DEEP NEURAL NETWORKS FOR SMALL FOOTPRINT TEXT-DEPENDENT SPEAKER VERIFICATION

In this paper we investigate the use of deep neural networks (DNNs) for a small footprint text-dependent speaker verification task. At de-velopment stage, a DNN is trained to classify speakers at the frame-level. During speaker enrollment, the trained DNN is used to extract speaker specific features from the last hidden layer. The average of these speaker features, or d-vector, is taken as the speaker model. At evaluation stage, a d-vector is extracted for each utterance and compared to the enrolled speaker model to make a verification deci-sion. Experimental results show the DNN based speaker verification system achieves good performance compared to a popular i-vector system on a small footprint text-dependent speaker verification task. In addition, the DNN based system is more robust to additive noise and outperforms the i-vector system at low False Rejection operat-ing points. Finally the combined system outperforms the i-vector system by 14 % and 25 % relative in equal error rate (EER) for clean and noisy conditions respectively. Index Terms — Deep neural networks, speaker verification. 1