Download Fourier Neural Operators for Sample-Rate-Independent Virtual Analog Modeling Neural networks that operate directly on time-domain signals are widely used for virtual analog (VA) modeling. A key limitation of these models is their dependence on the sampling rate used during training, which becomes implicitly encoded in the learned parameters, so that changing it generally alters the realized dynamics. Although architectural modifications to recurrent neural networks have been proposed to enable sample-rate independent operation, these approaches are inherently tailored to upsampling and do not accommodate downsampling scenarios. In this manuscript, we present a VA modeling framework based on Fourier Neural Operators (FNOs) adapted to process fixed-duration audio frames. The proposed formulation defines the learned mapping over a fixed temporal support and evaluates it on uniform grids of different densities, so that a model trained at a single sampling rate can be applied at unseen sampling resolutions. Numerical results on a nonlinear transistor circuit show that the proposed model achieves competitive accuracy in upsampling scenarios while remaining directly applicable to downsampling, unlike a sample-rate independent baseline recurrent architecture.
Download Deep Regularized RNNs for Virtual Analog Virtual analog (VA) modeling methods seek to emulate analog audio hardware using digital signal processing (DSP). Modeling approaches fall into three broad categories: white-box methods, which use detailed device knowledge for accurate simulation; gray-box methods that use generic DSP blocks to model the system; and black-box methods, which rely solely on opaque models learned from input–output data. A category of architectures used widely in black-box modeling are recurrent neural networks (RNNs). To model device controls, the control values can be provided as conditioning input to the network. However, when the conditioning is time-varied, the models are susceptible to producing noise artifacts. Regularization of the RNN dynamics significantly reduces these artifacts, though at a loss in modeling accuracy. This paper closes the dynamics regularization quality gap by introducing deep control-conditioned LSTMs and a gammatone filterbank (GFB) loss. Experiments indicate that the proposed method achieves comparable modeling performance as unregularized baselines while avoiding the noise artifacts caused by time-varying control inputs.
Download FM Parameter Estimation with Low-Order Rational Constraints on Wasserstein Loss Landscape Frequency modulation (FM) synthesis has been widely used in music production and sound design due to its ability to generate rich timbres with few control parameters. However, estimating the frequency parameters from a target sound remains challenging because different parameter configurations can yield similar spectra, creating numerous local minima in the loss landscape. In this paper, we analyze the Wasserstein distance loss landscape for two-operator FM synthesis under practical FFT-based spectral representations and show that it exhibits non-differentiable ridges at rational frequency ratios, arising from negative-frequency folding and spectral ordering transitions. Exploiting this structure, we propose a constrained gradient-based optimization strategy that constrains the frequency ratio in each optimization run to an interval bounded by consecutive low-order rational ratios and retains the lowest-loss candidate across intervals. Experimental results from controlled ablations show that maintaining the constraint throughout optimization improves reliability over random initialization and initialization-only constraints, particularly for more complex spectra at higher modulation indices.
Download Enhancing Automatic Chord Recognition via Pseudo-Labeling and Knowledge Distillation Automatic Chord Recognition (ACR) is constrained by the scarcity of aligned chord annotations, which are costly to acquire. At the same time, open-weight pre-trained models are more accessible than their proprietary training data. In this work, we present a two-stage training pipeline that leverages pre-trained models together with unlabeled audio. The proposed method decouples training into two stages. In the first stage, we use the pre-trained BTC model as a teacher to generate pseudo-labels for over 1,000 hours of diverse unlabeled audio and train a student model solely on these pseudo-labels. In the second stage, the student is continually trained on ground-truth labels as they become available. To prevent catastrophic forgetting of the representations learned in the first stage, we apply selective knowledge distillation (KD) from the teacher as a regularizer. In our experiments, two models (BTC, 2E1D) were used as students. In Stage 1, using only pseudo-labels, the BTC student achieves about 99% of the teacher's performance, while the 2E1D model achieves about 97% of the teacher's performance across seven standard mir_eval metrics. After continual training with labeled data in Stage 2, the resulting BTC student model consistently surpasses both the traditional supervised learning baseline and the original pre-trained teacher model across all metrics. The resulting 2E1D student model also outperforms the supervised baseline and approaches teacher-level performance, with both models demonstrating substantial gains on rare chord qualities.
