A Hybrid Discriminative and Generative System for Universal Speech Enhancement
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912851757629440 |
|---|---|
| author | Liu, Yinghao Liu, Chengwei Liang, Xiaotao Yan, Haoyin Xue, Shaofei Xue, Zheng |
| author_facet | Liu, Yinghao Liu, Chengwei Liang, Xiaotao Yan, Haoyin Xue, Shaofei Xue, Zheng |
| contents | Universal speech enhancement aims at handling inputs with various speech distortions and recording conditions. In this work, we propose a novel hybrid architecture that synergizes the signal fidelity of discriminative modeling with the reconstruction capabilities of generative modeling. Our system utilizes the discriminative TF-GridNet model with the Sampling-Frequency-Independent strategy to handle variable sampling rates universally. In parallel, an autoregressive model combined with spectral mapping modeling generates detail-rich speech while effectively suppressing generative artifacts. Finally, a fusion network learns adaptive weights of the two outputs under the optimization of signal-level losses and the comprehensive Speech Quality Assessment (SQA) loss. Our proposed system is evaluated in the ICASSP 2026 URGENT Challenge (Track 1) and ranks the third place. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_19113 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Hybrid Discriminative and Generative System for Universal Speech Enhancement Liu, Yinghao Liu, Chengwei Liang, Xiaotao Yan, Haoyin Xue, Shaofei Xue, Zheng Sound Audio and Speech Processing Universal speech enhancement aims at handling inputs with various speech distortions and recording conditions. In this work, we propose a novel hybrid architecture that synergizes the signal fidelity of discriminative modeling with the reconstruction capabilities of generative modeling. Our system utilizes the discriminative TF-GridNet model with the Sampling-Frequency-Independent strategy to handle variable sampling rates universally. In parallel, an autoregressive model combined with spectral mapping modeling generates detail-rich speech while effectively suppressing generative artifacts. Finally, a fusion network learns adaptive weights of the two outputs under the optimization of signal-level losses and the comprehensive Speech Quality Assessment (SQA) loss. Our proposed system is evaluated in the ICASSP 2026 URGENT Challenge (Track 1) and ranks the third place. |
| title | A Hybrid Discriminative and Generative System for Universal Speech Enhancement |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2601.19113 |