Welcome to the project page for Bayesian auditory scene synthesis. On this page, you can find:

• Explanations, demos, and example model inferences for the classic ASA phenomena in the paper
• Each figure with corresponding sounds
• Sounds for all of the everyday sound inferences

A good place to start: listen to some model inferences on everyday sounds.

To cite our paper:

    
      @article{cusimano2024listening,
        title = {Listening with generative models},
        journal = {Cognition},
        volume = {253},
        pages = {105874},
        year = {2024},
        issn = {0010-0277},
        doi = {https://doi.org/10.1016/j.cognition.2024.105874},
        url = {https://www.sciencedirect.com/science/article/pii/S0010027724001604},
        author = {Maddie Cusimano and Luke B. Hewitt and Josh H. McDermott}
      }
    
  

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License

.