On quick search algorithm for spoken term detection using suffix array and its practical evaluation
| Project/Area Number |
24700167
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Toyohashi University of Technology |
|---|
Principal Investigator |
KATSURADA Kouichi 豊橋技術科学大学, 国際交流センター, 准教授 (80324490)
|
|---|
| Co-Investigator(Renkei-kenkyūsha) |
NITTA Tsuneo 早稲田大学, グリーン・コンピューティング, システム研究機構 (70314101)
|
|---|
| Project Period (FY) |
2012-04-01 – 2015-03-31
|
| Project Status |
Completed (Fiscal Year 2014)
|
| Budget Amount *help |
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2014: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2013: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2012: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | Spoken Term Detection / Suffix Array / 音声検索語検出 / キーワード分割 |
|---|
| Outline of Final Research Achievements |
We developed a fast spoken term detection (STD) system using a suffix array that does not spend a large memory space. This system realizes quick and memory-saving search by regarding a suffix array as a tree and applying DP matching to all paths from the root node. In addition, to overcome the problem that search time exponentially increases according to the length of search keyword, the search keyword is divided into shorter sub-keywords and they are searched for instead of the original keyword. We evaluate our system by comparing it with a general N-gram-index based approach and some other fast STD methods. The experimental results show that our method achieves accurate search without losing quickness of search.
|
Report
(4 results)
Research Products
(24 results)
