Reliable Visualization for Deep Speaker Recognition - 语音可解释性

原创

于 2024-02-20 23:13:16 发布 · 965 阅读

9 ·

CC 4.0 BY-SA版权

文章标签：

#人工智能 #深度学习

本文探讨了三种视觉化方法（Grad-CAM++,Score-CAM和Layer-CAM）在语音识别中的应用，发现Layer-CAM在区分目标说话者和干扰者方面表现出色，尤其是在多说话者实验中。Layer-CAM生成的S2层地图被认为最具鉴别力，且跨层聚合可以进一步提升性能。

MOTIVATION OF READING: 语音任务可解释性

Link: http://arxiv.org/abs/2204.03852

Code：http://project.cslt.org/

1. Overview

Motivation of the work:

If any of the visualization tools are reliable when applied to speaker recognition, which makes the conclusions obtained from visualization not fully convincing.

Three CAM algorithms will be investigated: Grad-CAM++, Score-CAM and Layer-CAM. The main idea of these algorithms is to generate a saliency map by combining the activation maps (channels) of a convolutional layer.