Hledání nových cest v rozpoznávání řečníka založeného na neuronových sítích

Since the assignment of this work is very broad, it was necessary to focus only on a certain area. In the end, this work aims to apply the Stochastic Weight Averaging optimization method to the training process of the Deep Neural Network. After presenting the necessary theoretical knowledge in the first part of the work, the second part with the experiments courses follows. In the theoretical part, the main focus is on presenting the complete lifecycle of the training and evaluation process, including a description of each component. The practical part provides a detailed look at each experiment, intended to demonstrate the effectiveness of the overall speaker recognition system's performance enhancement. The overall performance improvement is achieved by gradually applying various training configurations where the experience from previous experiments is taken into account. The key ingredient to the successful Stochastic Weight Averaging in the experiments was a sufficiently high Learning Rate value with the successive transition applied or Cyclic course of the Learning Rate.

Speaker Recognition, Residual Network, x-vector, Deep Neural Network Training Optimization Techniques, Stochastic Weight Averaging