Neural Vocoders as Speech Enhancers
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913661943021568 |
|---|---|
| author | Li, Andong Sun, Zhihang Hao, Fengyuan Li, Xiaodong Zheng, Chengshi |
| author_facet | Li, Andong Sun, Zhihang Hao, Fengyuan Li, Xiaodong Zheng, Chengshi |
| contents | Speech enhancement (SE) and neural vocoding are traditionally viewed as separate tasks. In this work, we observe them under a common thread: the rank behavior of these processes. This observation prompts two key questions: \textit{Can a model designed for one task's rank degradation be adapted for the other?} and \textit{Is it possible to address both tasks using a unified model?} Our empirical findings demonstrate that existing speech enhancement models can be successfully trained to perform vocoding tasks, and a single model, when jointly trained, can effectively handle both tasks with performance comparable to separately trained models. These results suggest that speech enhancement and neural vocoding can be unified under a broader framework of speech restoration. Code: https://github.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_13465 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Neural Vocoders as Speech Enhancers Li, Andong Sun, Zhihang Hao, Fengyuan Li, Xiaodong Zheng, Chengshi Sound Audio and Speech Processing Speech enhancement (SE) and neural vocoding are traditionally viewed as separate tasks. In this work, we observe them under a common thread: the rank behavior of these processes. This observation prompts two key questions: \textit{Can a model designed for one task's rank degradation be adapted for the other?} and \textit{Is it possible to address both tasks using a unified model?} Our empirical findings demonstrate that existing speech enhancement models can be successfully trained to perform vocoding tasks, and a single model, when jointly trained, can effectively handle both tasks with performance comparable to separately trained models. These results suggest that speech enhancement and neural vocoding can be unified under a broader framework of speech restoration. Code: https://github.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers. |
| title | Neural Vocoders as Speech Enhancers |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2501.13465 |