Paper Archive

This paper investigates the optimization of Truncated Backpropagation Through Time (TBPTT) for training neural networks in digital audio effect modeling, with a focus on dynamic range compression. The study evaluates key TBPTT hyperparameters – sequence number, batch size, and sequence length – and their influence on model performance. Using a convolutional-recurrent architecture, we conduct extensive experiments across datasets with and without conditioning by user controls. Results demonstrate that carefully tuning these parameters enhances model accuracy and training stability, while also reducing computational demands. Objective evaluations confirm improved performance with optimized settings, while subjective listening tests indicate that the revised TBPTT configuration maintains high perceptual quality.

Download

In this paper, we introduce means of improving fidelity and controllability of the RAVE generative audio model by factorizing pitch and other features. We accomplish this primarily by creating a multi-band excitation signal capturing pitch and/or loudness information, and by using it to FiLM-condition the RAVE generator. To further improve fidelity when applied to a singing voice application explored here, we also consider concatenating a supervised phonetic encoding to its latent representation. An ablation analysis highlights the improved performance of our incremental improvements relative to the baseline RAVE model. As our primary enhancement involves adding a stable pitch conditioning mechanism into the RAVE model, we simply call our method P-RAVE.

Download

Reusing recorded sounds (sampling) is a key component in Electronic Music Production (EMP), which has been present since its early days and is at the core of genres like hip-hop or jungle. Commercial and non-commercial services allow users to obtain collections of sounds (sample packs) to reuse in their compositions. Automatic classification of one-shot instrumental sounds allows automatically categorising the sounds contained in these collections, allowing easier navigation and better characterisation. Automatic instrument classification has mostly targeted the classification of unprocessed isolated instrumental sounds or detecting predominant instruments in mixed music tracks. For this classification to be useful in audio databases for EMP, it has to be robust to the audio effects applied to unprocessed sounds. In this paper we evaluate how a state of the art model trained with a large dataset of one-shot instrumental sounds performs when classifying instruments processed with audio effects. In order to evaluate the robustness of the model, we use data augmentation with audio effects and evaluate how each effect influences the classification accuracy.

Download

This paper presents a deep learning approach to parametric timefrequency parameter prediction for use within stereo upmixing algorithms. The approach presented uses a Multi-Channel U-Net with Residual connections (MuCh-Res-U-Net) trained on a novel dataset of stereo and parametric time-frequency spatial audio data to predict time-frequency spatial parameters from a stereo input signal for positions on a 50-point Lebedev quadrature sampled sphere. An example upmix pipeline is then proposed which utilises the predicted time-frequency spatial parameters to both extract and remap stereo signal components to target spherical harmonic components to facilitate the generation of a full spherical representation of the upmixed sound field.

Download

Automatic blind upmixing aims to convert audio from a smaller channel format (e.g. mono or stereo) into a multichannel format using estimates of direct and diffuse spatial statistics within the signal. Current approaches rely on primary-ambient extraction (PAE) algorithms, which lack real-world context through limited processing windows. Deep learning music source separation (MSS) models have been applied in voice-primary-ambient extraction (VPA) upmixing systems for handling direct components, but still rely on DSP methods of surround channel generation. This work further investigates utilizing source separation within VPA upmixing, focusing specifically on the task of stereo decorrelation and ambience extraction for 5.1 surround. We also release PAEDB (Primary–Ambient Extraction Dataset), a high-quality music dataset derived from MUSDB18-HQ and MoisesDB, comprising 1,809 primary–ambient stem pairs totaling over 550 hours of audio. The performance of selected DNNs trained on PAEDB is then evaluated using signal metrics and a listening study. Our findings indicate that DNNs can effectively model the behavior of PAE algorithms, establishing PAEDB as a strong foundation for ML upmixing systems and underscoring the need for higher-quality multichannel data to advance beyond conventional methods.

