Automatic Generation of Utterances with speaker's characteristics
| Project/Area Number |
15K12179
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Entertainment and game informatics 1
|
|---|
| Research Institution | Nagoya University |
|---|
Principal Investigator |
Sato Satoshi 名古屋大学, 工学研究科, 教授 (30205918)
|
|---|
| Project Period (FY) |
2015-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥3,510,000 (Direct Cost: ¥2,700,000、Indirect Cost: ¥810,000)
Fiscal Year 2016: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2015: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
|---|
| Keywords | 自然言語処理 / 発話生成 / キャラクタ性 / ことばと個性 / ことばのキャラクタ性 / 発話意図 / 表現文型 / 発話文生成 / 発話 |
|---|
| Outline of Final Research Achievements |
We have complied “Dictionary of Japanese Sentence Patterns”, which is a base of automatic generation of utterances with speaker’s characteristics. This dictionary contains 675 sentence patterns, which are classified into 50 groups of utterance intensions, such as “request” and “invitation.” For each sentence pattern, an eight dimensional vector is defined, which indicates speech styles such as gender and politeness. Using this dictionary, we have implemented a system that can generate utterances with a given speaker’s characteristics.
|
Report
(3 results)
Research Products
(2 results)
