EUVIMEDEUVIMED entdecken
Crossref

Efficient Audio Enhancement With a Differentiable Psychoacoustic Loss

Wallace Abreu, Bernardo V. Miranda, Luiz W. P. Biscainho

Journal of the Audio Engineering Society · 09.06.2026 · 74 (6) · 430-444

DOI: 10.17743/jaes.2022.0277 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the Audio Engineering Society, online erschienen am 09.06.2026. Verfasst von Wallace Abreu und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Audio enhancement aims to improve the perceived quality of audio signals. Initially, to address bandwidth extension, this work proposes AEROMambaP, an efficient variant of the AERO super-resolution architecture in which attention and long short-term memory layers are replaced by the Mamba state-space model, together with a newly developed differentiable perceptual loss derived from the perceptual audio quality measure (PAQM). During training, the architecture requires two to fours times less GPU memory than the baseline; during inference, it achieves a 14× speedup while using one-fifth of the GPU memory. When upsampling both a piano dataset and MUSDB18 from 11.025 kHz to 44.1 kHz, subjective listening tests show that AEROMambaP outperforms AERO by 15% in perceived quality scores. Next, to enhance of audio signals highly compressed by lossy coding, it is further proposed AEROMambaPS̄, which applies the same framework but replaces short-time Fourier transform reconstruction losses with the PAQM loss, specifically to enhance MP3-encoded audio at 32 kbps. In listening evaluations, AEROMambaPS̄ achieves 52% higher quality rating than AEROMambaP when restoring compressed audio. These results demonstrate that PAQM-driven training coupled with lightweight state-space modeling yields high perceptual quality and computational efficiency in both band-limited and compressed audio scenarios.

Zitieren

APA

Abreu, W., Miranda, B. V., & Biscainho, L. W. P. (2026). Efficient Audio Enhancement With a Differentiable Psychoacoustic Loss. Journal of the Audio Engineering Society, 74(6), 430-444. https://doi.org/10.17743/jaes.2022.0277

Vancouver

Abreu W, Miranda BV, Biscainho LWP. Efficient Audio Enhancement With a Differentiable Psychoacoustic Loss. Journal of the Audio Engineering Society. 2026;74(6):430-444. doi:10.17743/jaes.2022.0277

BibTeX
@article{Abreu2026,
  author = {Abreu, Wallace and Miranda, Bernardo V. and Biscainho, Luiz W. P.},
  title = {Efficient Audio Enhancement With a Differentiable Psychoacoustic Loss},
  journal = {Journal of the Audio Engineering Society},
  year = {2026},
  volume = {74},
  number = {6},
  pages = {430--444},
  doi = {10.17743/jaes.2022.0277}
}
Kostenlos starten →