Lightweight Embeddings for Speaker Verification

This paper presents speaker verification (SV) system using deep neural networks with hash representations (binarization) of embeddings. The training procedure is performed on NIST SRE train set, verification is performed on the same corpus with test set. The system architecture is based on deep recurrent layers with attention mechanism. Semi-hard triplets selection is used for the training procedure. The resulting layer of neural network is the tanh function and it makes the hash representation training as end-to-end possible. As a consequence, such a system decreases the embedding memory size in 32x times and increases the system evaluation performance. The equal error rate (EER) is achieved with regard to embeddings without binarization.