Download Audio Effect Chain Estimation and Dry Signal Recovery From Multi-Effect-Processed Musical Signals In this paper we propose a method that can address a novel task, audio effect (AFX) chain estimation and dry signal recovery. AFXs are indispensable in modern sound design workflows. Sound engineers often cascade different AFXs (as an AFX chain) to achieve their desired soundscapes. Given a multi-AFX-applied solo instrument performance (wet signal), our method can automatically estimate the applied AFX chain and recover its unprocessed dry signal, while previous research only addresses one of them. The estimated chain is useful for novice engineers in learning practical usages of AFXs, and the recovered signal can be reused with a different AFX chain. To solve this task, we first develop a deep neural network model that estimates the last-applied AFX and undoes its AFX at a time. We then iteratively apply the same model to estimate the AFX chain and eventually recover the dry signal from the wet signal. Our experiments on guitar phrase recordings with various AFX chains demonstrate the validity of our method for both the AFX-chain estimation and dry signal recovery. We also confirm that the input wet signal can be reproduced by applying the estimated AFX chain to the recovered dry signal.
Download CONMOD: Controllable Neural Frame-Based Modulation Effects Deep learning models have seen widespread use in modelling LFOdriven audio effects, such as phaser and flanger. Although existing neural architectures exhibit high-quality emulation of individual effects, they do not possess the capability to manipulate the output via control parameters. To address this issue, we introduce Controllable Neural Frame-based Modulation Effects (CONMOD), a single black-box model which emulates various LFOdriven effects in a frame-wise manner, offering control over LFO frequency and feedback parameters. Additionally, the model is capable of learning the continuous embedding space of two distinct phaser effects, enabling us to steer between effects and achieve creative outputs. Our model outperforms previous work while possessing both controllability and universality, presenting opportunities to enhance creativity in modern LFO-driven audio effects. Additional demo of our model is available in the accompanying website.1
Download Sample Rate Independent Recurrent Neural Networks for Audio Effects Processing In recent years, machine learning approaches to modelling guitar amplifiers and effects pedals have been widely investigated and have become standard practice in some consumer products. In particular, recurrent neural networks (RNNs) are a popular choice for modelling non-linear devices such as vacuum tube amplifiers and distortion circuitry. One limitation of such models is that they are trained on audio at a specific sample rate and therefore give unreliable results when operating at another rate. Here, we investigate several methods of modifying RNN structures to make them approximately sample rate independent, with a focus on oversampling. In the case of integer oversampling, we demonstrate that a previously proposed delay-based approach provides high fidelity sample rate conversion whilst additionally reducing aliasing. For non-integer sample rate adjustment, we propose two novel methods and show that one of these, based on cubic Lagrange interpolation of a delay-line, provides a significant improvement over existing methods. To our knowledge, this work provides the first in-depth study into this problem.
Download A Diffusion-Based Generative Equalizer for Music Restoration This paper presents a novel approach to audio restoration, focusing on the enhancement of low-quality music recordings, and in particular historical ones. Building upon a previous algorithm called BABE, or Blind Audio Bandwidth Extension, we introduce BABE-2, which presents a series of improvements. This research broadens the concept of bandwidth extension to generative equalization, a task that, to the best of our knowledge, has not been previously addressed for music restoration. BABE-2 is built around an optimization algorithm utilizing priors from diffusion models, which are trained or fine-tuned using a curated set of high-quality music tracks. The algorithm simultaneously performs two critical tasks: estimation of the filter degradation magnitude response and hallucination of the restored audio. The proposed method is objectively evaluated on historical piano recordings, showing an enhancement over the prior version. The method yields similarly impressive results in rejuvenating the works of renowned vocalists Enrico Caruso and Nellie Melba. This research represents an advancement in the practical restoration of historical music. Historical music restoration examples are available at: research.spa.aalto.fi/publications/papers/dafx-babe2/.
Download Neural Audio Processing on Android Phones This study investigates the potential of real-time inference of neural audio effects on Android smartphones, marking an initial step towards bridging the gap in neural audio processing for mobile devices. Focusing exclusively on processing rather than synthesis, we explore the performance of three open-source neural models across five Android phones released between 2014 and 2022, showcasing varied capabilities due to their generational differences. Through comparative analysis utilizing two C++ inference engines (ONNX Runtime and RTNeural), we aim to evaluate the computational efficiency and timing performance of these models, considering the varying computational loads and the hardware specifics of each device. Our work contributes insights into the feasibility of implementing neural audio processing in real-time on mobile platforms, highlighting challenges and opportunities for future advancements in this rapidly evolving field.
