Download Interpretable timbre synthesis using variational autoencoders regularized on timbre descriptors 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 Fully Conditioned and Low-Latency Black-Box Modeling of Analog Compression Neural networks have been found suitable for virtual analog modeling applications. Several analog audio effects have been successfully modeled with deep learning techniques, using low-latency and conditioned architectures suitable for real-world applications. Challenges remain with effects presenting more complex responses, such as nonlinear and time-varying input-output relationships. This paper proposes a deep-learning model for the analog compression effect. The architecture we introduce is fully conditioned by the device control parameters and it works on small audio segments, allowing low-latency real-time implementations. The architecture is used to model the CL 1B analog optical compressor, showing an overall high accuracy and ability to capture the different attack and release compression profiles. The proposed architecture’ ability to model audio compression behaviors is also verified using datasets from other compressors. Limitations remain with heavy compression scenarios determined by the conditioning parameters.
Download Differentiable All-Pass Filters for Phase Response Estimation and Automatic Signal Alignment Virtual analog (VA) audio effects are increasingly based on neural networks and deep learning frameworks. Due to the underlying black-box methodology, a successful model will learn to approximate the data it is presented, including potential errors such as latency and audio dropouts as well as non-linear characteristics and frequency-dependent phase shifts produced by the hardware. The latter is of particular interest as the learned phase-response might cause unwanted audible artifacts when the effect is used for creative processing techniques such as dry-wet mixing or parallel compression. To overcome these artifacts we propose differentiable signal processing tools and deep optimization structures for automatically tuning all-pass filters to predict the phase response of different VA simulations, and align processed signals that are out of phase. The approaches are assessed using objective metrics while listening tests evaluate their ability to enhance the quality of parallel path processing techniques. Ultimately, an overparameterized, BiasNet-based, all-pass model is proposed for the optimization problem under consideration, resulting in models that can estimate all-pass filter coefficients to align a dry signal with its affected, wet, equivalent.
Download A Differentiable Digital Moog Filter For Machine Learning Applications In this project, a digital ladder filter has been investigated and expanded. This structure is a simplified digital analog model of the well known analog Moog ladder filter. The goal of this paper is to derive the differentiation expressions of this filter with respect to its control parameters in order to integrate it in machine learning systems. The derivation of the backpropagation method is described in this work, it can be generalized to a Moog filter or a similar filter having any number of stages. Subsequently, the example of an adaptive Moog filter is provided. Finally, a machine learning application example is shown where the filter is integrated in a deep learning framework.
Download Perceptual Evaluation and Genre-specific Training of Deep Neural Network Models of a High-gain Guitar Amplifier Modelling of analogue devices via deep neural networks (DNNs) has gained popularity recently, but their performance is usually measured using accuracy measures alone. This paper aims to assess the performance of DNN models of a high-gain vacuum-tube guitar amplifier using additional subjective measures, including preference and realism. Furthermore, the paper explores how the performance changes when genre-specific training data is used. In five listening tests, subjects rated models of a popular high-gain guitar amplifier, the Peavey 6505, in terms of preference, realism and perceptual accuracy. Two DNN models were used: a long short-term memory recurrent neural network (LSTM-RNN) and a WaveNet-based convolutional neural network (CNN). The LSTMRNN model was shown to be more accurate when trained with genre-specific data, to the extent that it could not be distinguished from the real amplifier in ABX tests. Despite minor perceptual inaccuracies, subjects found all models to be as realistic as the target in MUSHRA-like experiments, and there was no evidence to suggest that the real amplifier was preferred to any of the models in a mix. Finally, it was observed that a low-gain excerpt was more difficult to emulate, and was therefore useful to reveal differences between the models.
