EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Benchmarking Objective Quality Metrics for Audio Generation and Restoration: A Comprehensive Analysis

Estelle Mercier, Anna Clifford, Bertrand Dean, Doyun Choi

International Journal of Information and Communication Technology Trends · 05.05.2026 · 6 (1) · 239-247

DOI: 10.66525/ijictt88 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Information and Communication Technology Trends, online erschienen am 05.05.2026. Verfasst von Estelle Mercier und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid advancement of deep learning technologies has fundamentally transformed the fields of audio generation and restoration, enabling the synthesis of highly realistic speech, music, and environmental sounds, as well as the sophisticated recovery of degraded audio signals. However, the evaluation of these advanced systems remains a significant bottleneck. Subjective evaluation, predominantly through Mean Opinion Score testing, is considered the gold standard for assessing perceptual audio quality. Yet, it is inherently expensive, time-consuming, and susceptible to various human biases, rendering it impractical for the rapid and iterative development cycles typical of modern machine learning research. Consequently, there is a critical need for robust, reliable, and scalable objective quality metrics. This paper presents a comprehensive benchmarking of existing objective quality metrics, spanning traditional digital signal processing approaches to contemporary neural embedding-based distances. By evaluating these metrics across a diverse and extensive dataset comprising both generated and restored audio under multiple degradation conditions, we systematically analyze their correlation with human subjective judgments. Our findings indicate a pronounced divergence in metric efficacy depending on the specific task. Traditional metrics often fail to capture the perceptual fidelity of generative models, heavily penalizing realistic but unaligned synthesized content. Conversely, neural metrics demonstrate superior alignment with human perception in generative tasks but exhibit vulnerabilities to specific spectral artifacts in restoration scenarios. The analysis highlights the necessity for task-specific metric selection and underscores the imperative for developing next-generation hybrid evaluation frameworks that integrate psychoacoustic principles with deep feature representations

Zitieren

APA

Mercier, E., Clifford, A., Dean, B., & Choi, D. (2026). Benchmarking Objective Quality Metrics for Audio Generation and Restoration: A Comprehensive Analysis. International Journal of Information and Communication Technology Trends, 6(1), 239-247. https://doi.org/10.66525/ijictt88

Vancouver

Mercier E, Clifford A, Dean B, Choi D. Benchmarking Objective Quality Metrics for Audio Generation and Restoration: A Comprehensive Analysis. International Journal of Information and Communication Technology Trends. 2026;6(1):239-247. doi:10.66525/ijictt88

BibTeX
@article{Mercier2026,
  author = {Mercier, Estelle and Clifford, Anna and Dean, Bertrand and Choi, Doyun},
  title = {Benchmarking Objective Quality Metrics for Audio Generation and Restoration: A Comprehensive Analysis},
  journal = {International Journal of Information and Communication Technology Trends},
  year = {2026},
  volume = {6},
  number = {1},
  pages = {239--247},
  doi = {10.66525/ijictt88}
}
Kostenlos starten →