| Project/Area Number |
23500209
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Nagoya University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
TAKEDA Kazuya 名古屋大学, 大学院・情報科学研究科, 教授 (20273295)
MIYAJIMA Chiyomi 名古屋大学, 大学院・情報科学研究科, 助教 (90335092)
|
|---|
| Project Period (FY) |
2011 – 2013
|
| Project Status |
Completed (Fiscal Year 2013)
|
| Budget Amount *help |
¥5,070,000 (Direct Cost: ¥3,900,000、Indirect Cost: ¥1,170,000)
Fiscal Year 2013: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2012: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2011: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
|
|---|
| Keywords | 音声対話 / 情報検索 / 潜在意味解析 / 楽曲間類似度 / 音声ドキュメント / 楽曲 / 類似度 / 検索 / 人間対人間 / 潜在意味 |
|---|
| Research Abstract |
We conducted below:
(1)We proposed to explain multiple understanding states using graph structure and the method to expand the nodes according to the progress of the dialog, to lead a "good" answer from the user,(2)we also proposed the method to recommend suitable music for the situation where humans were talking using the recognition result of the conversation, (3)we improved spoken document retrieval methods towards constructing a prior knowledge for understanding, (4)Considering the dialog to search music, we investigated physical features of acoustics to express the individual similarity measurement of humans, to construct prior knowledge to the search.
|
