AEROMamba: An efficient architecture for audio super-resolution using generative adversarial networks and state space models

Audio super-resolution aims to enhance low-resolution signals by creating high-frequency content. In this work, we modify the architecture of AERO (a state-of-the-art system for this task) for music super-resolution. SPecifically, we replace its original Attention and LSTM layers with Mamba, a State Space Model (SSM), across all network layers. Mamba is capable of effectively substituting the mentioned modules, as it offers a mechanism similar to that of Attention while also functioning as a recurrent network. With the proposed AEROMamba, training requires 2-4x less GPU memory, since Mamba exploits the convolutional formulation and leverages GPU memory hierarchy. Additionally, during inference, Mamba operates in constant memory due to recurrence, avoiding memory growth associated with Attention. This results in a 14x speed improvement using 5x less GPU. Subjective listening tests (0 to 100 scale) show that the proposed model surpasses the AERO model. In the MUSDB dataset, degraded signals scored 38.22, while AERO and AEROMamba scored 60.03 and 66.74, respectively. For the PianoEval dataset, scores were 72.92 for degraded signals, 76.89 for AERO, and 84.41 for AEROMamba.

We collected the PianoEval data set, which consists of two parts. The first is composed of the 24 Preludes for Piano, op. 28, by Chopin performed by 33 pianists in 45 different recordings available on CD (Compact Disc), totaling approximately 22 hours. The second part contains excerpts of Ligeti piano études, a Schumann sonata, and the Barber sonata, played by three different performers, respectively, totaling approximately 3.5 hours. Each file is stored in WAV format, stereo mode and sampled at 44.1 kHz. Information about performers, record label and year of recording are detailed in the Tables below.