A Study on the LSI Design with Ultra Low-Power Consumption of Robust Speech Recognition Systems
| Project/Area Number |
20300014
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Computer system/Network
|
|---|
| Research Institution | Hokkaido University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
YOSHIZAWA Shingo 北海道大学, 大学院・情報科学研究科, 助教 (20447080)
|
|---|
| Project Period (FY) |
2008 – 2011
|
| Project Status |
Completed (Fiscal Year 2011)
|
| Budget Amount *help |
¥18,460,000 (Direct Cost: ¥14,200,000、Indirect Cost: ¥4,260,000)
Fiscal Year 2011: ¥5,460,000 (Direct Cost: ¥4,200,000、Indirect Cost: ¥1,260,000)
Fiscal Year 2010: ¥6,760,000 (Direct Cost: ¥5,200,000、Indirect Cost: ¥1,560,000)
Fiscal Year 2009: ¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2008: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
|
|---|
| Keywords | 回路とシステム / ハードウエア設計 / 音声情報処理 / 信号処理 / 音声認識チップ / 雑音ロバスト音声認識 / 音響ゴースト / 極低消費電力化 / サブシュレッシュホールド / フレーズ認識 / 実時間音声認識 / 低電圧回路 |
|---|
| Research Abstract |
In this study, the following two important results have been obtained :(1) the development of acoustic ghost canceller in automatic speech recognition system, and (2) very low power consumption LSI of real time speech recognition. About (1), the new speech feature extraction and the new training method for HMM have been proposed and developed. Using these techniques, the high accuracy of speech recognition is shown under actual noisy environment. About (2), the new hardware design suitable for the method of (1) has been proposed. The proposed LSI has been designed with ultra low power consumption where lower voltage supply, lower clock rate, and parallel/pipeline processing are applied to the proposed architecture.
|
Report
(6 results)
Research Products
(166 results)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
[Presentation] Binary Maximal-Ratio Combining2011
Author(s)
Constantin Siriteanu, Yoshikazu Miyanaga
Organizer
Proceedings of APSIPA Annual Summit and Conference 2011
Place of Presentation
Grand New World Hotel Xian (西安, 中国)
Year and Date
2011-10-18
Related Report
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
[Presentation] VT-AMDF, a Pitch Detection Algorithm2009
Author(s)
Nutthacha Prukkanon, Kosin Chamnongthai, Yoshikazu Miyanaga, KohjiHiguchi
Organizer
International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)
Place of Presentation
金沢
Year and Date
2009-12-07
Related Report
-
-
[Presentation] VT-AMDF, a Pitch Detection Algorithm2009
Author(s)
Nutthacha Prukkanon, Kosin Chamnongthai, Yoshikazu Miyanaga, Kohji Higuchi,
Organizer
International Symposium on Intelligent Signal Processing and Communication Systems(ISPACS)
Place of Presentation
金沢エクセルホテル、石川県
Year and Date
2009-12-07
Related Report
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
