Paper Archive

In this paper, we approach the problem of atomic decomposition of audio at the symbolic level of atom parameters through the lens of hyperdimensional computing (HDC) – a non-traditional computing paradigm. Existing atomic decomposition algorithms often operate using waveforms from a redundant dictionary of atoms causing them to become increasingly memory/computationally intensive as the signal length grows and/or the atoms become more complicated. We systematically build an atom encoding using vector function architecture (VFA), a field of HDC. We train a neural network encoder on synthetic audio signals to generate these encodings and observe that the network can generalize to real recordings. This system, we call Hyperdimensional Atomic Decomposition (HD-AD), avoids time-domain correlations all together. Because HD-AD scales with the sparsity of the signal, rather than its length in time, atomic decompositions are often produced much faster than real-time.

Download

This paper presents our Task A submission to the 1st DAFx Parameter Estimation Challenge. We use the official ModalPlate dataset generator to synthesize 1000 one-second plate impulse responses with randomly sampled parameters inside the public ranges. A time-domain CNN-GRU regressor then estimates the six official Task A parameters from each unnormalised waveform. The model combines three one-dimensional convolutional blocks with a bidirectional gated recurrent unit and is trained with mean squared error on min-max normalised targets. The generated data are split into 700/150/150 train/validation/test examples, and the test split is never used during training or model selection. The implementation follows the official Task A format and exports evaluation-compatible prediction files for both development evaluation and blind-set submission.

Download

Head-Related Transfer Functions (HRTFs) are one of the main aspects of binaural rendering. By definition, these functions express the deep linkage that exists between hearing and morphology especially of the torso, head and ears. Although the perceptive effects of HRTFs is undeniable, the exact influence of the human morphology is still unclear. Its reduction into few anthropometric measurements have led to numerous studies aiming at establishing a ranking of these parameters. However, no consensus has yet been set. In this paper, we study the influence of the anthropometric measurements of the ear, as defined by the CIPIC database, on the HRTFs. This is done through the computation of HRTFs by Fast Multipole Boundary Element Method (FM-BEM) from a parametric model of torso, head and ears. Their variations are measured with 4 different spectral metrics over 4 frequency bands spanning from 0 to 16kHz. Our contribution is the establishment of a ranking of the selected parameters and a comparison to what has already been obtained by the community. Additionally, a discussion over the relevance of each approach is conducted, especially when it relies on the CIPIC data, as well as a discussion over the CIPIC database limitations.

Download

This paper reports on a new multi-label classification task for guitar effect recognition that is closer to the actual use case of guitar effect pedals. To generate the dataset, we used multiple clean guitar audio datasets and applied various combinations of 13 commonly used guitar effects. We compared four neural network structures: a simple Multi-Layer Perceptron as a baseline, ResNet models, a CRNN model, and a sample-level CNN model. The ResNet models achieved the best performance in terms of accuracy and robustness under various setups (with or without clean audio, seen or unseen dataset), with a micro F1 of 0.876 and Macro F1 of 0.906 in the hardest setup. An ablation study on the ResNet models further indicates the necessary model complexity for the task.

Download

Automatic drum transcription, a subtask of the more general automatic music transcription, deals with extracting drum instrument note onsets from an audio source. Recently, progress in transcription performance has been made using non-negative matrix factorization as well as deep learning methods. However, these works primarily focus on transcribing three drum instruments only: snare drum, bass drum, and hi-hat. Yet, for many applications, the ability to transcribe more drum instruments which make up standard drum kits used in western popular music would be desirable. In this work, convolutional and convolutional recurrent neural networks are trained to transcribe a wider range of drum instruments. First, the shortcomings of publicly available datasets in this context are discussed. To overcome these limitations, a larger synthetic dataset is introduced. Then, methods to train models using the new dataset focusing on generalization to real world data are investigated. Finally, the trained models are evaluated on publicly available datasets and results are discussed. The contributions of this work comprise: (i.) a large-scale synthetic dataset for drum transcription, (ii.) first steps towards an automatic drum transcription system that supports a larger range of instruments by evaluating and discussing training setups and the impact of datasets in this context, and (iii.) a publicly available set of trained models for drum transcription. Additional materials are available at http://ifs.tuwien.ac.at/~vogl/dafx2018.

Download

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

Extraction of symbolic information from signals is an active field of research enabling numerous applications especially in the Musical Information Retrieval domain. This complex task, that is also related to other topics such as pitch extraction or instrument recognition, is a demanding subject that gave birth to numerous approaches, mostly based on advanced signal processing-based algorithms. However, these techniques are often non-generic, allowing the extraction of definite physical properties of the signal (pitch, octave), but not allowing arbitrary vocabularies or more general annotations. On top of that, these techniques are one-sided, meaning that they can extract symbolic data from an audio signal, but cannot perform the reverse process and make symbol-to-signal generation. In this paper, we propose an bijective approach for signal/symbol translation by turning this problem into a density estimation task over signal and symbolic domains, considered both as related random variables. We estimate this joint distribution with two different variational auto-encoders, one for each domain, whose inner representations are forced to match with an additive constraint, allowing both models to learn and generate separately while allowing signal-to-symbol and symbol-to-signal inference. In this article, we test our models on pitch, octave and dynamics symbols, which comprise a fundamental step towards music transcription and label-constrained audio generation. In addition to its versatility, this system is rather light during training and generation while allowing several interesting creative uses that we outline at the end of the article.

Download

Piano transcription is a fundamental problem in the field of music information retrieval. At present, a large number of transcriptional studies are mainly based on audio or video, yet there is a small number of discussion based on audio-visual fusion. In this paper, a piano transcription model based on strategy fusion is proposed, in which the transcription results of the video model are used to assist audio transcription. Due to the lack of datasets currently used for audio-visual fusion, the OMAPS data set is proposed in this paper. Meanwhile, our strategy fusion model achieves a 92.07% F1 score on OMAPS dataset. The transcription model based on feature fusion is also compared with the one based on strategy fusion. The experiment results show that the transcription model based on strategy fusion achieves better results than the one based on feature fusion.

Download

Modal synthesis methods are a long-standing approach for modelling distributed musical systems. In some cases extensions are possible in order to handle geometric nonlinearities. One such case is the high-amplitude vibration of a string, where geometric nonlinear effects lead to perceptually important effects including pitch glides and a dependence of brightness on striking amplitude. A modal decomposition leads to a coupled nonlinear system of ordinary differential equations. Recent work in applied machine learning approaches (in particular neural ordinary differential equations) has been used to model lumped dynamic systems such as electronic circuits automatically from data. In this work, we examine how modal decomposition can be combined with neural ordinary differential equations for modelling distributed musical systems. The proposed model leverages the analytical solution for linear vibration of system’s modes and employs a neural network to account for nonlinear dynamic behaviour. Physical parameters of a system remain easily accessible after the training without the need for a parameter encoder in the network architecture. As an initial proof of concept, we generate synthetic data for a nonlinear transverse string and show that the model can be trained to reproduce the nonlinear dynamics of the system. Sound examples are presented.

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