Uni-VERSA: Versatile Speech Assessment with a Unified Network
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908381213622272 |
|---|---|
| author | Shi, Jiatong Shim, Hye-Jin Watanabe, Shinji |
| author_facet | Shi, Jiatong Shim, Hye-Jin Watanabe, Shinji |
| contents | Subjective listening tests remain the golden standard for speech quality assessment, but are costly, variable, and difficult to scale. In contrast, existing objective metrics, such as PESQ, F0 correlation, and DNSMOS, typically capture only specific aspects of speech quality. To address these limitations, we introduce Uni-VERSA, a unified network that simultaneously predicts various objective metrics, encompassing naturalness, intelligibility, speaker characteristics, prosody, and noise, for a comprehensive evaluation of speech signals. We formalize its framework, evaluation protocol, and applications in speech enhancement, synthesis, and quality control. A benchmark based on the URGENT24 challenge, along with a baseline leveraging self-supervised representations, demonstrates that Uni-VERSA provides a viable alternative to single-aspect evaluation methods. Moreover, it aligns closely with human perception, making it a promising approach for future speech quality assessment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20741 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Uni-VERSA: Versatile Speech Assessment with a Unified Network Shi, Jiatong Shim, Hye-Jin Watanabe, Shinji Sound Audio and Speech Processing Subjective listening tests remain the golden standard for speech quality assessment, but are costly, variable, and difficult to scale. In contrast, existing objective metrics, such as PESQ, F0 correlation, and DNSMOS, typically capture only specific aspects of speech quality. To address these limitations, we introduce Uni-VERSA, a unified network that simultaneously predicts various objective metrics, encompassing naturalness, intelligibility, speaker characteristics, prosody, and noise, for a comprehensive evaluation of speech signals. We formalize its framework, evaluation protocol, and applications in speech enhancement, synthesis, and quality control. A benchmark based on the URGENT24 challenge, along with a baseline leveraging self-supervised representations, demonstrates that Uni-VERSA provides a viable alternative to single-aspect evaluation methods. Moreover, it aligns closely with human perception, making it a promising approach for future speech quality assessment. |
| title | Uni-VERSA: Versatile Speech Assessment with a Unified Network |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2505.20741 |