Efficient Audio Super-Resolution with a Differentiable Psychoacoustic Loss

Audio super-resolution is commonly seen as the task of enhancing low-bitrate audio signals by creating missing high-frequency content. This work proposes AEROMamba-PAQM, an efficient variant of the AERO super-resolution architecture where attention and LSTM layers are replaced by the Mamba state-space model, and which incorporates a newly developed differentiable perceptual loss derived from the Perceptual Audio Quality Measure (PAQM). During training, the architecture requires approximately 2–4x less GPU memory than the baseline; during inference, it achieves a 14x speedup while using only 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 AEROMamba-PAQM outperforms AERO by 15% in perceived quality scores. To address the broader problem of improving audio that has been highly compressed by lossy coding, it is further proposed AEROMamba-PAQM++, which applies the same framework but replaces STFT reconstruction losses with the PAQM loss, specifically to enhance MP3 encoded audio at 32 kbps. In listening evaluations, AEROMamba-PAQM++ achieves 52% higher quality rating than AEROMamba-PAQM 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.

Objective and subjective scores for low-bitrate (MP3 32kbps) signals and various models evaluated on MUSDB and PianoEval.

Subjective Score Distributions

MUSDB

PianoEval