shlogg · Early preview
Mike Young @mikeyoung44

Detecting AI Voice Deepfakes With Crowdsourced Data

Researchers tackle AI voice deepfakes with crowdsourced data in 5th ASVspoof challenge, detecting spoofing & adversarial attacks. New dataset created with natural recording conditions.

This is a Plain English Papers summary of a research paper called Global Study Reveals New Methods to Detect AI Voice Deepfakes Using Crowdsourced Data. If you like these kinds of analysis, you should join AImodels.fyi or follow us on Twitter.

  
  
  Overview

Fifth iteration of ASVspoof challenge focused on detecting fake speech
Uses crowdsourced recordings from 800+ speakers worldwide
Tests detection of spoofing, deepfakes, and adversarial attacks
Created new dataset with natural recording conditions
Implements quality control measures for data collection

  
  
  Plain English Explanation...