Exploiting auditory filter models as interpretable convolutional frontends to obtain optimal architectures for speaker gender recognition

Applied Acoustics（2023）

引用 0|浏览0

暂无评分

摘要

•The use of auditory filter model (AFM) makes DNNs interpretable.•Reducing the number of network parameters is a way to create more efficient architectures.•A clustering approach is used to reduce the number of learnable filters of the AFM.

查看译文

关键词

Speech Processing,Gender Recognition,Auditory Filter Models,Interpretable Convolutional Frontend,Convolutional Neural Network,Deep Learning

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要