Discriminative learning in sequential pattern recognition

被引：86
作者：
He, Xiaodong
Deng, Li [1 ,2 ]
Chou, Wu
机构：
[1] Microsoft Res, Redmond, WA USA
[2] Univ Washington, Seattle, WA 98195 USA
来源：
IEEE SIGNAL PROCESSING MAGAZINE | 2008年 / 25卷 / 05期
关键词：
D O I：
10.1109/MSP.2008.926652
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
引用
收藏
页码：14 / 36
页数：23
相关论文
共 67 条
[31]  
Lafferty J., 2001, PROC 18 INT C MACHIN, DOI [DOI 10.1038/NPROT.2006.61, 10.1038/nprot.2006.61]
[32]  
LEROUX J, 2005, P EUR, P3341
[33]  
Li Y, 2005, IEEE I CONF COMP VIS, P1605
[34]  
Macherey W., 2005, P INT LISB PORT, P2133
[35]   A tribute to Larry Erlbaum [J].
Markman, Arthur B. .
COGNITIVE SCIENCE, 2007, 31 (01) :1-1
[36]  
McCallum A., 2000, Icml, V17, P591
[37]  
MCDERMOTT E, 2005, NEUR INF PROC SYST N
[38]  
MCDERMOTT E, 2006, P INT C AC SPEECH SI, P15
[39]   Discriminative training for large-vocabulary speech recognition using minimum classification error [J].
McDermott, Erik ;
Hazen, Timothy J. ;
Le Roux, Jonathan ;
Nakamura, Atsushi ;
Katagiri, Shigeru .
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2007, 15 (01) :203-223
[40]   ON A MODEL-ROBUST TRAINING METHOD FOR SPEECH RECOGNITION [J].
NADAS, A ;
NAHAMOO, D ;
PICHENY, MA .
IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1988, 36 (09) :1432-1436
1234567