Joint Factor Analysis for Text-Dependent Speaker Verification
Patrick J Kenny, Themos Stafylakis, Alam Md. Jahangir, Pierre Ouellet, Marcel Kockmann · 2014
We tackle the problem of text-dependent speaker verification using a version of Joint Factor Analysis (JFA) in which speaker-phrase variability is modeled with a factorial prior and channel variability with a subspace prior. We implemented this using Zhao and Dong’s variational Bayes algorithm, an extension of Vogt’s Gauss-Seidel method that supports UBM adaptation to the speaker and channel effects in enrollment and test utter-ances. We report results on the RSR2015 dataset obtained with two types of likelihood ratio and several strategies for UBM adaptation. We found that using a large UBM and decomposing JFA into a feature extractor and a simple back end classifier (in a way broadly analogous to the i-vector/PLDA cascade) gives better results than using likelihood ratios of either type to make verification decisions. This method involves no UBM adapta-tion other than to the lexical content of utterances and it is based on Vogt’s algorithm rather than Zhao and Dong’s. It results in an equal error rate of 0.5 % on the RSR2015 evaluation set. 1.