Paper Archive

Neural networks have been applied within the Wave Digital Filter (WDF) framework as data-driven models for nonlinear multi-port circuit elements. Conventionally, these models are trained on wave variables obtained by sampling the current-voltage characteristic of the considered nonlinear element before being incorporated into the circuit WDF implementation. However, isolating multi-port elements for this process can be challenging, as their nonlinear behavior often depends on dynamic effects that emerge from interactions with the surrounding circuit. In this paper, we propose a novel approach for training neural models of nonlinear multi-port elements directly within a circuit’s Wave Digital (WD) discretetime implementation, relying solely on circuit input-output voltage measurements. Exploiting the differentiability of WD simulations, we embed the neural network into the simulation process and optimize its parameters using gradient-based methods by minimizing a loss function defined over the circuit output voltage. Experimental results demonstrate the effectiveness of the proposed approach in accurately capturing the nonlinear circuit behavior, while preserving the interpretability and modularity of WDFs.

Download

This paper addresses the task of lyrics-to-audio alignment, which involves synchronizing textual lyrics with corresponding music audio. Most publicly available datasets for this task provide annotations only at the line or word level. This poses a challenge for training lyrics-to-audio models due to the lack of frame-wise phoneme labels. However, we find that phoneme labels can be partially derived from word-level annotations: for single-phoneme words, all frames corresponding to the word can be labeled with the same phoneme; for multi-phoneme words, phoneme labels can be assigned at the first and last frames of the word. To leverage this partial information, we construct a mask for those frames and propose a masked frame-wise cross-entropy (CE) loss that considers only frames with known phoneme labels. As a baseline model, we adopt an autoencoder trained with a Connectionist Temporal Classification (CTC) loss and a reconstruction loss. We then enhance the training process by incorporating the proposed framewise masked CE loss. Experimental results show that incorporating the frame-wise masked CE loss improves alignment performance. In comparison to other state-of-the art models, our model provides a comparable Mean Absolute Error (MAE) of 0.216 seconds and a top Median Absolute Error (MedAE) of 0.041 seconds on the testing Jamendo dataset.

Download

Audio effects and sound synthesizers are widely used processors in popular music. Their parameters control the quality of the output sound. Multiple combinations of parameters can lead to the same sound. While recent approaches have been proposed to estimate these parameters given only the output sound, those are deterministic, i.e. they only estimate a single solution among the many possible parameter configurations. In this work, we propose to model the parameters as probability distributions instead of deterministic values. To learn the distributions, we optimize two objectives: (1) we minimize the reconstruction error between the ground truth output sound and the one generated using the estimated parameters, asisit usuallydone, but also(2)we maximize the parameter diversity, using entropy. We evaluate our approach through two numerical audio experiments to show its effectiveness. These results show how our approach effectively outputs multiple combinations of parameters to match one sound.

Download

This paper presents a novel approach to neural instrument sound synthesis using a two-stage semi-supervised learning framework capable of generating pitch-accurate, high-quality music samples from an expressive timbre latent space. Existing approaches that achieve sufficient quality for music production often rely on highdimensional latent representations that are difficult to navigate and provide unintuitive user experiences. We address this limitation through a two-stage training paradigm: first, we train a pitchtimbre disentangled 2D representation of audio samples using a Variational Autoencoder; second, we use this representation as conditioning input for a Transformer-based generative model. The learned 2D latent space serves as an intuitive interface for navigating and exploring the sound landscape. We demonstrate that the proposed method effectively learns a disentangled timbre space, enabling expressive and controllable audio generation with reliable pitch conditioning. Experimental results show the model’s ability to capture subtle variations in timbre while maintaining a high degree of pitch accuracy. The usability of our method is demonstrated in an interactive web application, highlighting its potential as a step towards future music production environments that are both intuitive and creatively empowering: https://pgesam.faresschulz.com/.

Download

The snoring noise can be extremely annoying and can negatively affect people’s social lives. To reduce this problem, active noise control (ANC) systems can be adopted for snoring cancellation. Recently, adaptive subband systems have been developed to improve the convergence rate and reduce the computational complexity of the ANC algorithm. Several structures have been proposed with different approaches. This paper proposes a non-uniform subband adaptive filtering (SAF) structure to improve a feedforward active noise control algorithm. The non-uniform band distribution allows for a higher frequency resolution of the lower frequencies, where the snoring noise is most concentrated. Several experiments have been carried out to evaluate the proposed system in comparison with a reference ANC system which uses a uniform approach.

