Deep neural network based posteriors for text-dependent speaker verification

The i-vector and Joint Factor Analysis (JFA) systems for text- dependent speaker verification use sufficient statistics computed from a speech utterance to estimate speaker models. These statis- tics average the acoustic information over the utterance thereby losing all the sequence information. In this paper, we study ex- plicit content matching using Dynamic Time Warping (DTW) and present the best achievable error rates for speaker-dependent and speaker-independent content matching. For this purpose, a Deep Neural Network/Hidden Markov Model Automatic Speech Recog- nition (DNN/HMM ASR) system is used to extract content-related posterior probabilities. This approach outperforms systems using Gaussian mixture model posteriors by at least 50% Equal Error Rate (EER) on the RSR2015 in content mismatch trials. DNN posteriors are also used in i-vector and JFA systems, obtaining EERs as low as 0.02%.