Paper Archive

This paper proposes to use a recurrent neural network for black-box modelling of nonlinear audio systems, such as tube amplifiers and distortion pedals. As a recurrent unit structure, we test both Long Short-Term Memory and a Gated Recurrent Unit. We compare the proposed neural network with a WaveNet-style deep neural network, which has been suggested previously for tube amplifier modelling. The neural networks are trained with several minutes of guitar and bass recordings, which have been passed through the devices to be modelled. A real-time audio plugin implementing the proposed networks has been developed in the JUCE framework. It is shown that the recurrent neural networks achieve similar accuracy to the WaveNet model, while requiring significantly less processing power to run. The Long Short-Term Memory recurrent unit is also found to outperform the Gated Recurrent Unit overall. The proposed neural network is an important step forward in computationally efficient yet accurate emulation of tube amplifiers and distortion pedals.

Download

Advances in deep learning have led to novel, state-of-the-art techniques for blind source separation, particularly for the application of non-stationary noise removal from speech. In this paper, we show how a simple reformulation allows us to adapt blind source separation techniques to the problem of speech dereverberation and, accordingly, train a bidirectional recurrent neural network (BRNN) for this task. We compare the performance of the proposed neural network approach with that of a baseline dereverberation algorithm based on spectral subtraction. We find that our trained neural network quantitatively and qualitatively outperforms the baseline approach.

Download

This paper proposes to speed up the design of a third-order graphic equalizer by training a neural network to imitate its gain optimization. Instead of using the neural network to learn to design the graphic equalizer by optimizing its magnitude response, we present the network only with example command gains and the corresponding optimized gains, which are obtained with a previously proposed least-squares-based method. We presented this idea recently for the octave graphic equalizer with 10 band filters and extend it here to the third-octave case. Instead of a network with a single hidden layer, which we previously used, this task appears to require two hidden layers. This paper shows that good results can be reached with a neural network having 62 and 31 units in the first and the second hidden layer, respectively. After the training, the resulting network can quickly and accurately design a third-order graphic equalizer with a maximum error of 1.2 dB. The computing of the filter gains is over 350 times faster with the neural network than with the original optimization method. The method is easy to apply, and may thus lead to widespread use of accurate digital graphic equalizers.

Download

Audio processors whose parameters are modified periodically over time are often referred as time-varying or modulation based audio effects. Most existing methods for modeling these type of effect units are often optimized to a very specific circuit and cannot be efficiently generalized to other time-varying effects. Based on convolutional and recurrent neural networks, we propose a deep learning architecture for generic black-box modeling of audio processors with long-term memory. We explore the capabilities of deep neural networks to learn such long temporal dependencies and we show the network modeling various linear and nonlinear, time-varying and time-invariant audio effects. In order to measure the performance of the model, we propose an objective metric based on the psychoacoustics of modulation frequency perception. We also analyze what the model is actually learning and how the given task is accomplished.

Download

The following article introduces a new parametric synthesis algorithm for sound textures inspired by existing methods used for visual textures. Using a 2D Convolutional Neural Network (CNN), a sound signal is modified until the temporal cross-correlations of the feature maps of its log-spectrogram resemble those of a target texture. We show that the resulting synthesized sound signal is both different from the original and of high quality, while being able to reproduce singular events appearing in the original. This process is performed in the time domain, discarding the harmful phase recovery step which usually concludes synthesis performed in the time-frequency domain. It is also straightforward and flexible, as it does not require any fine tuning between several losses when synthesizing diverse sound textures. Synthesized spectrograms and sound signals are showcased, and a way of extending the synthesis in order to produce a sound of any length is also presented. We also discuss the choice of CNN, border effects in our synthesized signals and possible ways of modifying the algorithm in order to improve its current long computation time.

Download

In this paper we present a new method for the pseudo black-box modelling of general continuous-time state-space systems using a discrete-time state-space system with an embedded deep neural network. Examples are given of how this method can be applied to a number of common nonlinear electronic circuits used in music technology, namely two kinds of diode-based guitar distortion circuits and the lowpass filter of the Korg MS-20 synthesizer.

Download

Many recent approaches to creative transformations of musical audio have been motivated by the success of raw audio generation models such as WaveNet, in which audio samples are modeled by generative neural networks. This paper describes a generative audio synthesis model for multi-drum translation based on a WaveNet denosing autoencoder architecture. The timbre of an arbitrary source audio input is transformed to sound as if it were played by various percussive instruments while preserving its rhythmic structure. Two evaluations of the transformations are conducted based on the capacity of the model to preserve the rhythmic patterns of the input and the audio quality as it relates to timbre of the target drum domain. The first evaluation measures the rhythmic similarities between the source audio and the corresponding drum translations, and the second provides a numerical analysis of the quality of the synthesised audio. Additionally, a semi- and fully-automatic audio effect has been proposed, in which the user may assist the system by manually labelling source audio segments or use a state-of-the-art automatic drum transcription system prior to drum translation.

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

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

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