Harmonic enhancement using learnable comb filter for light-weight full-band speech enhancement model
Abstract
With fewer feature dimensions, filter banks are often used in light-weight full-band speech enhancement models. In order to further enhance the coarse speech in the sub-band domain, it is necessary to apply a post-filtering for harmonic retrieval. The signal processing-based comb filters used in RNNoise and PercepNet have limited performance and may cause speech quality degradation due to inaccurate fundamental frequency estimation. To tackle this problem, we propose a learnable comb filter to enhance harmonics. Based on the sub-band model, we design a DNN-based fundamental frequency estimator to estimate the discrete fundamental frequencies and a comb filter for harmonic enhancement, which are trained via an end-to-end pattern. The experiments show the advantages of our proposed method over PecepNet and DeepFilterNet.
Cite
@article{arxiv.2306.00812,
title = {Harmonic enhancement using learnable comb filter for light-weight full-band speech enhancement model},
author = {Xiaohuai Le and Tong Lei and Li Chen and Yiqing Guo and Chao He and Cheng Chen and Xianjun Xia and Hua Gao and Yijian Xiao and Piao Ding and Shenyi Song and Jing Lu},
journal= {arXiv preprint arXiv:2306.00812},
year = {2023}
}
Comments
accepted by Interspeech 2023