Joshua D. Reiss
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Joshua D. Reiss has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Zhiyuan Xu
Queen Mary University of London
3 shared publications - Christian J. Steinmetz
Centre for Digital Music Queen Mary University of London UK
2 shared publications - David Moffat
Plymouth Marine Laboratory, UK
2 shared publications - Emmanouil Benetos
Centre for Digital Music Queen Mary University of London UK
2 shared publications - Marco A. Martinez Ramirez
Adobe Research, USA
2 shared publications - Marco Comunità
Centre for Digital Music Mary University of London UK
2 shared publications
Latest Publications
- Open Access
Differentiable Attenuation Filters for Feedback Delay Networks
We introduce a novel method for designing attenuation filters in digital audio reverberation systems based on Feedback Delay Networks (FDNs). Our approach uses Second Order Sections (SOS) of Infinite Impulse Response (IIR) filters arranged as parametric equalizers (PEQ), enabling fine control over frequency-dependent reverberation decay. Unlike traditional graphic equalizer designs, which require numerous filters per delay line, we propose a scalable solution where the number of filters can be adjusted. The frequency, gain, and quality factor (Q) parameters are shared parameters across delay lines and only the gain is adjusted based on delay length. This design not only reduces the number of optimization parameters, but also remains fully differentiable and compatible with gradient-based learning frameworks. Leveraging principles of analog filter design, our method allows for efficient and accurate filter fitting using supervised learning. Our method delivers a flexible and differentiable design, achieving state-of-the-art performance while significantly reducing computational cost.
Open AccessDifferentiable Attenuation Filters for Feedback Delay Networks
We introduce a novel method for designing attenuation filters in digital audio reverberation systems based on Feedback Delay Networks (FDNs). Our approach uses Second Order Sections (SOS) of Infinite Impulse Response (IIR) filters arranged as parametric equalizers (PEQ), enabling fine control over frequency-dependent reverberation decay. Unlike traditional graphic equalizer designs, which require numerous filters per delay line, we propose a scalable solution where the number of filters can be adjusted. The frequency, gain, and quality factor (Q) parameters are shared parameters across delay lines and only the gain is adjusted based on delay length. This design not only reduces the number of optimization parameters, but also remains fully differentiable and compatible with gradient-based learning frameworks. Leveraging principles of analog filter design, our method allows for efficient and accurate filter fitting using supervised learning. Our method delivers a flexible and differentiable design, achieving state-of-the-art performance while significantly reducing computational cost.
- 13 October 2025
- Published by Springer Nature
- p. 161-173
PinkVocalTransformer: Neural Acoustic-to-Articulatory Inversion Based on the Pink Trombone
- 13 October 2025
- Published by Springer Nature
- p. 161-173
PinkVocalTransformer: Neural Acoustic-to-Articulatory Inversion Based on the Pink Trombone
- Open Access
Improving Neural Pitch Estimation with SWIPE Kernels
Neural networks have become the dominant technique for accurate pitch and periodicity estimation. Although a lot of research has gone into improving network architectures and training paradigms, most approaches operate directly on the raw audio waveform or on general-purpose time-frequency representations. We investigate the use of Sawtooth-Inspired Pitch Estimation (SWIPE) kernels as an audio frontend and find that these hand-crafted, task-specific features can make neural pitch estimators more accurate, robust to noise, and more parameter-efficient. We evaluate supervised and self-supervised state-of-the-art architectures on common datasets and show that the SWIPE audio frontend allows for reducing the network size by an order of magnitude without performance degradation. Additionally, we show that the SWIPE algorithm on its own is much more accurate than commonly reported, outperforming state-of-the-art self-supervised neural pitch estimators.
