https://scholars.lib.ntu.edu.tw/handle/123456789/294424
標題: | Eigen-MLLR Coefficients as New Feature Parameters for Speaker Identification | 作者: | Nick J.-C. Wang Wei-Ho Tsai LIN-SHAN LEE |
公開日期: | 九月-2001 | 起(迄)頁: | 1385-1388 | 來源出版物: | EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology | 會議論文: | 7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001 | 摘要: | Eigen-MLLR coefficients are proposed as new feature pa- rameters for speaker-identiffication in this paper. By performing principle component analysis on MLLR parameters among training speakers, the eigen-MLLR coefficients (EMCs) are derived as the coefficients for the eigenvectors. The discriminating function of the new EMC features based on the Fisher criterion is found to be ten times larger than that of mel-frequency cepstral coefficient (MFCC) features, for distinguishing speakers. The speaker-identification accuracy using the EMC features are shown to be significantly better than that using MFCC features, especially when the quantity of enrollment data is limited. It is also shown that properly combining MFCC and EMC features can achieve a significant error rate re- duction on the order of 50%-60% as compared to using MFCC features alone. |
URI: | http://scholars.lib.ntu.edu.tw/handle/123456789/294424 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85009063026&partnerID=40&md5=5629708599eaa63bfc2e542cf7bc5854 |
SDG/關鍵字: | Loudspeakers; Principal component analysis; Speech communication; Error rate; Feature parameters; Fisher criterion; Mel-frequency cepstral coefficients; Principle component analysis; Speaker identification; Speech recognition |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。