With the advent of the deep neural network, automatic speech recognition (ASR) has seen
significant improvements in recent years. However, ASR performance degrades rapidly …

A method is presented in which conventional speech algorithms are applied, with no
modifications, to improve their performance in extremely noisy environments. It has been …

This thesis focuses on the robustness issues of speaker verification (SV) systems. Although
current SV systems perform well under clean condition, their performance degrades …