Paper Archive

This paper describes experiments on sonifying data obtained using the VICON motion capture system. The main goal is to build the necessary infrastructure in order to be able to map motion parameters of the human body to sound. For sonification the following three software frameworks were used: Marsyas, traditionally used for music information retrieval with audio analysis and synthesis, CHUCK, an on-the-fly real-time synthesis language, and Synthesis Toolkit (STK), a toolkit for sound synthesis that includes many physical models of instruments and sounds. An interesting possibility is the use of motion capture data to control parameters of digital audio effects. In order to experiment with the system, different types of motion data were collected. These include traditional performance on musical instruments, acting out emotions as well as data from individuals having impairments in sensor motor coordination. Rhythmic motion (i.e. walking) although complex, can be highly periodic and maps quite naturally to sound. We hope that this work will eventually assist patients in identifying and correcting problems related to motor coordination through sound.

Download

Guitar effects are commonly used in popular music to shape the guitar sound to fit specific genres or to create more variety within musical compositions. The sound is not only determined by the choice of the guitar effect, but also heavily depends on the parameter settings of the effect. This paper introduces a method to estimate the parameter settings of guitar effects, which makes it possible to reconstruct the effect and its settings from an audio recording of a guitar. The method utilizes audio feature extraction and shallow neural networks, which are trained on data created specifically for this task. The results show that the method is generally suited for this task with average estimation errors of ±5% − ±16% of different parameter scales and could potentially perform near the level of a human expert.

Download

In this paper we introduce a simple and fast method for realtime recognition of multiple pitches produced by multiple musical instruments. Our proposed method is based on two important facts: (1) that timbral information of any instrument is pitch-dependant and (2) that the modulation spectrum of the same pitch seems to result into a persistent representation of the characteristics of the instrumental family. Using these basic facts, we construct a learning algorithm to obtain pitch templates of all possible notes on various instruments and then devise an online algorithm to decompose a realtime audio buffer using the learned templates. The learning and decomposition proposed here are inspired by non-negative matrix factorization methods but differ by introduction of an explicit sparsity control. Our test results show promising recognition rates for a realtime system on real music recordings. We discuss further improvements that can be made over the proposed system.

Download

There is an increasing need for automatically classifying sounds for MIR and interactive music applications. In the context of supervised classification, we describe an approach that improves the performance of the general bag-of-frame scheme without loosing its generality. This method is based on the construction and exploitation of specific audio features, called analytical, as input to classifiers. These features are better, in a sense we define precisely than standard, general features, or even than ad hoc features designed by hand for specific problems. To construct these features, our method explores a very large space of functions, by composing basic operators in syntactically correct ways. These operators are taken from the Mathematical and Audio Processing domains. Our method allows us to build a large number of these features, evaluate and select them automatically for arbitrary audio classification problems. We present here a specific study concerning the analysis of Pandeiro (Brazilian tambourine) sounds. Two problems are considered: the classification of entire sounds, for MIR applications, and the classification of attacks portions of the sound only, for interactive music applications. We evaluate precisely the gain obtained by analytical features on these two problems, in comparison with standard approaches.

Download

Sound effect libraries are commonly used by sound designers in a range of industries. Taxonomies exist for the classification of sounds into groups based on subjective similarity, sound source or common environmental context. However, these taxonomies are not standardised, and no taxonomy based purely on the sonic properties of audio exists. We present a method using feature selection, unsupervised learning and hierarchical clustering to develop an unsupervised taxonomy of sound effects based entirely on the sonic properties of the audio within a sound effect library. The unsupervised taxonomy is then related back to the perceived meaning of the relevant audio features.

Download

Latent force models are a Bayesian learning technique that combine physical knowledge with dimensionality reduction — sets of coupled differential equations are modelled via shared dependence on a low-dimensional latent space. Analogously, modal sound synthesis is a technique that links physical knowledge about the vibration of objects to acoustic phenomena that can be observed in data. We apply latent force modelling to sinusoidal models of audio recordings, simultaneously inferring modal synthesis parameters (stiffness and damping) and the excitation or contact force required to reproduce the behaviour of the observed vibrational modes. Exposing this latent excitation function to the user constitutes a controllable synthesis method that runs in real time and enables sound morphing through interpolation of learnt parameters.

Download

We release synth1B1, a multi-modal audio corpus consisting of 1 billion 4-second synthesized sounds, paired with the synthesis parameters used to generate them. The dataset is 100x larger than any audio dataset in the literature. We also introduce torchsynth, an open source modular synthesizer that generates the synth1B1 samples on-the-fly at 16200x faster than real-time (714MHz) on a single GPU. Finally, we release two new audio datasets: FM synth timbre and subtractive synth pitch. Using these datasets, we demonstrate new rank-based evaluation criteria for existing audio representations. Finally, we propose a novel approach to synthesizer hyperparameter optimization.

Download

Controllable timbre synthesis has been a subject of research for several decades, and deep neural networks have been the most successful in this area. Deep generative models such as Variational Autoencoders (VAEs) have the ability to generate a high-level representation of audio while providing a structured latent space. Despite their advantages, the interpretability of these latent spaces in terms of human perception is often limited. To address this limitation and enhance the control over timbre generation, we propose a regularized VAE-based latent space that incorporates timbre descriptors. Moreover, we suggest a more concise representation of sound by utilizing its harmonic content, in order to minimize the dimensionality of the latent space.

Download

Recent advances in data-driven expressive performance rendering have enabled automatic models to reproduce the characteristics and the variability of human performances of musical compositions. However, these models need to be trained with aligned pairs of scores and performances and they rely notably on score-specific markings, which limits their scope of application. This work tackles the piano performance rendering task in a low-informed setting by only considering the score note information and without aligned data. The proposed model relies on an adversarial training where the basic score notes properties are modified in order to reproduce the expressive qualities contained in a dataset of real performances. First results for unaligned score-to-performance rendering are presented through a conducted listening test. While the interpretation quality is not on par with highly-supervised methods and human renditions, our method shows promising results for transferring realistic expressivity into scores.

Download

Conventional Deep Learning (DL) approaches to Infinite Impulse Response (IIR) filter coefficients estimation from arbitrary frequency response are quite limited. They often suffer from inefficiencies such as tight training requirements, high complexity, and limited accuracy. As an alternative, in this paper, we explore the use of Kolmogorov-Arnold Networks (KANs) to predict the IIR filter—specifically biquad coefficients—effectively. By leveraging the high interpretability and accuracy of KANs, we achieve smooth coefficients’ optimization. Furthermore, by constraining the search space and exploring different loss functions, we demonstrate improved performance in speed and accuracy. Our approach is evaluated against other existing differentiable IIR filter solutions. The results show significant advantages of KANs over existing methods, offering steadier convergences and more accurate results. This offers new possibilities for integrating digital infinite impulse response (IIR) filters into deep-learning frameworks.

Download