Hybrid Real- And Complex-Valued Neural Network Concept For Low-Complexity Phase-Aware Speech Enhancement
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914056585084928 |
|---|---|
| author | Fiorio, Luan Vinícius Young, Alex Aarts, Ronald M. |
| author_facet | Fiorio, Luan Vinícius Young, Alex Aarts, Ronald M. |
| contents | In this paper, we propose hybrid real- and complex-valued neural networks for speech enhancement. Real- or complex-valued models are either inefficient or present high complexity. We devise a straightforward design method for extending a real-valued network into its hybrid counterpart. Based on speech intelligibility and quality metrics, we compare the real, complex, and hybrid versions of a convolutional and a convolutional-recurrent architecture. The hybrid network consistently outperforms its counterparts with the same number of parameters. Additionally, the hybrid models' complexity in terms of multiply-accumulate operations is substantially lower than that of their counterparts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21185 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hybrid Real- And Complex-Valued Neural Network Concept For Low-Complexity Phase-Aware Speech Enhancement Fiorio, Luan Vinícius Young, Alex Aarts, Ronald M. Audio and Speech Processing In this paper, we propose hybrid real- and complex-valued neural networks for speech enhancement. Real- or complex-valued models are either inefficient or present high complexity. We devise a straightforward design method for extending a real-valued network into its hybrid counterpart. Based on speech intelligibility and quality metrics, we compare the real, complex, and hybrid versions of a convolutional and a convolutional-recurrent architecture. The hybrid network consistently outperforms its counterparts with the same number of parameters. Additionally, the hybrid models' complexity in terms of multiply-accumulate operations is substantially lower than that of their counterparts. |
| title | Hybrid Real- And Complex-Valued Neural Network Concept For Low-Complexity Phase-Aware Speech Enhancement |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2509.21185 |