0
喜欢
0
书签
声明论文
DATA COLLECTION AND EVALUATION OF AURORA-2 JAPANESE CORPUS   
摘  要:   Speech recognition systems must still be improved when they are exposed to noisy environments. For this improvement, develop- ments of the standard evaluation corpus and assessment technolo- gies are essential. Recently the AURORA-2,3 corpus and their evaluation scenarios have had significant impacts on noisy speech recognition research. This paper introduces a Japanese noisy speech corpus and its evaluation scripts, called AURORA-2J. The AURORA-2J is a Japanese connected digits corpus. The data col- lection and evaluation scenarios are designed in the same way as AURORA-2 with the help of ETSI AURORA group. Furthermore, we have collected in-car speech corpus similar to AURORA-3. The in-car speech corpus includes Japanese connected digits and command words collected in a moving car. This paper describes the data collection, baseline scripts, and its baseline performance.
发  表:   2003

论文统计图
共享有1个版本

Bibtex
创新指数 
阅读指数 
重现指数 
论文点评
还没有人点评哦

Feedback
Feedback
Feedback
我想反馈:
排行榜