| Project/Area Number |
16K18111
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Measurement engineering
|
|---|
| Research Institution | Saitama University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2016-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2017: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2016: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
|
|---|
| Keywords | 音声強調 / 雑音除去 / 音声解析 / 周波数推定 / ピッチ抽出 / 深層学習 |
|---|
| Outline of Final Research Achievements |
We proposed accurate analysis methods for speech and and a speech enhancement architecture using deep neural network (DNN) in order to develop a speech enhancement algorithm on highly noisy environment. The former is an method to estimate the speech and noise accurately from the noisy speech including the non-stationary noise. The latter is designed analytically so as to be a structure matching the speech enhancement. They are expected to be important techniques in the environment affected by noise, such as the hands-free speech communication or the speech recognition on the AI speaker.
|
