system. And also it is not clear how the characteristic of the Internet which is based on packet transfer system, affects the control. To examine these issues, we developed a system with which one can operate a remote barreling process machine using IPv6. This paper describes details of the function and an implementation of the system. We also describe the consideration of the evaluation experiment of this system.

Interfaces for handwritten inputs are expected to be useful as means by which a student can use natural handwritten inputs in an intelligent tutoring system. Intelligent tutoring systems operating on the WWW have been developed with the input interfaces of the mouse and keyboard. The authors have developed HandChaRM-WWW, which is a module performing handwritten character recognition on the WWW. The module is written in Java and installed on a WWW client such that no communication delay occurs during character recognition. The characters recognized are limited to numbers, operators, the equal sign, and the like, and handwritten character recognition is realized by extracting characters with high speed and high accuracy. WWW FRONTIER has been developed by implementing HandChaRM-WWW on an intelligent CAI system which guides fractional calculations. WWW FRONTIER is a drill-type intelligent tutoring system which responds to a student by giving a fractional adding or subtracting problem. A student can input a fractional equation on the WWW in handwritten form. A handwritten character recognition rate of 93% has been obtained in evaluation experiments, which constitutes a practical level. The architecture of HandChaRM-WWW is considered to be effective in intelligent tutoring systems for other domains which have characters as targets of recognition. © 2002 Scripta Technica, Syst Comp Jpn, 33(2): 12–21, 2002

This paper describes our on-line handwriting mathematical expression input interface for our Intelligent Algebraic Calculation Tutoring System (ACTS). It consists of a Java-based client, which receives user's handwriting input and displays output, and a C-based server, which recognizes hand-written symbols. Our interface provides simple and easy mathematical expression input environment. Its distinctive features are automatic stroke segmentation based on spatial relationship and time intervals of consecutive strokes, symbol recognition based on DDCPM (Directional and Direction-Change Pattern Matching) method and function buttons that help user's input and correction. Our experiment results show that the recognition rate is 79 % for 91 kinds of symbols and 90 % for 34 kinds of restricted ones for our target domain.

Various kinds of high-quality media systems have been developed. It is expected that these systems can be used for remote lectures. We are adopting these systems including a high-speed network to construct a remote lecture based on "Instruction with Blackboard", which provides an old-fashioned but very common style of lecture. This instruction style has been often avoided in remote lectures so far because it requires high-quality data transmission. However it is no doubt that this style of instruction is still a very popular teaching method. Therefore, it is educationally meaningful that this teaching method is realized on remote lectures. This paper describes a construction method of the remote lecture based on Instruction with Blackboard and the experiment on the remote lecture using high-quality media systems.

Instruction with Blackboard" is one of traditional lec-ture styles. In this style, the instructor explicates contents with writing the main point on the blackboard. This style has been enough considered as instructional method. We design a style of distance lecture based on Instruction with Blackboard. This style provides a teaching envi-ronment wherein the instructor gives a lecture without getting used to new computer applications. For investi-gating features of distance lecture based on this style, we constructed a distance lecture system and a studio wherein an instructor can teach using a blackboard. This paper reports the model of Instruction with Black-board and distance lecture based on the model.

In this paper, we integrate an Intelligent Tutoring System (ITS) with World Wide Web (WWW) technology, investigate the benefits and limits of the WWW-based ITS, and study technical problems in system development and their solutions. © 1997 Scripta Technica, Inc. Syst Comp Jpn, 28(9): 11–16, 1997