Download RIR2FDN: An Improved Room Impulse Response Analysis and Synthesis This paper seeks to improve the state-of-the-art in delay-networkbased analysis-synthesis of measured room impulse responses (RIRs). We propose an informed method incorporating improved energy decay estimation and synthesis with an optimized feedback delay network. The performance of the presented method is compared against an end-to-end deep-learning approach. A formal listening test was conducted where participants assessed the similarity of reverberated material across seven distinct RIRs and three different sound sources. The results reveal that the performance of these methods is influenced by both the excitation sounds and the reverberation conditions. Nonetheless, the proposed method consistently demonstrates higher similarity ratings compared to the end-to-end approach across most conditions. However, achieving an indistinguishable synthesis of measured RIRs remains a persistent challenge, underscoring the complexity of this problem. Overall, this work helps improve the sound quality of analysis-based artificial reverberation.
Download Audio-Visual Talker Localization in Video for Spatial Sound Reproduction Object-based audio production requires the positional metadata to be defined for each point-source object, including the key elements in the foreground of the sound scene. In many media production use cases, both cameras and microphones are employed to make recordings, and the human voice is often a key element. In this research, we detect and locate the active speaker in the video, facilitating the automatic extraction of the positional metadata of the talker relative to the camera’s reference frame. With the integration of the visual modality, this study expands upon our previous investigation focused solely on audio-based active speaker detection and localization. Our experiments compare conventional audio-visual approaches for active speaker detection that leverage monaural audio, our previous audio-only method that leverages multichannel recordings from a microphone array, and a novel audio-visual approach integrating vision and multichannel audio. We found the role of the two modalities to complement each other. Multichannel audio, overcoming the problem of visual occlusions, provides a double-digit reduction in detection error compared to audio-visual methods with single-channel audio. The combination of multichannel audio and vision further enhances spatial accuracy, leading to a four-percentage point increase in F1 score on the Tragic Talkers dataset. Future investigations will assess the robustness of the model in noisy and highly reverberant environments, as well as tackle the problem of off-screen speakers.
Download Leveraging Electric Guitar Tones and Effects to Improve Robustness in Guitar Tablature Transcription Modeling Guitar tablature transcription (GTT) aims at automatically generating symbolic representations from real solo guitar performances. Due to its applications in education and musicology, GTT has gained traction in recent years. However, GTT robustness has been limited due to the small size of available datasets. Researchers have recently used synthetic data that simulates guitar performances using pre-recorded or computer-generated tones, allowing for scalable and automatic data generation. The present study complements these efforts by demonstrating that GTT robustness can be improved by including synthetic training data created using recordings of real guitar tones played with different audio effects. We evaluate our approach on a new evaluation dataset with professional solo guitar performances that we composed and collected, featuring a wide array of tones, chords, and scales.
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 Differentiable MIMO Feedback Delay Networks for Multichannel Room Impulse Response Modeling Recently, with the advent of new performing headsets and goggles, the demand for Virtual and Augmented Reality applications has experienced a steep increase. In order to coherently navigate the virtual rooms, the acoustics of the scene must be emulated in the most accurate and efficient way possible. Amongst others, Feedback Delay Networks (FDNs) have proved to be valuable tools for tackling such a task. In this article, we expand and adapt a method recently proposed for the data-driven optimization of single-inputsingle-output FDNs to the multiple-input-multiple-output (MIMO) case for addressing spatial/space-time processing applications. By testing our methodology on items taken from two different datasets, we show that the parameters of MIMO FDNs can be jointly optimized to match some perceptual characteristics of given multichannel room impulse responses, overcoming approaches available in the literature, and paving the way toward increasingly efficient and accurate real-time virtual room acoustics rendering.