Download RAVE for Speech: Efficient Voice Conversion at High Sampling Rates Voice conversion has gained increasing popularity within the field of audio manipulation and speech synthesis. Often, the main objective is to transfer the input identity to that of a target speaker without changing its linguistic content. While current work provides high-fidelity solutions they rarely focus on model simplicity, high-sampling rate environments or stream-ability. By incorporating speech representation learning into a generative timbre transfer model, traditionally created for musical purposes, we investigate the realm of voice conversion generated directly in the time domain at high sampling rates. More specifically, we guide the latent space of a baseline model towards linguistically relevant representations and condition it on external speaker information. Through objective and subjective assessments, we demonstrate that the proposed solution can attain levels of naturalness, quality, and intelligibility comparable to those of a state-of-the-art solution for seen speakers, while significantly decreasing inference time. However, despite the presence of target speaker characteristics in the converted output, the actual similarity to unseen speakers remains a challenge.
Download Network Bending of Diffusion Models for Audio-Visual Generation In this paper we present the first steps towards the creation of a tool which enables artists to create music visualizations using pretrained, generative, machine learning models. First, we investigate the application of network bending, the process of applying transforms within the layers of a generative network, to image generation diffusion models by utilizing a range of point-wise, tensorwise, and morphological operators. We identify a number of visual effects that result from various operators, including some that are not easily recreated with standard image editing tools. We find that this process allows for continuous, fine-grain control of image generation which can be helpful for creative applications. Next, we generate music-reactive videos using Stable Diffusion by passing audio features as parameters to network bending operators. Finally, we comment on certain transforms which radically shift the image and the possibilities of learning more about the latent space of Stable Diffusion based on these transforms.
Download Automatic Equalization for Individual Instrument Tracks Using Convolutional Neural Networks We propose a novel approach for the automatic equalization of individual musical instrument tracks. Our method begins by identifying the instrument present within a source recording in order to choose its corresponding ideal spectrum as a target. Next, the spectral difference between the recording and the target is calculated, and accordingly, an equalizer matching model is used to predict settings for a parametric equalizer. To this end, we build upon a differentiable parametric equalizer matching neural network, demonstrating improvements relative to previously established state-of-the-art. Unlike past approaches, we show how our system naturally allows real-world audio data to be leveraged during the training of our matching model, effectively generating suitably produced training targets in an automated manner mirroring conditions at inference time. Consequently, we illustrate how fine-tuning our matching model on such examples considerably improves parametric equalizer matching performance in realworld scenarios, decreasing mean absolute error by 24% relative to methods relying solely on random parameter sampling techniques as a self-supervised learning strategy. We perform listening tests, and demonstrate that our proposed automatic equalization solution subjectively enhances the tonal characteristics for recordings of common instrument types.
Download Balancing Error and Latency of Black-Box Models for Audio Effects Using Hardware-Aware Neural Architecture Search In this paper, we address automating and systematizing the process of finding black-box models for virtual analogue audio effects with an optimal balance between error and latency. We introduce a multi-objective optimization approach based on hardware-aware neural architecture search which allows specifying the optimization balance of model error and latency according to the requirements of the application. By using a regularized evolutionary algorithm, it is able to navigate through a huge search space systematically. Additionally, we propose a search space for modelling non-linear dynamic audio effects consisting of over 41 trillion different WaveNet-style architectures. We evaluate its performance and usefulness by yielding highly effective architectures, either up to 18× faster or with a test loss of up to 56% less than the best performing models of the related work, while still showing a favourable trade-off. We can conclude that hardware-aware neural architecture search is a valuable tool that can help researchers and engineers developing virtual analogue models by automating the architecture design and saving time by avoiding manual search and evaluation through trial-and-error.
Download ICGAN: An Implicit Conditioning Method for Interpretable Feature Control of Neural Audio Synthesis Neural audio synthesis methods can achieve high-fidelity and realistic sound generation by utilizing deep generative models. Such models typically rely on external labels which are often discrete as conditioning information to achieve guided sound generation. However, it remains difficult to control the subtle changes in sounds without appropriate and descriptive labels, especially given a limited dataset. This paper proposes an implicit conditioning method for neural audio synthesis using generative adversarial networks that allows for interpretable control of the acoustic features of synthesized sounds. Our technique creates a continuous conditioning space that enables timbre manipulation without relying on explicit labels. We further introduce an evaluation metric to explore controllability and demonstrate that our approach is effective in enabling a degree of controlled variation of different synthesized sound effects for in-domain and cross-domain sounds.