Download

Traditional screen-based graphical user interfaces (GUIs) pose significant accessibility challenges for visually impaired users. This paper demonstrates how existing GUI elements can be translated into an interactive auditory domain using high-order Ambisonics and inertial sensor-based head tracking, culminating in a realtime binaural rendering over headphones. The proposed system is designed to spatialize the auditory output from VoiceOver, the built-in macOS screen reader, aiming to foster clearer mental mapping and enhanced navigability. A between-groups experiment was conducted to compare standard VoiceOver with the proposed spatialized version. Non visually-impaired participants (n = 32), with no visual access to the test interface, completed a list-based exploration and then attempted to reconstruct the UI solely from auditory cues. Experimental results indicate that the head-tracked group achieved a slightly higher accuracy in reconstructing the interface, while user experience assessments showed no significant differences in self-reported workload or usability. These findings suggest that potential benefits may come from the integration of head-tracked binaural audio into mainstream screen-reader workflows, but future investigations involving blind and low-vision users are needed. Although the experimental testbed uses a generic desktop app, our ultimate goal is to tackle the complex visual layouts of music-production software, where an head-tracked audio approach could benefit visually impaired producers and musicians navigating plug-in controls.

Download

For their low and constant computational cost, non-iterative methods for the solution of differential problems are gaining popularity in virtual analog provided their stability properties and accuracy level afford their use at no exaggerate temporal oversampling. At least in some application case studies, one recent family of noniterative schemes has shown promise to outperform methods that achieve accurate results at the cost of iterating several times while converging to the numerical solution. Here, this family is contextualized and studied against known classes of non-iterative methods. The results from these studies foster a more general discussion about the possibilities, role and prospective use of non-iterative methods in virtual analog.

Download

In this paper, we present an approach to the neural modeling of overdrive guitar pedals with conditioning from a cross-circuit and cross-setting latent space. The resulting network models the behavior of multiple overdrive pedals across different settings, offering continuous morphing between real configurations and hybrid behaviors. Compact conditioning spaces are obtained through unsupervised training of a variational autoencoder with adversarial training, resulting in accurate reconstruction performance across different sets of pedals. We then compare three Hyper-Recurrent architectures for processing, including dynamic and static HyperRNNs, and a smaller model for real-time processing. Additionally, we present pOD-set, a new open dataset including recordings of 27 analog overdrive pedals, each with 36 gain and tone parameter combinations totaling over 97 hours of recordings. Precise parameter setting was achieved through a custom-deployed recording robot.

Download

This study investigates the use of an unsupervised, physicsinformed deep learning framework to model a one-degree-offreedom mass-spring system subjected to a nonlinear friction bow force and governed by a set of ordinary differential equations. Specifically, it examines the application of Physics-Informed Neural Networks (PINNs) and Physics-Informed Deep Operator Networks (PI-DeepONets). Our findings demonstrate that PINNs successfully address the problem across different bow force scenarios, while PI-DeepONets perform well under low bow forces but encounter difficulties at higher forces. Additionally, we analyze the Hessian eigenvalue density and visualize the loss landscape. Overall, the presence of large Hessian eigenvalues and sharp minima indicates highly ill-conditioned optimization. These results underscore the promise of physics-informed deep learning for nonlinear modelling in musical acoustics, while also revealing the limitations of relying solely on physics-based approaches to capture complex nonlinearities. We demonstrate that PI-DeepONets, with their ability to generalize across varying parameters, are well-suited for sound synthesis. Furthermore, we demonstrate that the limitations of PI-DeepONets under higher forces can be mitigated by integrating observation data within a hybrid supervised-unsupervised framework. This suggests that a hybrid supervised-unsupervised DeepONets framework could be a promising direction for future practical applications.

Download

We present a spline-based method for compressing and reconstructing Head-Related Transfer Functions (HRTFs) that preserves perceptual quality. Our approach focuses on the magnitude response and consists of four stages: (1) acquiring minimumphase head-related impulse responses (HRIR), (2) transforming them into the frequency domain and applying adaptive Wiener filtering to preserve important spectral features, (3) extracting a minimal set of control points using derivative-based methods to identify local maxima and inflection points, and (4) reconstructing the HRTF using piecewise cubic Hermite interpolation (PCHIP) over the refined control points. Evaluation on 301 subjects demonstrates that our method achieves an average compression ratio of 4.7:1 with spectral distortion ≤ 1.0 dB in each Equivalent Rectangular Band (ERB). The method preserves binaural cues with a mean absolute interaural level difference (ILD) error of 0.10 dB. Our method achieves about three times the compression obtained with a PCA-based method.

Download