HiFi-Stream: Streaming Speech Enhancement with Generative Adversarial Networks
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_ | 1866911071474810880 |
|---|---|
| author | Dmitrieva, Ekaterina Kaledin, Maksim |
| author_facet | Dmitrieva, Ekaterina Kaledin, Maksim |
| contents | Speech Enhancement techniques have become core technologies in mobile devices and voice software. Still, modern deep learning solutions often require high amount of computational resources what makes their usage on low-resource devices challenging. We present HiFi-Stream, an optimized version of recently published HiFi++ model. Our experiments demonstrate that HiFi-Stream saves most of the qualities of the original model despite its size and computational complexity improved in comparison to the original HiFi++ making it one of the smallest and fastest models available. The model is evaluated in streaming setting where it demonstrates its superior performance in comparison to modern baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_17141 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HiFi-Stream: Streaming Speech Enhancement with Generative Adversarial Networks Dmitrieva, Ekaterina Kaledin, Maksim Sound Machine Learning Audio and Speech Processing Speech Enhancement techniques have become core technologies in mobile devices and voice software. Still, modern deep learning solutions often require high amount of computational resources what makes their usage on low-resource devices challenging. We present HiFi-Stream, an optimized version of recently published HiFi++ model. Our experiments demonstrate that HiFi-Stream saves most of the qualities of the original model despite its size and computational complexity improved in comparison to the original HiFi++ making it one of the smallest and fastest models available. The model is evaluated in streaming setting where it demonstrates its superior performance in comparison to modern baselines. |
| title | HiFi-Stream: Streaming Speech Enhancement with Generative Adversarial Networks |
| topic | Sound Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2503.17141 |