Download Hybrid Audio Inpainting Approach with Structured Sparse Decomposition and Sinusoidal Modeling This research presents a novel hybrid audio inpainting approach that considers the diversity of signals and enhances the reconstruction quality. Existing inpainting approaches have limitations, such as energy drop and poor reconstruction quality for non-stationary signals. Based on the fact that an audio signal can be considered as a mixture of three components: tonal, transients, and noise, the proposed approach divides the left and right reliable neighborhoods around the gap into these components using a structured sparse decomposition technique. The gap is reconstructed by extrapolating parameters estimated from the reliable neighborhoods of each component. Component-targeted methods are refined and employed to extrapolate the parameters based on their own acoustic characteristics. Experiments were conducted to evaluate the performance of the hybrid approach and compare it with other stateof-the-art inpainting approaches. The results show the hybrid approach achieves high-quality reconstruction and low computational complexity across various gap lengths and signal types, particularly for longer gaps and non-stationary signals.
Download GRAFX: An Open-Source Library for Audio Processing Graphs in Pytorch We present GRAFX, an open-source library designed for handling audio processing graphs in PyTorch. Along with various library functionalities, we describe technical details on the efficient parallel computation of input graphs, signals, and processor parameters in GPU. Then, we show its example use under a music mixing scenario, where parameters of every differentiable processor in a large graph are optimized via gradient descent. The code is available at https://github.com/sh-lee97/grafx.
Download GPGPU Audio Benchmark Framework Acceleration of audio workloads on generally-programmable GPU (GPGPU) hardware offers potentially high speedup factors, but also presents challenges in terms of development and deployment. We can increasingly depend on such hardware being available in users’ systems, yet few real-time audio products use this resource. We propose a suite of benchmarks to qualify a GPU as suitable for batch or real-time audio processing. This includes both microbenchmarks and higher-level audio domain benchmarks. We choose metrics based on application, paying particularly close attention to latency tail distribution. We propose an extension to the benchmark framework to more accurately simulate the real-world request pattern and performance requirements when running in a digital audio workstation. We run these benchmarks on two common consumer-level platforms: a PC desktop with a recent midrange discrete GPU and a Macintosh desktop with unified CPUGPU memory architecture.
Download Wave Digital Model of the MXR Phase 90 Based on a Time-Varying Resistor Approximation of JFET Elements Virtual Analog (VA) modeling is the practice of digitally emulating analog audio gear. Over the past few years, with the purpose of recreating the alleged distinctive sound of audio equipment and musicians, many different guitar pedals have been emulated by means of the VA paradigm but little attention has been given to phasers. Phasers process the spectrum of the input signal with time-varying notches by means of shifting stages typically realized with a network of transistors, whose nonlinear equations are, in general, demanding to be solved. In this paper, we take as a reference the famous MXR Phase 90 guitar pedal, and we propose an efficient time-varying model of its Junction Field-Effect Transistors (JFETs) based on a channel resistance approximation. We then employ such a model in the Wave Digital domain to emulate in real-time the guitar pedal, obtaining an implementation characterized by low computational cost and good accuracy.
Download A Real-Time Approach for Estimating Pulse Tracking Parameters for Beat-Synchronous Audio Effects Predominant Local Pulse (PLP) estimation, an established method for extracting beat positions and other periodic pulse information from audio signals, has recently been extended with an online variant tailored for real-time applications. In this paper, we introduce a novel approach to generating various real-time control signals from the original online PLP output. While the PLP activation function encodes both predominant pulse information and pulse stability, we propose several normalization procedures to discern local pulse oscillation from stability, utilizing the PLP activation envelope. Through this, we generate pulse-synchronous Low Frequency Oscillators (LFOs) and supplementary confidence-based control signals, enabling dynamic control over audio effect parameters in real-time. Additionally, our approach enables beat position prediction, providing a look-ahead capability, for example, to compensate for system latency. To showcase the effectiveness of our control signals, we introduce an audio plugin prototype designed for integration within a Digital Audio Workstation (DAW), facilitating real-time applications of beat-synchronous effects during live mixing and performances. Moreover, this plugin serves as an educational tool, providing insights into PLP principles and the tempo structure of analyzed music signals.