MALSORI (대한음성학회지:말소리)
- Issue 51
- /
- Pages.99-115
- /
- 2004
- /
- 1226-1173(pISSN)
Language Model Adaptation for Broadcast News Recognition
방송 뉴스 인식을 위한 언어 모델 적응
-
Kim Hyun Suk
(ETRI) ;
-
Jeon Hyung Bae
(ETRI) ;
-
Kim Sanghun
(ETRI) ;
- Choi Joon Ki (ETRI) ;
-
Yun Seung
(ETRI)
- Published : 2004.09.01
Abstract
In this parer, we propose LM adaptation for broadcast news recognition. We collect information of recent articles from the internet on real time, make a recent small size LM, and then interpolate recent LM with a existing LM composed of existing large broadcast news corpus. We performed interpolation experiments to get the best type of articles from recent corpus because collected recent corpus is composed of articles which are related with test set, and which are unrelated. When we made an adapted LM using recent LM with similar articles to test set through Tf-Idf method and existing LM, we got the best result that ERR of pseudo-morpheme based recognition performance has 17.2 % improvement and the number of OOV has reduction from 70 to 27.