Impostor Detection in Speaker Recognition Using Confusion-Based Confidence Measures

ETRI Journal

关键词: confidence measure;    open-set speaker identification;    speaker verification;    Speaker recognition;   

Others  :  1185342
DOI  :  10.4218/etrij.06.0205.0122

【 摘 要 】

In this letter, we introduce confusion-based confidence measures for detecting an impostor in speaker recognition, which does not require an alternative hypothesis. Most traditional speaker verification methods are based on a hypothesis test, and their performance depends on the robustness of an alternative hypothesis. Compared with the conventional Gaussian mixture model–universal background model (GMM-UBM) scheme, our confusion-based measures show better performance in noise-corrupted speech. The additional computational requirements for our methods are negligible when used to detect or reject impostors.

   

【 参考文献 】

• [1]D. Reynolds, T. Quatieri, and R. Dunn, "Speaker Verification Using Adapted Gaussian Mixture Models," Digital Signal Process, vol. 10, 2000, pp. 19-41.
• [2]Y. Jeong and H.S. Kim, "Recognition Confidence Scoring Using Recognition Results from Perturbed Input Feature Vectors," IEE Electronics Letters, vol. 37, Aug. 2001, pp. 1143-1145.
• [3]K. Kim, H. Kim, and M. Hahn, "Utterance Verification Using Search Confusion Rate and Its N-Best Approach," ETRI J., vol. 27, Aug. 2005, pp. 461-464.
• [4]A. Dempster, N. Laird, and D. Rubin, "Maximum Likelihood from Incomplete Data via the EM Algorithm," J. Roy. Statist. Soc., vol. 39, 1977, pp. 1-38.
• [5]D. Reynolds, "Speaker Identification and Verification Using Gaussian Mixture Models," Speech Communication, vol. 17, 1995, pp. 91-108.
• [6]D. Reynolds and R.C. Rose, "Robust Text Independent Speaker Identification Using Gaussian Mixture Speaker Models," IEEE Trans. on SAP, vol. 3, Jan. 1995, pp. 72-83.