Please use this identifier to cite or link to this item:
Title: Normalization of total variability matrix for i-vector/PLDA speaker verification
Authors: Rao, W
Mak, MW 
Lee, KA
Keywords: i-Vectors
Probabilistic linear discriminant analysis
Speaker verification
Total variability matrix
Uncertainty propagation
Issue Date: 2015
Publisher: Institute of Electrical and Electronics Engineers Inc.
Source: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2015, v. 2015-August, 7178758, p. 4180-4184 How to cite?
Abstract: Gaussian PLDA with uncertainty propagation is effective for i-vector based speaker verification. The idea is to propagate the uncertainty of i-vectors caused by the duration variability of utterances to the PLDA model. However, a limitation of the method is the difficulty of performing length normalization on the posterior covariance matrix of an i-vector. This paper proposes a method to avoid performing length normalization on i-vectors in Gaussian PLDA modeling so that uncertainty propagation can be directly applied without transforming the posterior covariance matrices of i-vectors. Instead of performing length normalization on i-vectors independently, the proposed method normalizes the column vectors of the total variability matrix. Because the i-vectors of all utterances are derived from the same normalized total variability matrix, they will be subject to the same degree of normalization, thereby avoiding the undesirable distortion introduced by the utterance-dependent length-normalization process. Experimental results on both NIST 2010 and 2012 SREs demonstrate that the proposed method achieves a performance similar to (and in some situations better than) that of Gaussian PLDA with length normalization. The method has the potential of improving the performance of uncertainty propagation for i-vector/PLDA speaker verification.
Description: 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015, 19-24 April 2014
ISBN: 9781467369985
DOI: 10.1109/ICASSP.2015.7178758
Appears in Collections:Conference Paper

View full-text via PolyU eLinks SFX Query
Show full item record


Last Week
Last month
Citations as of Jul 15, 2018

Page view(s)

Last Week
Last month
Citations as of Jul 10, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.