This paper describes a preliminary approach to algorithmically reproduce the archetypical structure adopted by humans to classify sounds. In particular, we propose an approach to predict the human perceived chaos/order level in a sound and synthesize new timbres that present the desired amount of this feature. We adopted a Neural Network based method, in order to exploit its inner predisposition to model perceptive and abstract features. We finally discuss the obtained accuracy and possible implications in creative contexts.
Ritsumeikan University（立命馆大学）；Doshisha University（同志社大学）；The University of Tokyo（东京大学）；Kansai University（关西大学）
Environmental sound synthesis is a technique for generating a natural environmental sound. Conventional work on environmental sound synthesis using sound event labels cannot finely control synthesized sounds, for example, the pitch and timbre. We consider that onomatopoeic words can be used for environmental sound synthesis. Onomatopoeic words are effective for explaining the feature of sounds. We believe that using onomatopoeic words will enable us to control the fine time-frequency structure of synthesized sounds. However, there is no dataset available for environmental sound synthesis using…
Ritsumeikan University（立命馆大学）；LINE Corporation（LINE公司）；The University of Tokyo（东京大学）
Synthesizing and converting environmental sounds have the potential for many applications such as supporting movie and game production, data augmentation for sound event detection and scene classification. Conventional works on synthesizing and converting environmental sounds are based on a physical modeling or concatenative approach. However, there are a limited number of works that have addressed environmental sound synthesis and conversion with statistical generative models; thus, this research area is not yet well organized. In this paper, we review problem definitions, applications, and e…
Ritsumeikan University（立命馆大学）；Doshisha University（同志社大学）；The University of Tokyo（东京大学）；Kansai University（关西大学）
In this paper, we propose a framework for environmental sound synthesis from onomatopoeic words. As one way of expressing an environmental sound, we can use an onomatopoeic word, which is a character sequence for phonetically imitating a sound. An onomatopoeic word is effective for describing diverse sound features. Therefore, using onomatopoeic words for environmental sound synthesis will enable us to generate diverse environmental sounds. To generate diverse sounds, we propose a method based on a sequence-to-sequence framework for synthesizing environmental sounds from onomatopoeic words. We…
We present an interface involving four degrees-of-freedom (DOF) mechanical control of a two dimensional, mid-sagittal tongue through a biomechanical toolkit called ArtiSynth and a sound synthesis engine called JASS towards articulatory sound synthesis. As a demonstration of the project, the user will learn to produce a range of JASS vocal sounds, by varying the shape and position of the ArtiSynth tongue in 2D space through a set of four force-based sensors. In other words, the user will be able to physically play around with these four sensors, thereby virtually controlling the magnitude of fo…
National Institute of Technology, Tokuyama College（德山国立技术学院）；The University of Tokyo（东京大学）；Doshisha University（同志社大学）；Ritsumeikan University（立命馆大学）
We propose a method for synthesizing environmental sounds from visually represented onomatopoeias and sound sources. An onomatopoeia is a word that imitates a sound structure, i.e., the text representation of sound. From this perspective, onoma-to-wave has been proposed to synthesize environmental sounds from the desired onomatopoeia texts. Onomatopoeias have another representation: visual-text representations of sounds in comics, advertisements, and virtual reality. A visual onomatopoeia (visual text of onomatopoeia) contains rich information that is not present in the text, such as a long-sh…
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…
This article introduces a new parametric synthesis method for sound textures based on existing works in visual and sound texture synthesis. Starting from a base sound signal, an optimization process is performed until the cross-correlations between the feature-maps of several untrained 2D Convolutional Neural Networks (CNN) resemble those of an original sound texture. We use compressed RI spectrograms as input to the CNN: this time-frequency representation is the stacking of the real and imaginary part of the Short Time Fourier Transform (STFT) and thus implicitly contains both the magnitude a…
A method of optimizing secondary source placement in sound field synthesis is proposed. Such an optimization method will be useful when the allowable placement region and available number of loudspeakers are limited. We formulate a mean-square-error-based cost function, incorporating the statistical properties of possible desired sound fields, for general linear-least-squares-based sound field synthesis methods, including pressure matching and (weighted) mode matching, whereas most of the current methods are applicable only to the pressure-matching method. An efficient greedy algorithm for min…
Gaudio Lab, Inc.（Gaudio实验室公司）；KAIST（韩国科学技术院）；Carnegie Mellon University（卡内基梅隆大学）；New York University（纽约大学）；Doshisha University（同志社大学）；Ritsumeikan University（立命馆大学）；CNRS（法国国家科学研究中心）；Ecole Centrale Nantes（南特中央理工学院）；The University of Tokyo（东京大学）
