DeePAQ: A Perceptual Audio Quality Metric Based On Foundational Models and Weakly Supervised Learning
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_ | 1866908591940698112 |
|---|---|
| author | Jiang, Guanxin Brendel, Andreas Delgado, Pablo M. Herre, Jürgen |
| author_facet | Jiang, Guanxin Brendel, Andreas Delgado, Pablo M. Herre, Jürgen |
| contents | This paper presents the Deep learning-based Perceptual Audio Quality metric (DeePAQ) for evaluating general audio quality. Our approach leverages metric learning together with the music foundation model MERT, guided by surrogate labels, to construct an embedding space that captures distortion intensity in general audio. To the best of our knowledge, DeePAQ is the first in the general audio quality domain to leverage weakly supervised labels and metric learning for fine-tuning a music foundation model with Low-Rank Adaptation (LoRA), a direction not yet explored by other state-of-the-art methods. We benchmark the proposed model against state-of-the-art objective audio quality metrics across listening tests spanning audio coding and source separation. Results show that our method surpasses existing metrics in detecting coding artifacts and generalizes well to unseen distortions such as source separation, highlighting its robustness and versatility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_12326 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DeePAQ: A Perceptual Audio Quality Metric Based On Foundational Models and Weakly Supervised Learning Jiang, Guanxin Brendel, Andreas Delgado, Pablo M. Herre, Jürgen Audio and Speech Processing This paper presents the Deep learning-based Perceptual Audio Quality metric (DeePAQ) for evaluating general audio quality. Our approach leverages metric learning together with the music foundation model MERT, guided by surrogate labels, to construct an embedding space that captures distortion intensity in general audio. To the best of our knowledge, DeePAQ is the first in the general audio quality domain to leverage weakly supervised labels and metric learning for fine-tuning a music foundation model with Low-Rank Adaptation (LoRA), a direction not yet explored by other state-of-the-art methods. We benchmark the proposed model against state-of-the-art objective audio quality metrics across listening tests spanning audio coding and source separation. Results show that our method surpasses existing metrics in detecting coding artifacts and generalizes well to unseen distortions such as source separation, highlighting its robustness and versatility. |
| title | DeePAQ: A Perceptual Audio Quality Metric Based On Foundational Models and Weakly Supervised Learning |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2510.12326 |