X-ARES (eXtensive Audio Representation and Evaluation Suite) is an audio encoder benchmark with kNN (K-nearest neighbor) evaluation method. This unparameterized evaluation uses pre-trained model embeddings directly for classification without training, testing the inherent quality of audio representations.
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.