SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model

Open paper
Benchmark Model Rank Results
keyword-spotting-on-google-speech-commandsSSAMBA#11Google Speech Commands V1 12: 96.9Google Speech Commands V2 35: 97.4
speaker-identification-on-voxceleb1SSAMBA#10Top-1 (%): 70.1Number of Params: 99MAccuracy: 70.1

Rank counts only results with a code link.