Browse > Article
http://dx.doi.org/10.7776/ASK.2014.33.1.068

Histogram Equalization Using Centroids of Fuzzy C-Means of Background Speakers' Utterances for Majority Voting Based Speaker Identification  

Kim, Myung-Jae (서울시립대학교 컴퓨터과학부)
Yang, Il-Ho (서울시립대학교 컴퓨터과학부)
Yu, Ha-Jin (서울시립대학교 컴퓨터과학부)
Publication Information
The Journal of the Acoustical Society of Korea / v.33, no.1, 2014 , pp. 68-74 More about this Journal
Abstract
In a previous work, we proposed a novel approach of histogram equalization using a supplement set which is composed of centroids of Fuzzy C-Means of the background utterances. The performance of the proposed method is affected by the size of the supplement set, but it is difficult to find the best size at the point of recognition. In this paper, we propose a histogram equalization using a supplement set for majority voting based speaker identification. The proposed method identifies test utterances using a majority voting on the histogram equalization methods with various sizes of supplement sets. The proposed method is compared with the conventional feature normalization methods such as CMN(Cepstral Mean Normalization), MVN(Mean and Variance Normalization), and HEQ(Histogram Equalization) and the histogram equalization method using a supplement set.
Keywords
Speaker recognition; Speaker identification; Histogram equalization; Majority voting;
Citations & Related Records
연도 인용수 순위
  • Reference
1 R. O. Duda and P. E. Hart, D. G. Stork, Pattern Classification (John Wiley & Sons, New York, 2012), pp. 528-530.
2 D. A. Reynolds, T. F. Quatieri, and R. B. Dunn, "Speaker verification using adapted gaussian mixture models," Digit. Signal Process. 10, 19-41 (2000).   DOI   ScienceOn
3 M. Kim, I. Yang, and H. Yu, "Histogram Equalization Using Centroids of Fuzzy C-Means of Background Speakers' Utterances for Speaker Identification," in Proc. Stat. Lang. and Speech Proc. 1, 143-151 (2013).
4 I. Oh, Pattern Recognition, (in korean, Kyobobook, Seoul, 2008), pp. 438-441.
5 G.729 [online], http://www.itu.int/rec/T-REC-G.729-200701-S/en.
6 SILK [online], https://developer.skype.com/silk.
7 Speex [online], http://www.speex.org/.
8 B. Atal, "Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification," J. Acoust. Soc. Am. 55, 1304 (1974).   DOI   ScienceOn
9 O. Viikki and K. Laurila, "Cepstral domain segmental feature vector normalization for noise robust speech recognition," Speech Commun. 25, 133-147 (1998).   DOI
10 P. J. Moreno, B. Raj, and R. M. Stern, "A vector taylor series approach for environment-independent speech recognition," in Proc. IEEE Int. Conf. Acoust. Speech Signal Proc. 2, 733-736 (1996).
11 N. S. Kim, "Statistical linear approximation for environment compensation," IEEE Signal Proc. Lett. 5, 8-10 (1998).   DOI
12 M. Skosan and D. Mashao, "Modified segmental histogram equalization for robust speaker verification," Pattern Recognit. Lett. 27, 479-486 (2006).   DOI
13 J. C. Segura, C. Benitez, A. De La Torre, A. J. Rubio, and J. Ramirez, "Cepstral domain segmental nonlinear feature transformations for robust speech recognition," IEEE Signal Proc. Lett. 11, 517-520 (2004).   DOI
14 A. de la Torre, A. M. Peinado, J. C. Segura, J. L. Perez-Cordoba, M. C. Benitez, and A. J. Rubio, "Histogram equalization of speech representation for robust speech recognition," IEEE Trans. Speech Audio Proc. 13, 355-366 (2005).   DOI
15 J. Pelecanos and S. Sridharan, "Feature warping for robust speaker verification," in Proc. Speaker Odyssey, 213-218 (2001).
16 M. Skosan and D. Mashao, "Matching feature distributions for robust speaker verification," in Proc. PRASA, 42-47 (2004).
17 R. C. Gonzalez and P. wintz, Digital Image Processing (Addision-Wesley Publishing Company, Reading, 1987), pp. 275-281.