Understanding Self-Attention of Self-Supervised Audio Transformers
2020-06-05Code Available0· sign in to hype
Shu-wen Yang, Andy T. Liu, Hung-Yi Lee
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/592595/TERApytorch★ 4
- github.com/Pandade1997/tera_asvproofpytorch★ 2
Abstract
Self-supervised Audio Transformers (SAT) enable great success in many downstream speech applications like ASR, but how they work has not been widely explored yet. In this work, we present multiple strategies for the analysis of attention mechanisms in SAT. We categorize attentions into explainable categories, where we discover each category possesses its own unique functionality. We provide a visualization tool for understanding multi-head self-attention, importance ranking strategies for identifying critical attention, and attention refinement techniques to improve model performance.