2000 Fiscal Year Final Research Report Summary
Study for Spontaneous Spoken Dialogue Understanding System
| Project/Area Number |
09480059
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B).
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | CHIBA UNIVERSITY |
|---|
Principal Investigator |
ICHIKAWA Akira Chiba University, Graduate School on Science and Technology, Professor, 自然科学研究科, 教授 (80241933)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
HATAOKA Nobuo Hitachi Central Research Laboratory, Chief Research Scientist, 主管研究員
IMIYA Atsushi Chiba University, Department of Engineering, Professor, 工学部, 教授 (10176505)
HORIUCHI Yasuo Chiba University, Graduate School on Science and Technology, Assistant, 自然科学研究科, 助手 (30272347)
|
|---|
| Project Period (FY) |
1997 – 2000
|
| Keywords | spontaneous spoken dialogue understanding system / multi-agent system / reinforcement learning / reinforcement learning / utterance forecasting / 協調的同時処理手法 / 予測文 |
|---|
| Research Abstract |
In a spontaneous spoken dialogue understanding system, real-time response and robustness to the environment are required.
To realize these requirements, we propose a multi-agent system as the system architecture. Each agent has its own function, e.g.phoneme recognition, input utterance structure reasoning from prosody, input utterance forecasting, word reasoning, parsing, etc. The output of this system is the result of co-operation of individual agents that adjust their own behavior to the environment or the input data independency. We propose the co-operation processes.
A reinforcement learning method is proposed for a phoneme recognition agent as a sample agent, and adopted a continuous dynamic programming technique to deal with continuous phoneme recognition. To clarify the fundamental characteristics of the proposed method, we define some simple quasi conditions for the experiments, and confirm favorable results.
The prosodic structure of the input utterance is represented as a tree form and constructed using FO, duration and pause information of each phrase of the utterance. The tree structure shows how strong successive phrases are concerned with each other.
The forecasting the next input utterance uses the handling of two status transfer tables ; controlling for the dialogue in progress and for the dialogue in future.
The system can be expected to achieve high adaptability to the environment(e.g., variation of speakers and tasks)and robustness. Some application systems(e.g.WWW voice browser)ware developed.
|