Download

This paper presents a data-driven approach to the construction of mapping models relating sound features and blowing pressure in recorder playing. Blowing pressure and sound feature data are synchronously obtained from real performance: blowing pressure is measured by means of a piezoelectric transducer inserted into the mouth piece of a modified recorder, while produced sound is acquired using a close-field microphone. Acquired sound is analyzed frame-by-frame, and features are extracted so that original sound can be reconstructed with enough fidelity. A multi-modal database of aligned blowing pressure and sound feature signals is constructed from real performance recordings designed to cover basic performance contexts. Out of the gathered data, two types of mapping models are constructed using artificial neural networks: (i) a model able to generate sound feature signals from blowing pressure signals, and therefore used to produce synthetic sound from recorded blowing pressure profiles via additive synthesis; and (ii) a model able to estimate the blowing pressure from extracted sound features.

Download

We explore two approaches to creatively altering vocal timbre using Differentiable Digital Signal Processing (DDSP). The first approach is inspired by classic cross-synthesis techniques. A pretrained DDSP decoder predicts a filter for a noise source and a harmonic distribution, based on pitch and loudness information extracted from the vocal input. Before synthesis, the harmonic distribution is modified by interpolating between the predicted distribution and the harmonics of the input. We provide a real-time implementation of this approach in the form of a Neutone model. In the second approach, autoencoder models are trained on datasets consisting of both vocal and instrument training data. To apply the effect, the trained autoencoder attempts to reconstruct the vocal input. We find that there is a desirable “sweet spot” during training, where the model has learned to reconstruct the phonetic content of the input vocals, but is still affected by the timbre of the instrument mixed into the training data. After further training, that effect disappears. A perceptual evaluation compares the two approaches. We find that the autoencoder in the second approach is able to reconstruct intelligible lyrical content without any explicit phonetic information provided during training.

Download

Audio effects (AFXs) are essential tools in music production, frequently applied in chains to shape timbre and dynamics. The order of AFXs in a chain plays a crucial role in determining the final sound, particularly when non-linear (e.g., distortion) or timevariant (e.g., chorus) processors are involved. Despite its importance, most AFX-related studies have primarily focused on estimating effect types and their parameters from a wet signal. To address this gap, we formulate AFX chain recognition as the task of jointly estimating AFX types and their order from a wet signal. We propose a neural-network-based method that embeds wet signals into a hyperbolic space and classifies their AFX chains. Hyperbolic space can represent tree-structured data more efficiently than Euclidean space due to its exponential expansion property. Since AFX chains can be represented as trees, with AFXs as nodes and edges encoding effect order, hyperbolic space is well-suited for modeling the exponentially growing and non-commutative nature of ordered AFX combinations, where changes in effect order can result in different final sounds. Experiments using guitar sounds demonstrate that, with an appropriate curvature, the proposed method outperforms its Euclidean counterpart. Further analysis based on AFX type and chain length highlights the effectiveness of the proposed method in capturing AFX order.

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

Deep generative neural networks have thrived in the field of computer vision, enabling unprecedented intelligent image processes. Yet the results in audio remain less advanced and many applications are still to be investigated. Our project targets real-time sound synthesis from a reduced set of high-level parameters, including semantic controls that can be adapted to different sound libraries and specific tags. These generative variables should allow expressive modulations of target musical qualities and continuously mix into new styles. To this extent we train auto-encoders on an orchestral database of individual note samples, along with their intrinsic attributes: note class, timbre domain (an instrument subset) and extended playing techniques. We condition the decoder for explicit control over the rendered note attributes and use latent adversarial training for learning expressive style parameters that can ultimately be mixed. We evaluate both generative performances and correlations of the attributes with the latent representation. Our ablation study demonstrates the effectiveness of the musical conditioning. The proposed model generates individual notes as magnitude spectrograms from any probabilistic latent code samples (each latent point maps to a single note), with expressive control of orchestral timbres and playing styles. Its training data subsets can directly be visualized in the 3-dimensional latent representation. Waveform rendering can be done offline with the Griffin-Lim algorithm. In order to allow real-time interactions, we fine-tune the decoder with a pretrained magnitude spectrogram inversion network and embed the full waveform generation pipeline in a plugin. Moreover the encoder could be used to process new input samples, after manipulating their latent attribute representation, the decoder can generate sample variations as an audio effect would. Our solution remains rather light-weight and fast to train, it can directly be applied to other sound domains, including an user’s libraries with custom sound tags that could be mapped to specific generative controls. As a result, it fosters creativity and intuitive audio style experimentations. Sound examples and additional visualizations are available on Github1, as well as codes after the review process.

Download