Download Real-Time Singing Voice Conversion Plug-In In this paper, we propose an approach to real-time singing voice conversion and outline its development as a plug-in suitable for streaming use in a digital audio workstation. In order to simultaneously ensure pitch preservation and reduce the computational complexity of the overall system, we adopt a source-filter methodology and consider a vocoder-free paradigm for modeling the conversion task. In this case, the source is extracted and altered using more traditional DSP techniques, while the filter is determined using a deep neural network. The latter can be trained in an end-toend fashion and additionally uses adversarial training to improve system fidelity. Careful design allows the system to scale naturally to sampling rates higher than the neural filter model sampling rate, outputting full-band signals while avoiding the need for resampling. Accordingly, the resulting system, when operating at 44.1 kHz, incurs under 60 ms of latency and operates 20 times faster than real-time on a standard laptop CPU.
Download Neural Grey-Box Guitar Amplifier Modelling with Limited Data This paper combines recurrent neural networks (RNNs) with the discretised Kirchhoff nodal analysis (DK-method) to create a grey-box guitar amplifier model. Both the objective and subjective results suggest that the proposed model is able to outperform a baseline black-box RNN model in the task of modelling a guitar amplifier, including realistically recreating the behaviour of the amplifier equaliser circuit, whilst requiring significantly less training data. Furthermore, we adapt the linear part of the DK-method in a deep learning scenario to derive multiple state-space filters simultaneously. We frequency sample the filter transfer functions in parallel and perform frequency domain filtering to considerably reduce the required training times compared to recursive state-space filtering. This study shows that it is a powerful idea to separately model the linear and nonlinear parts of a guitar amplifier using supervised learning.
Download Optimization techniques for a physical model of human vocalisation We present a non-supervised approach to optimize and evaluate the synthesis of non-speech audio effects from a speech production model. We use the Pink Trombone synthesizer as a case study of a simplified production model of the vocal tract to target nonspeech human audio signals –yawnings. We selected and optimized the control parameters of the synthesizer to minimize the difference between real and generated audio. We validated the most common optimization techniques reported in the literature and a specifically designed neural network. We evaluated several popular quality metrics as error functions. These include both objective quality metrics and subjective-equivalent metrics. We compared the results in terms of total error and computational demand. Results show that genetic and swarm optimizers outperform least squares algorithms at the cost of executing slower and that specific combinations of optimizers and audio representations offer significantly different results. The proposed methodology could be used in benchmarking other physical models and audio types.
Download Neural Modeling of Magnetic Tape Recorders The sound of magnetic recording media, such as open-reel and cassette tape recorders, is still sought after by today’s sound practitioners due to the imperfections embedded in the physics of the magnetic recording process. This paper proposes a method for digitally emulating this character using neural networks. The signal chain of the proposed system consists of three main components: the hysteretic nonlinearity and filtering jointly produced by the magnetic recording process as well as the record and playback amplifiers, the fluctuating delay originating from the tape transport, and the combined additive noise component from various electromagnetic origins. In our approach, the hysteretic nonlinear block is modeled using a recurrent neural network, while the delay trajectories and the noise component are generated using separate diffusion models, which employ U-net deep convolutional neural networks. According to the conducted objective evaluation, the proposed architecture faithfully captures the character of the magnetic tape recorder. The results of this study can be used to construct virtual replicas of vintage sound recording devices with applications in music production and audio antiquing tasks.
Download Vocal Tract Area Estimation by Gradient Descent Articulatory features can provide interpretable and flexible controls for the synthesis of human vocalizations by allowing the user to directly modify parameters like vocal strain or lip position. To make this manipulation through resynthesis possible, we need to estimate the features that result in a desired vocalization directly from audio recordings. In this work, we propose a white-box optimization technique for estimating glottal source parameters and vocal tract shapes from audio recordings of human vowels. The approach is based on inverse filtering and optimizing the frequency response of a waveguide model of the vocal tract with gradient descent, propagating error gradients through the mapping of articulatory features to the vocal tract area function. We apply this method to the task of matching the sound of the Pink Trombone, an interactive articulatory synthesizer, to a given vocalization. We find that our method accurately recovers control functions for audio generated by the Pink Trombone itself. We then compare our technique against evolutionary optimization algorithms and a neural network trained to predict control parameters from audio. A subjective evaluation finds that our approach outperforms these black-box optimization baselines on the task of reproducing human vocalizations.