Author : Veena K V 1
Date of Publication :7th November 2015
Abstract: The two major applications of speaker recognition applications are speaker verification and speaker identification. But in most of the cases the signal is corrupted with background interferences such as noise and echo. This paper proposes the method of speaker recognition and identification after the noise separation and echo cancellation. Support vector machine(svm) classification based signal separation is adopted here and general kalman filter is used for echo cancellation. Adapted gaussian mixture models along with universal background model(ubm) is used for speaker verification and identification tasks.
Reference :
-
[1] Douglas A. Reynolds, Thomas F. Quatieri, and Robert B.Dunn ”Speaker Verification Using Adapted Gaussian Mixture Models”M.I.T. Lincoln Laboratory, 244 Wood St., Lexington, Massachusetts 02420
[2] Constantin Paleologu, Jacob Benesty, and Silviu Ciochina “Study of the General Kalman Filter for Echo Cancellation in ”IEEE Trans. on Audio, Speech, Lang. Process. ” vol. 21, no.8,August 2013.
[3] Kun Han, and DeLiang Wang “Towards Generalizing Classification Based Speech Separation, ” in ”IEEE Trans. on Audio, Speech, Lang. Process. ” vol. 21, no. 1,January 2013.
[4] Frank Dellaert “The Expectation Maximization Algorithm ,”Georgia Institute of Technology Technical Report number GIT-GVU-02-20 February 2002
[5] Y. Ephraim and D. Malah, “Speech enhancement using a minimum- mean square error short-time spectral amplitude estimator,”IEEE Trans. Acoust., Speech, Signal Process., vol. ASSP-32, no. 6, pp. 1109–1121, Dec. 1984.