Towards Robust Speech Quality Evaluation in Challenging Acoustic Conditions

Ravizza G. Towards Robust Speech Quality Evaluation in Challenging Acoustic Conditions. In: Express Paper. Audio Engineering Society; 2025. Paper 357. Available from: https://aes.org/publications/elibrary-page/?id=23031

@inproceedings{Ravizza2025_23031,
  author = {Ravizza, Gabriele},
  title = {{Towards Robust Speech Quality Evaluation in Challenging Acoustic Conditions}},
  note = {Paper 357},
  year = {2025},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=23031}
}

TY  - CPAPER
TI  - Towards Robust Speech Quality Evaluation in Challenging Acoustic Conditions
AU  - Ravizza, Gabriele
M1  - Paper 357
PY  - 2025
DA  - 2025/10/14
UR  - https://aes.org/publications/elibrary-page/?id=23031
PB  - Audio Engineering Society
LA  - en
AB  - Assessing speech quality in noisy environments remains a significant challenge for research and development. This study evaluates the robustness of four objective models3QUEST, VISQOL, NISQA, and DNSMOS P.835by comparing their predictions with controlled listening test data from 32 participants. Three perceptual dimensions were analyzed: overall quality (G-MOS), speech quality (S-MOS), and noise intrusiveness (N-MOS). Results show that objective metrics reliably capture overall quality trends across diverse background noise scenarios, with correlations often exceeding 0.9. However, ranking system performance proved less consistent, particularly in complex conditions. Intrusive metrics demonstrated more substantial alignment with speech quality judgments. Higher-order ambisonics noise scenes did not weaken metric reliability. These findings highlight the usefulness of objective metrics for broad evaluation while emphasizing the need for hybrid approaches that incorporate targeted perceptual validation.
ER  -