BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//global2024.pydata.org//cfp//DKXZFQ
BEGIN:VEVENT
UID:pretalx-cfp-LJPSKA@global2024.pydata.org
DTSTART:20241203T160000Z
DTEND:20241203T163000Z
DESCRIPTION:This talk will cover how to use pre-trained HuggingFace models\
 , specifically wav2vec 2.0 and WavLM\, to detect audio deepfakes. These de
 epfakes\, made possible by advanced voice cloning tools like ElevenLabs an
 d Respeecher\, present risks in areas like misinformation\, fraud\, and pr
 ivacy violations. The session will introduce deepfake audio\, discuss curr
 ent trends in voice cloning\, and provide a hands-on tutorial for using th
 ese transformer-based models to identify synthetic voices by spotting subt
 le anomalies. Participants will learn how to set up these models\, analyze
  deepfake audio datasets\, and assess detection performance\, bridging the
  gap between speech generation and detection technologies.
DTSTAMP:20250709T220252Z
LOCATION:AI/ML Track
SUMMARY:Off-the-shelf HuggingFace models for audio deepfake detection - Adr
 iana Stan
URL:https://global2024.pydata.org/cfp/talk/LJPSKA/
END:VEVENT
END:VCALENDAR