Emotion mismatch between training and testing will cause system performance decline sharply which is emotional speaker recognition. It is an important idea to solve this problem according to the emotion normalization of test speech. This method proceeds from analysis of the differences between every kind of emotional speech and neutral speech. Besides, it takes the baseband mismatch of emotional changes as the main line. At the same time, it gives the corresponding algorithm according to four technical points which are emotional expansion, emotional shield, emotional normalization and score compensation. Compared with the traditional GMM-UBM method, the recognition rate in MASC corpus and EPST corpus was increased by 3.80% and 8.81% respectively.
 M. Pawlewski and J. Jones, “URU Plus—A Scalable Component-Based Speaker-Verification System for BT’s 21st Century Network,” BT Technology Journal, Vol. 25, No. 3-4, 2007, pp. 170-178. http://dx.doi.org/10.1007/s10550-007-0072-y
 S. Furui, “Cepstral Analysis Technique for Automatic Speaker Verification,” IEEE Transactions on Acoustics, Speech and Signal Processing, Vol. 29, No. 2, 1981, pp. 254-272. http://dx.doi.org/10.1109/TASSP.1981.1163530
 R. D. Zilca, B. Kingsbury, J. Navratil, et al., “Pseudo Pitch Synchronous Analysis of Speech with Applications to Speaker Recognition,” IEEE Transactions on Audio Speech and Language Processing, Vol. 14, No. 2, 2006, pp. 467-478. http://dx.doi.org/10.1109/TSA.2005.857809
 D. Morrison, R. Wang and L. C. De Silva, “Ensemble Methods for Spoken Emotion Recognition in Call-Centres,” Speech Communication, Vol. 49, No. 2, 2007, pp. 98-112. http://dx.doi.org/10.1016/j.specom.2006.11.004