DeePAQ: A Perceptual Audio Quality Metric Based on Foundational Models and Weakly Supervised Learning

Jiang G, Brendel A, Delgado P, Herre J (2026)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2026

Publisher: IEEE

Pages Range: 14467-14471

Event location: Barcelona

DOI: 10.1109/ICASSP55912.2026.11465130

Authors with CRIS profile

Guanxin Jiang Lehrstuhl für Audiocodierung (AudioLabs) Pablo Delgado International Audio Laboratories Erlangen (AudioLabs) Jürgen Herre Lehrstuhl für Audiocodierung (AudioLabs)

Involved external institutions

Fraunhofer-Institut für Integrierte Schaltungen (IIS) DE Germany (DE)

How to cite

APA:

Jiang, G., Brendel, A., Delgado, P., & Herre, J. (2026). DeePAQ: A Perceptual Audio Quality Metric Based on Foundational Models and Weakly Supervised Learning. In IEEE (Eds.), Proceedings of the 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 14467-14471). Barcelona: IEEE.

MLA:

Jiang, Guanxin, et al. "DeePAQ: A Perceptual Audio Quality Metric Based on Foundational Models and Weakly Supervised Learning." Proceedings of the 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona Ed. IEEE, IEEE, 2026. 14467-14471.

BibTeX: Download