Title: Text-Independent speaker identification in phoneme-independent subspace using PCA transformation
Authors: Haoze Lu, Masafumi Nishida, Yasuo Horiuchi, Shingo Kuroiwa
Addresses: Graduate School of Advanced Integration Science, Chiba University, Chiba 2638522, Japan. ' Faculty of Science and Engineering, Doshisha University, Kyotanabe 6100394, Japan. ' Graduate School of Advanced Integration Science, Chiba University, Chiba 2638522, Japan. ' Graduate School of Advanced Integration Science, Chiba University, Chiba 2638522, Japan
Abstract: In this paper we proposed a text-independent (TI) speaker identification method that suppresses the phonetic information by a subspace method, under the assumption that a subspace with large variance in the speech feature space is a |phoneme-dependent subspace| and a complementary subspace of it is a |phoneme-independent subspace|. Principal Component Analysis (PCA) is employed to construct these subspaces. Gaussian Mixture Model (GMM)-based speaker identification experiments using both the phonetic information suppressed feature and the conventional Mel-Frequency Ceptrum Coefficient (MFCC) were carried out. As a result, the proposed method has been proven to be effective for decreasing the identification error rates.
Keywords: text-independent speaker recognition; speaker identification; PCA; principal component analysis; phonetic information; subspace projection; MFCC; Mel frequency ceptrum coefficient; MFB; Mel-frequency filter banks; GMM; Gaussian mixture model; biometrics; phoneme-independent subspace.
International Journal of Biometrics, 2010 Vol.2 No.4, pp.379 - 390
Published online: 30 Sep 2010 *Full-text access for editors Access for subscribers Purchase this article Comment on this article