Download A Perceptually Inspired Single Parameter Auditory Distance Renderer for Music Production Conveying auditory distance in a digital audio workstation requires balancing several uncoupled tools (reverb, gain, equalization, pre-delay) by hand, a workflow that is cognitively demanding and easily produces spatially incoherent results. We demonstrate a real-time VST3 plugin that derives five correlated distance cues from a single normalized control and keeps them mutually coherent by construction, grounded in the psychoacoustics of auditory distance perception. A headphone listening test with 18 participants showed that the coupled renderer roughly halves distance placement error relative to an uncoupled manual mix and was unanimously preferred on composite spatial quality. Users sweep one knob and hear sources move convincingly from near to far on multitrack material, compare the result against a manual uncoupled mix, and toggle an optional binaural externalization stage. Source code is available on GitHub.
Download IRIS: Continuous Spatial Navigation of Measured Acoustic Fields via Impulse Response Interpolation Impulse response (IR) collections are useful in virtual acoustics, sound design, and field-based acoustic research, but they remain difficult to explore as continuous resources in lightweight real-time plugin workflows. This demo paper presents IRIS, a VST3 plugin for arranging, navigating, and auditioning measured or user-defined IR collections in a two-dimensional navigation plane. Each IR is represented as a node whose position can be imported from metadata or assigned manually. During navigation, nearby responses are combined using Gaussian distance-based weighting, while a bounded active set limits the number of simultaneous convolutions. The system also includes smoothing, hysteresis, optional preprocessing, boundary attenuation, OSC control, and coupled multichannel handling. The demo focuses on workflow and audible behavior rather than perceptual validation. A short timing characterization reports practical real-time limits as a function of IR length, buffer size, and active-set size. IRIS is presented as a practical tool for exploratory, analytical, and creative navigation of IR collections rather than as a physically optimal interpolation method.
Download FDN Sandbox: Real-Time Experimentation and Analysis of FDNs This work presents sfFDN, a modular and real-time-capable C++ library for Feedback Delay Networks (FDNs), together with the companion FDN Sandbox application designed for interactive experimentation, analysis, and parameter optimization. The library implements the canonical FDN as well as several recent extensions, including filter feedback matrices, velvet-noise decorrelation filters, and two-stage graphic equalizers for attenuation and tone correction. The Sandbox application exposes these features through a graphical interface, providing a suite of real-time visualizations, as well as an optimization framework supporting nine algorithms from the ensmallen library, with built-in loss functions for both colorless reverberation and room impulse response matching. Both the library and the application are open-source.
Download A Frequency-Domain Reverberator Plug-In We present FDverb, a frequency-domain artificial reverberator, based on the idea of a vocoder with a noise carrier signal. Using a short-time Fourier transform (STFT) for analysis and synthesis, FDverb generates late reverberation by weighting spectral noise components with envelopes. We extend FDverb with early reflections, nonlinear decay, and pitch shifting. These extensions enable creative sound-design applications. We provide FDverb as an open-source DAW plug-in, using the JUCE framework.
Download Bunkervik Spatial Reverb Demo This paper accompanies a demonstration of a real-time audio plug-in for a dynamic spatial reverb. The reverb is based on acoustic measurements of the Bunkervik creative arts space in Brescia, Italy. A modal synthesis reverberation engine was created based on measured impulse responses from three locations in the tunnel. Using a common set of modal frequencies the position of the receiver can be dynamically moved through the space by interpolating between data sets of residue weights and FIR filter taps. The audio plug-in also allows real-time manipulation of the high-frequency content, damping, and microphone rotation, all of which can be modulated using two LFOs.
Download Pulsetable Synthesis of Wind Instrument Tones We revisit pulsetable synthesis, an efficient technique for generating plausible and expressive wind instrument tones. Based on the principles of pulse forming theory, this method models sound production as the periodic repetition of shaped pulses characterizing the target instruments' spectral envelope. In this approach, single-cycle waveforms, referred to as pulses, are stored in pulsetables indexed by their corresponding fundamental frequency. During synthesis, the pulses are read from these tables to form a periodic waveform, which is further shaped by time-varying low-pass filtering, amplification, and reverberation. These processes are guided by control signal contours that describe how fundamental frequency, brightness, and loudness evolve over time. Through case studies with real-world wind instrument recordings, we show how the interplay between these control signals gives rise to articulations such as attack transients, vibrato, and growl. Finally, we discuss the potential of this framework for integration into Differentiable Digital Signal Processing (DDSP) models, where neural networks could learn synthesis parameters directly from training data.