Researchers Use AI To Turn Sound Recordings Into Accurate Street Images
SMRTR summary
University of Texas researchers used AI to convert audio recordings into accurate street-view images, demonstrating machines can replicate human audio-visual perception. The AI model, trained on YouTube video data from various locations, generated images with strong correlations to real-world photos in sky, greenery, and building proportions, with 80% accuracy in human evaluations.
SMRTR provides this summary for quick context. The original article belongs to Daily.dev.
Read the original article