Open AccessImproving Neural Pitch Estimation with SWIPE Kernels
Neural networks have become the dominant technique for accurate pitch and periodicity estimation. Although a lot of research has gone into improving network architectures and training paradigms, most approaches operate directly on the raw audio waveform or on general-purpose time-frequency representations. We investigate the use of Sawtooth-Inspired Pitch Estimation (SWIPE) kernels as an audio frontend and find that these hand-crafted, task-specific features can make neural pitch estimators more accurate, robust to noise, and more parameter-efficient. We evaluate supervised and self-supervised state-of-the-art architectures on common datasets and show that the SWIPE audio frontend allows for reducing the network size by an order of magnitude without performance degradation. Additionally, we show that the SWIPE algorithm on its own is much more accurate than commonly reported, outperforming state-of-the-art self-supervised neural pitch estimators.
- 10 July 2025
- Published by Springer Nature
- p. 51-67
Sound Effects in Media:A Comparative Analysis of Recorded and Synthetic Samples in Live-Action and Animation
- 10 July 2025
- Published by Springer Nature
- p. 51-67
Sound Effects in Media:A Comparative Analysis of Recorded and Synthetic Samples in Live-Action and Animation
- Open Access
Learning Control of Neural Sound Effects Synthesis from Physically Inspired Models
Sound effects model design commonly uses digital signal processing techniques with full control ability, but it is difficult to achieve realism within a limited number of parameters. Recently, neural sound effects synthesis methods have emerged as a promising approach for generating high-quality and realistic sounds, but the process of synthesizing the desired sound poses difficulties in terms of control. This paper presents a real-time neural synthesis model guided by a physically inspired model, enabling the generation of high-quality sounds while inheriting the control interface of the physically inspired model. We showcase the superior performance of our model in terms of sound quality and control.
Open AccessLearning Control of Neural Sound Effects Synthesis from Physically Inspired Models
Sound effects model design commonly uses digital signal processing techniques with full control ability, but it is difficult to achieve realism within a limited number of parameters. Recently, neural sound effects synthesis methods have emerged as a promising approach for generating high-quality and realistic sounds, but the process of synthesizing the desired sound poses difficulties in terms of control. This paper presents a real-time neural synthesis model guided by a physically inspired model, enabling the generation of high-quality sounds while inheriting the control interface of the physically inspired model. We showcase the superior performance of our model in terms of sound quality and control.
- Open Access
Visual-based spatial audio generation system for multi-speaker environments
In multimedia applications such as films and video games, spatial audio techniques are widely employed to enhance user experiences by simulating 3D sound: transforming mono audio into binaural formats. However, this process is often complex and labor-intensive for sound designers, requiring precise synchronization of audio with the spatial positions of visual components. To address these challenges, we propose a visual-based spatial audio generation system - an automated system that integrates face detection YOLOv8 for object detection, monocular depth estimation, and spatial audio techniques. Notably, the system operates without requiring additional binaural dataset training. The proposed system is evaluated against existing Spatial Audio generation system using objective metrics. Experimental results demonstrate that our method significantly improves spatial consistency between audio and video, enhances speech quality, and performs robustly in multi-speaker scenarios. By streamlining the audio-visual alignment process, the proposed system enables sound engineers to achieve high-quality results efficiently, making it a valuable tool for professionals in multimedia production.
Open AccessVisual-based spatial audio generation system for multi-speaker environments
In multimedia applications such as films and video games, spatial audio techniques are widely employed to enhance user experiences by simulating 3D sound: transforming mono audio into binaural formats. However, this process is often complex and labor-intensive for sound designers, requiring precise synchronization of audio with the spatial positions of visual components. To address these challenges, we propose a visual-based spatial audio generation system - an automated system that integrates face detection YOLOv8 for object detection, monocular depth estimation, and spatial audio techniques. Notably, the system operates without requiring additional binaural dataset training. The proposed system is evaluated against existing Spatial Audio generation system using objective metrics. Experimental results demonstrate that our method significantly improves spatial consistency between audio and video, enhances speech quality, and performs robustly in multi-speaker scenarios. By streamlining the audio-visual alignment process, the proposed system enables sound engineers to achieve high-quality results efficiently, making it a valuable tool for professionals in multimedia production.
