Event information

Global AI Bootcamp 2024 Lviv Audio Deepfake Detection

Event Description: The rapid development of generative AI in the audio domain has raised concerns about its potential misuse in creating deceptive audio content. The potential misuse has prompted the urgent need for audio deepfake detection. In this presentation, we will cover the state-of-the-art methods for audio deepfake detection, including the building blocks such as feature extractors, classifiers, and loss functions. We will also introduce some key research directions of audio deepfake detection, such as improving the generalization ability and promoting proactive methods. The presentation also encourages participants to contemplate the broader implications of generative AI technology on society and individual privacy.

About the Speaker: You (Neil) Zhang is a PhD candidate in the Department of Electrical and Computer Engineering at the University of Rochester, Rochester, NY, USA. Neil's research focuses on applied machine learning, particularly in speech and audio processing. This includes topics such as spatial audio, synthetic voice detection, and audio-visual analysis. His research contributions have been showcased at prestigious venues such as ICASSP, Interspeech, SPL, WASPAA, TMM. Neil received recognition through the Rising Star Program in Signal Processing at ICASSP 2023 and the Graduate Research Fellowship Program from National Institute of Justice.