Researchers at The University of Texas at Austin have used artificial intelligence to create visual images from audio recordings of various urban and rural areas around the world. Through machine learning, the team was able to accurately generate street-view images based on sound cues, demonstrating that machines can replicate the human connection between audio and visual perception of environments. The AI model created by the researchers was able to produce high-resolution images matching real-world photos, with human participants successfully selecting generated images that corresponded to source audio samples 80% of the time. This innovative technology has the potential to change how we interact with and understand different places.
https://news.utexas.edu/2024/11/27/researchers-use-ai-to-turn-sound-recordings-into-accurate-street-images/