# Visually Indicated Sounds Source: [Visually Indicated Sounds]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:20:33.540Z Authors: Andrew Owens, Phillip Isola, Josh McDermott, Antonio Torralba, Edward H. Adelson, William T. Freeman Published: 2015-12-28T20:56:50.000Z ## Abstract Objects make distinctive sounds when they are hit or scratched. These sounds reveal aspects of an object's material properties, as well as the actions that produced them. In this paper, we propose the task of predicting what sound an object makes when struck as a way of studying physical interactions within a visual scene. We present an algorithm that synthesizes sound from silent videos of people hitting and scratching objects with a drumstick. This algorithm uses a recurrent neural network to predict sound features from videos and then produces a waveform from these features with an example-based synthesis procedure. We show that the sounds predicted by our model are realistic enough to fool participants in a "real or fake" psychophysical experiment, and that they convey significant information about material properties and physical interactions. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Predicting Sounds from Video on Greatest Hits](): Predicting Sounds from Video; Greatest Hits; Loudness Error: 0.21. - [Impact sound synthesis on Greatest Hits (test)](): Impact sound synthesis; Greatest Hits (test); KL Div.: 7.39. ## Original sources and implementation [Original paper]() [PDF]()