-
公开(公告)号：EP0870300A1
公开(公告)日：1998-10-14
申请号：EP96921329.0
申请日：1996-06-06
申请人： RUTGERS UNIVERSITY
发明人： MAMMONE, Richard, J. , FARRELL, Kevin , SHARMA, Manish , DEVANG, Naik , ZHANG, Xiaoyu , ASSALEH, Khaled , LIOU, Han-Sheng
摘要： The present invention relates to a pattern recognition system (Fig. 1) which uses data fusion to combine data from a plurality of extracted features (60, 61, 62) and a plurality of classifiers (70, 71, 72). Speaker patterns can be accurately verified with the combination of discriminant based and distortion based classifiers. A novel approach using a training set of a 'leave one out' data can be used for training the system with a reduced data set (Figs. 7A, 7B, 7C). Extracted features can be improved with a pole filtered method for reducing channel effects (Fig. 11B) and an affine transformation for improving the correlation between training and testing data (Fig. 14).
-
公开(公告)号：EP0870300B1
公开(公告)日：2006-04-19
申请号：EP96921329.7
申请日：1996-06-06
申请人： RUTGERS UNIVERSITY
发明人： MAMMONE, Richard, J. , FARRELL, Kevin , SHARMA, Manish , DEVANG, Naik , ZHANG, Xiaoyu , ASSALEH, Khaled , LIOU, Han-Sheng
IPC分类号： G10L17/00
摘要： The present invention relates to a pattern recognition system (Fig. 1) which uses data fusion to combine data from a plurality of extracted features (60, 61, 62) and a plurality of classifiers (70, 71, 72). Speaker patterns can be accurately verified with the combination of discriminant based and distortion based classifiers. A novel approach using a training set of a "leave one out" data can be used for training the system with a reduced data set (Figs. 7A, 7B, 7C). Extracted features can be improved with a pole filtered method for reducing channel effects (Fig. 11B) and an affine transformation for improving the correlation between training and testing data (Fig. 14).
-
搜索结果
2 条记录 (耗时 0.008 秒)
