ZipEnhancer: Dual-Path Down-Up Sampling-based Zipformer for Monaural Speech Enhancement
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929668176740352 |
|---|---|
| author | Wang, Haoxu Tian, Biao |
| author_facet | Wang, Haoxu Tian, Biao |
| contents | In contrast to other sequence tasks modeling hidden layer features with three axes, Dual-Path time and time-frequency domain speech enhancement models are effective and have low parameters but are computationally demanding due to their hidden layer features with four axes. We propose ZipEnhancer, which is Dual-Path Down-Up Sampling-based Zipformer for Monaural Speech Enhancement, incorporating time and frequency domain Down-Up sampling to reduce computational costs. We introduce the ZipformerBlock as the core block and propose the design of the Dual-Path DownSampleStacks that symmetrically scale down and scale up. Also, we introduce the ScaleAdam optimizer and Eden learning rate scheduler to improve the performance further. Our model achieves new state-of-the-art results on the DNS 2020 Challenge and Voicebank+DEMAND datasets, with a perceptual evaluation of speech quality (PESQ) of 3.69 and 3.63, using 2.04M parameters and 62.41G FLOPS, outperforming other methods with similar complexity levels. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_05183 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ZipEnhancer: Dual-Path Down-Up Sampling-based Zipformer for Monaural Speech Enhancement Wang, Haoxu Tian, Biao Sound Audio and Speech Processing In contrast to other sequence tasks modeling hidden layer features with three axes, Dual-Path time and time-frequency domain speech enhancement models are effective and have low parameters but are computationally demanding due to their hidden layer features with four axes. We propose ZipEnhancer, which is Dual-Path Down-Up Sampling-based Zipformer for Monaural Speech Enhancement, incorporating time and frequency domain Down-Up sampling to reduce computational costs. We introduce the ZipformerBlock as the core block and propose the design of the Dual-Path DownSampleStacks that symmetrically scale down and scale up. Also, we introduce the ScaleAdam optimizer and Eden learning rate scheduler to improve the performance further. Our model achieves new state-of-the-art results on the DNS 2020 Challenge and Voicebank+DEMAND datasets, with a perceptual evaluation of speech quality (PESQ) of 3.69 and 3.63, using 2.04M parameters and 62.41G FLOPS, outperforming other methods with similar complexity levels. |
| title | ZipEnhancer: Dual-Path Down-Up Sampling-based Zipformer for Monaural Speech Enhancement |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2501.05183 |