Source code for paper "Who is real Bob? Adversarial Attacks on Speaker Recognition Systems" (IEEE S&P 2021)

Final project for the Speaker Recognition course on Udemy, 机器之心, 深蓝学院 and 语音之家

Advanced speaker identification and verification system using deep learning. Features emotion recognition, language detection, and anti-spoofing capabilities for secure voice authentication applications.

Voice Activity Detection and signal segmentation in time windows. Feature extraction in time and frequency domain. Classification in ten individual speakers.

Speaker recognition task using wav2vec2 model.