Xi-Vector Embedding for Speaker Recognition

We present a Bayesian formulation for deep speaker embedding, wherein the xi-vector is counterpart of x-vector, taking into account uncertainty estimate. On technology front, we offer simple and straightforward extension to now widely used x-vector. It consists an auxiliary neural net predicting frame-wise input sequence. show that proposed leads substantial improvement across all operating points, with significant reduction in error rates detection cost. theoretical our proposal integrates linear Gaussian model speaker-embedding networks via pooling layer. In one sense, i-vector Hence, refer embedding as xi-vector, which pronounced /zai/ vector. Experimental results on SITW evaluation set consistent over 17.5% equal-error-rate 10.9% minimum