Download Evaluating Dynamic Range Compressor Models Using Control-Voltage Measurements: An Approach and Dataset The quantity that defines the behavior of a dynamic range compressor is the time-varying gain applied to the signal as a function of the input level. However, models of these devices are typically evaluated using proxy metrics because isolating the gain reduction signal from the audio input–output data included in existing datasets creates an ill-conditioned inverse problem. It is unclear how accurately these metrics describe the behavior the model is tasked with emulating, particularly as waveform-based metrics can be influenced by secondary effects introduced by analog processing and capture, even when those effects are inaudible. We investigate a method of evaluation in which the gain-reduction signal produced by a model is measured directly against a gain-reduction control voltage signal produced by the hardware. To evaluate the efficacy of this metric as a learning objective, a gray-box model is trained using loss computed directly over the gain control signals alongside two models trained using common proxy losses. The models trained using proxy losses did not achieve parity with models trained directly on the gain control signal when evaluated with respect to the underlying control trajectory, and the waveform-domain metrics assigned similar errors to models that were clearly separated by the direct metric. To facilitate further exploration of this method of evaluation, we present a Solid State Logic bus compressor dataset that includes the gain control voltage signal captured alongside the audio output.
Download Robust Recovery of Deterministic Timecode Signals Under Analog Degradation This paper presents a controlled evaluation framework for recovering deterministic stereo timecode waveforms used in digital vinyl systems. Three lightweight decoding policies are compared: Fixed-Threshold Symbol Decoder (FTSD), Adaptive-Threshold Symbol Decoder (ATSD), and State-Constrained Temporal Decoder (SCTD). The work provides matched comparison and explicit separation of availability, reference-relative correctness, and temporal behavior across noise, dropout, and clipping conditions.
Download Real-Time Neural Audio on Apple Silicon: Benchmarking Inference Frameworks Under Realistic DAW Contention Neural network models are increasingly deployed in audio plugins across a wide range of applications, including amplifier emulation, effects modeling, and synthesis. This paper evaluates widely used inference options including BNNSGraph, RTNeural, LibTorch, ONNX Runtime, and anira on model architectures commonly used in neural audio plugins. The key contribution is moving beyond isolated benchmarks to evaluate performance under realistic DAW contention, constructing mix sessions with configurable plugin loads. Results show that isolated benchmarks can be misleading, and BNNSGraph proves most robust for convolutional models on Apple Silicon.
Download Benchmarking Integrated GPU Acceleration of Real-Time Neural Audio Inference on Snapdragon This paper investigates whether integrated GPUs on Qualcomm Snapdragon SoCs can accelerate streaming inference of neural audio models. Five models spanning three orders of magnitude in parameter count are benchmarked across three inference approaches (best available CPU, QNN CPU, and QNN GPU). Results reveal when GPU acceleration offers meaningful gains, when per-call overhead negates benefits, and how model size and architecture determine GPU suitability.
Download Perceptually Motivated Alignment and Interpolation of Pitch-Aligned Time-Frequency Representations This paper proposes methods for alignment and interpolation of pitch-aligned time-frequency representations, building on the tonal interval vector. Extensions reformulate it as an invertible operator, enabling alignment via permutation search under perceptually weighted distances and interpolation via optimal transport with a circular formulation respecting harmonic structure. The work also develops a geometric scale representation factorizing scale structure into root, density, and color.
Download Probing Low-Level Acoustic Attribute Encoding in CLAP Audio Embeddings This work analyzes CLAP audio embeddings through a probing framework, studying the encoding of reverberation (RT60), loudness (LUFS), spectral content (SC), and relative pitch (RP). Results show that all attributes are reliably recoverable from CLAP embeddings, with RT60, LUFS, and RP approximately linearly encoded, while SC requires non-linear probes. The identified patterns generalize across eight additional audio foundation models.