화자확인에서 특징벡터의 순시 정보와 선형 변환의 효과적인 적용
Effective Combination of Temporal Information and Linear Transformation of Feature Vector in Speaker Verification
0
조회
0
다운로드
2
인용
0
참고문헌
초록
Abstract
The feature vectors which are used in conventional speaker recognition (SR) systems may have many correlations between their neighbors. To improve the performance of the SR, many researchers adopted linear transformation method like principal component analysis (PCA). In general, the linear transformation of the feature vectors is based on concatenated form of the static features and their dynamic features. However, the linear transformation which based on both the static features and their dynamic features is more complex than that based on the static features alone due to the high order of the features. To overcome these problems, we propose an efficient method that applies linear transformation and temporal information of the features to reduce complexity and improve the performance in speaker verification (SV). The proposed method first performs a linear transformation by PCA coefficients. The delta parameters for temporal information are then obtained from the transformed features. The proposed method only requires 1/4 in the size of the covariance matrix compared with adding the static and their dynamic features for PCA coefficients. Also, the delta parameters are extracted from the linearly transformed features after the reduction of dimension in the static features. Compared with the PCA and conventional methods in terms of equal error rate (EER) in SV, the proposed method shows better performance while requiring less storage space and complexity.
참고문헌 (17)
- Liu, "On the use of orthogonal GMM in speaker recognition", ICASSP 99, pp.845~849 (1999), ICASSP
- Y. Ariki, "Speaker recognition and speaker normalization by projection to speaker subspace", ICASSP 96, pp.319~322 (1996), ICASSP
- 서창우, "화자식별을 위한 전역 공분산에 기반한 주성분분석", 말소리와 음성과학, 1(1), pp.69~73 (2009), 한국음성학회
- 서창우, "화자식별을 위한 전역 공분산에 기반한 주성분분석", 말소리와 음성과학, 1(1), pp.69~73 (2009), 한국음성학회
- T. Takiguchi, "Robust Feature Extraction using Kernel PCA", ICASSP 06, pp.509~512 (2006), ICASSP
- N. Kambhatla, "Dimension reduction by local PCA", Neural Computation, 9, pp.1493~1503 (1997)
- C. Seo, "GMM based on local PCA for speaker identification", Electronic Letters, 37(24), pp.1486~1488 (2001)
- S. Young, "The HTK Book (for HTK version 3.2)", Cambridge University Engineering Department, ~ (2002)
- G.H. Golub, "Matrix Computations" (1996), The Johns Hopkins University Press
- B.N. Flury, "Common Principal Components in k Groups", JASA, 79(388), pp.892~898 (1984)
- O. Thyes, "Speaker Identification and Verification Using Eigenvoices", ICSLP-2000, pp.242~245 (2000)
- K.Y. Lee, "Local fuzzy PCA based GMM with dimension reduction on speaker identification", Pattern Recog. Letters, 25, pp.1811~1817 (2004)
- D. Reynolds, "Robust text-independent speaker identification using Gaussian mixture speaker models", IEEE Trans. on SAP, 3(1), pp.72~82 (1995)
- A. Dempster, "Maximum likelihood from incomplete data via the EM algorithm", J. Royal Stat. Sco, 29, pp.1~38 (1977)
- S. Parthasarathy, "General phrase speaker verification using sub-word background models and likelihood-ratio scoring", ICSLP-96 (1996), ICSLP
- T. Matsui, "Likelihood normalization for speaker verification using a phoneme and speaker-independent model", Speech Communication, 17, pp.109~116 (1995)
- Y. Lind, "An algorithm for vector quantizer design", IEEE Trans. Commun, 28, pp.84~95 (1980), IEEE