- Open Access
6KSFx Synth Dataset
Procedural audio, often referred to as "digital Foley", generates sound from scratch using computational processes. It represents an innovative approach to sound-effects creation. However, the development and adoption of procedural audio has been constrained by a lack of publicly available datasets and models, which hinders evaluation and optimization. To address this important gap, this paper presents a dataset of 6000 synthetic audio samples specifically designed to advance research and development in sound synthesis within 30 sound categories. By offering a description of the diverse synthesis methods used in each sound category and supporting the creation of robust evaluation frameworks, this dataset not only highlights the potential of procedural audio, but also provides a resource for researchers, audio developers, and sound designers. This contribution can accelerate the progress of procedural audio, opening up new possibilities in digital sound design.
Open Access6KSFx Synth Dataset
Procedural audio, often referred to as "digital Foley", generates sound from scratch using computational processes. It represents an innovative approach to sound-effects creation. However, the development and adoption of procedural audio has been constrained by a lack of publicly available datasets and models, which hinders evaluation and optimization. To address this important gap, this paper presents a dataset of 6000 synthetic audio samples specifically designed to advance research and development in sound synthesis within 30 sound categories. By offering a description of the diverse synthesis methods used in each sound category and supporting the creation of robust evaluation frameworks, this dataset not only highlights the potential of procedural audio, but also provides a resource for researchers, audio developers, and sound designers. This contribution can accelerate the progress of procedural audio, opening up new possibilities in digital sound design.
- Open Access
- 10 December 2023
- Published by Audio Engineering Society in Journal of the Audio Engineering Society
- Vol. 71 (12) , 825-847
The State of the Art in Procedural Audio
Procedural audio may be defined as real-time sound generation according to programmatic rules and live input. It is often considered a subset of sound synthesis and is especially applicable to nonlinear media, such as video games, virtual reality experiences and interactive audiovisual installations. However, there is resistance to widespread adoption of procedural audio because there is little awareness of the state of the art, including the diversity of sounds that may be generated, the...
- 10 December 2023
- Published by Audio Engineering Society in Journal of the Audio Engineering Society
- Vol. 71 (12) , 825-847
Open AccessThe State of the Art in Procedural Audio
Procedural audio may be defined as real-time sound generation according to programmatic rules and live input. It is often considered a subset of sound synthesis and is especially applicable to nonlinear media, such as video games, virtual reality experiences and interactive audiovisual installations. However, there is resistance to widespread adoption of procedural audio because there is little awareness of the state of the art, including the diversity of sounds that may be generated, the...
- Open Access
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 non-speech 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.
Open AccessOptimization 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 non-speech 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.
- 12 September 2023
- Published by Audio Engineering Society in Journal of the Audio Engineering Society
- Vol. 71 (9) , 586-595
Reverse Engineering a Nonlinear Mix of a Multitrack Recording
In the field of intelligent audio production, neural networks have been trained to automatically mix a multitrack to a stereo mixdown. Although these algorithms contain latent models of mix engineering, there is still a lack of approaches that explicitly model the decisions a mix engineer makes while mixing. In this work, a method to retrieve the parameters used to create a multitrack mix using only raw tracks and the stereo mixdown is presented. This method is able to model a multitrack mix...
- 12 September 2023
- Published by Audio Engineering Society in Journal of the Audio Engineering Society
- Vol. 71 (9) , 586-595
Reverse Engineering a Nonlinear Mix of a Multitrack Recording
In the field of intelligent audio production, neural networks have been trained to automatically mix a multitrack to a stereo mixdown. Although these algorithms contain latent models of mix engineering, there is still a lack of approaches that explicitly model the decisions a mix engineer makes while mixing. In this work, a method to retrieve the parameters used to create a multitrack mix using only raw tracks and the stereo mixdown is presented. This method is able to model a multitrack mix...