The Vocal Imitation dataset is a collection of crowd-sourced recordings where people imitate a wide variety of sounds, like animal noises or mechanical sounds. The dataset was created to support research into systems that can understand and process vocal imitations, such as search engines that can be queried by imitating a sound (Query-by-Vocal Imitation or QBV).
No results indexed yet — be the first to submit a score.
Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.