Non-linear PLDA for i-vector speaker verification
نویسندگان
چکیده
Two approaches are presented for non-linear PLDA to be used in speaker verification. In NIST 2010 speaker recognition evaluation (SRE) tests under DET-5 conditions, the two methods and particularly their combination provided significant improvements in equal error rates and minDCF values over a standard PLDA scheme. The proposed schemes were also applied within a speaker verification system that employs DNN-based sufficient statistics calculation resulting in a 45 % reduction in minDCF relative to a conventional GMM based system
منابع مشابه
PLDA based speaker verification with weighted LDA techniques
This paper investigates the use of the dimensionality-reduction techniques weighted linear discriminant analysis (WLDA), and weighted median fisher discriminant analysis (WMFD), before probabilistic linear discriminant analysis (PLDA) modeling for the purpose of improving speaker verification performance in the presence of high inter-session variability. Recently it was shown that WLDA techniqu...
متن کاملPLDA Modeling in I-Vector and Supervector Space for Speaker Verification
In this paper, we advocate the use of uncompressed form of ivector. We employ the probabilistic linear discriminant analysis (PLDA) to handle speaker and session variability for speaker verification task. An i-vector is a low-dimensional vector containing both speaker and channel information acquired from a speech segment. When PLDA is used on i-vector, dimension reduction is performed twice – ...
متن کاملExploring Hilbert envelope based acoustic features in i-vector speaker verification using HT-PLDA
In this study we evaluate the effectiveness of our recently introduced Mean Hilbert Envelope Coefficients (MHEC) in i-vector speaker verification using heavy-tailed probabilistic linear discriminant analysis (HT-PLDA) as the compensation/backend framework. The i-vectors are estimated for MHECs, and also the conventional and widely used MFCCs for comparison. The linear discriminant analysis (LDA...
متن کاملSNR-invariant PLDA modeling for robust speaker verification
In spite of the great success of the i-vector/PLDA framework, speaker verification in noisy environments remains a challenge. To compensate for the variability of i-vectors caused by different levels of background noise, this paper proposes a new framework, namely SNR-invariant PLDA, for robust speaker verification. By assuming that i-vectors extracted from utterances falling within a narrow SN...
متن کاملComparison between supervised and unsupervised learning of probabilistic linear discriminant analysis mixture models for speaker verification
We present a comparison of speaker verification systems based on unsupervised and supervised mixtures of probabilistic linear discriminant analysis (PLDA) models. This paper explores current applicability of unsupervised mixtures of PLDA models with Gaussian priors in a total variability space for speaker verification. Moreover, we analyze the experimental conditions under which this applicatio...
متن کامل