BAT: Better Audio Transformer Guided by Convex Gated Probing
Researchers have developed a new probing method called Convex Gated Probing (CGP) to more accurately evaluate audio self-supervised learning (SSL) embeddings. This method aims to bridge the gap between finetuning and probing, which has historically been a challenge in the audio domain. By using CGP to guide the refinement of existing audio SSL pipelines, the team introduced the Better Audio Transformer (BAT), setting new state-of-the-art results on audio benchmarks. AI
IMPACT Introduces a more reliable evaluation method for audio SSL, potentially guiding future research and model development in the field.