Personalized Speech Enhancement Combining Band-Split RNN and Speaker Attentive Module
Xiaohuai Le, Li Chen, Chao He, Yiqing Guo, Cheng Chen, Xianjun Xia, Jing Lu
Abstract
Target speaker information can be utilized in speech enhancement (SE) models to more effectively extract the desired speech. Previous works introduce the speaker embedding into speech enhancement models by means of concatenation or affine transformation. In this paper, we propose a speaker attentive module to calculate the attention scores between the speaker embedding and the intermediate features, which are used to rescale the features. By merging this module in the state-of-the-art SE model, we construct the personalized SE model for ICASSP Signal Processing Grand Challenge: DNS Challenge 5 (2023). Our system achieves a final score of 0.529 on the blind test set of track1 and 0.549 on track2.
BibTeX
@inproceedings{icassp2023_personalizedspee,
title = {Personalized Speech Enhancement Combining Band-Split RNN and Speaker Attentive Module},
author = {Xiaohuai Le and Li Chen and Chao He and Yiqing Guo and Cheng Chen and Xianjun Xia and Jing Lu},
booktitle = {ICASSP 2023},
year = {2023}
}