| Project/Area Number |
23650072
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Osaka Institute of Technology (2012)
The University of Tokushima (2011) |
|---|
Principal Investigator |
|
|---|
| Research Collaborator |
MIFUNE Masaki 徳島大学, 大学院・先端技術科学教育部, 博士前期課程2年
|
|---|
| Project Period (FY) |
2011 – 2012
|
| Project Status |
Completed (Fiscal Year 2012)
|
| Budget Amount *help |
¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
Fiscal Year 2012: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2011: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | 知識発見とデータマイニング / 話者識別 / ML-BEATS法 / ML-BEATS / モデル化 / 時系列解析 / 音声符号化 |
|---|
| Research Abstract |
In this study, we have applied the ML-BEATS method to two research fields, constructing a new speaker model and a new speech coding system based on speech recognition and synthesis. Experimental results showed that the new speaker model gave higher performance than conventional models when a few training samples can be used. On the other hand, we could not evaluate sufficiently a performance of a new speech coding system because of delay of implementation of ML-BEATS method.
|