Sony CSL（索尼计算机科学实验室）；LTCI, Télécom Paris（巴黎电信学院LTCI）；Institut Polytechnique de Paris（巴黎理工学院）
Synthetic creation of drum sounds (e.g., in drum machines) is commonly performed using analog or digital synthesis, allowing a musician to sculpt the desired timbre modifying various parameters. Typically, such parameters control low-level features of the sound and often have no musical meaning or perceptual correspondence. With the rise of Deep Learning, data-driven processing of audio emerges as an alternative to traditional signal processing. This new paradigm allows controlling the synthesis process through learned high-level features or by conditioning a model on musically relevant inform…
College of Engineering, Trivandrum（特里凡得琅工程学院）；Govt. Engineering College, Barton Hill, Thiruvananthapuram（巴顿山政府工程学院）
The research in Environmental Sound Classification (ESC) has been progressively growing with the emergence of deep learning algorithms. However, data scarcity poses a major hurdle for any huge advance in this domain. Data augmentation offers an excellent solution to this problem. While Generative Adversarial Networks (GANs) have been successful in generating synthetic speech and sounds of musical instruments, they have hardly been applied to the generation of environmental sounds. This paper presents EnvGAN, the first ever application of GANs for the adversarial generation of environmental sou…
CNRS（法国国家科学研究中心）；Ecole Centrale Nantes（南特中央理工学院）；Nantes Université（南特大学）；Gaudio Lab, Inc.（Gaudio实验室公司）；KAIST（韩国科学技术院）；Carnegie Mellon University（卡内基梅隆大学）；New York University（纽约大学）；Doshisha University（同志社大学）；The University of Tokyo（东京大学）
Footsteps are among the most ubiquitous sound effects in multimedia applications. There is substantial research into understanding the acoustic features and developing synthesis models for footstep sound effects. In this paper, we present a first attempt at adopting neural synthesis for this task. We implemented two GAN-based architectures and compared the results with real recordings as well as six traditional sound synthesis methods. Our architectures reached realism scores as high as recorded samples, showing encouraging results for the task at hand.
The University of Tokyo（东京大学）；National Institute of Technology, Kagawa College（国立高等专门学校机构 香川高等专门学校）；Yamaha Corporation（雅马哈公司）
A differentiable digital signal processing (DDSP) autoencoder is a musical sound synthesizer that combines a deep neural network (DNN) and spectral modeling synthesis. It allows us to flexibly edit sounds by changing the fundamental frequency, timbre feature, and loudness (synthesis parameters) extracted from an input sound. However, it is designed for a monophonic harmonic sound and cannot handle mixtures of harmonic sounds. In this paper, we propose a model (DDSP mixture model) that represents a mixture as the sum of the outputs of multiple pretrained DDSP autoencoders. By fitting the output…
The rise of deep learning algorithms has led many researchers to withdraw from using classic signal processing methods for sound generation. Deep learning models have achieved expressive voice synthesis, realistic sound textures, and musical notes from virtual instruments. However, the most suitable deep learning architecture is still under investigation. The choice of architecture is tightly coupled to the audio representations. A sound's original waveform can be too dense and rich for deep learning models to deal with efficiently - and complexity increases training time and computational cos…
Sony Computer Science Laboratories（索尼计算机科学实验室）；National Institute of Applied Sciences, Lyon（里昂国立应用科学学院）
In contemporary popular music production, drum sound design is commonly performed by cumbersome browsing and processing of pre-recorded samples in sound libraries. One can also use specialized synthesis hardware, typically controlled through low-level, musically meaningless parameters. Today, the field of Deep Learning offers methods to control the synthesis process via learned high-level features and allows generating a wide variety of sounds. In this paper, we present DrumGAN VST, a plugin for synthesizing drum sounds using a Generative Adversarial Network. DrumGAN VST operates on 44.1 kHz s…
Gaudio Lab, Inc.（高迪奥实验室公司）；New York University（纽约大学）
"Foley" refers to sound effects that are added to multimedia during post-production to enhance its perceived acoustic properties, e.g., by simulating the sounds of footsteps, ambient environmental sounds, or visible objects on the screen. While foley is traditionally produced by foley artists, there is increasing interest in automatic or machine-assisted techniques building upon recent advances in sound synthesis and generative models. To foster more participation in this growing research area, we propose a challenge for automatic foley synthesis. Through case studies on successful previous ch…
Queen Mary University of London（伦敦玛丽女王大学）；Native Instruments GmbH（Native Instruments 有限公司）；Nemisindo Ltd（Nemisindo 有限公司）
A recent comparative study evaluated all known thunder synthesis techniques in terms of their perceptual realness. The findings concluded that none of the synthesised audio extracts seemed as realistic as the genuine phenomenon. The work presented herein is motivated by those findings, and attempts to create a synthesised sound effect of thunder indistinguishable from a real recording. The technique supplements an existing implementation with physics-inspired, signal-based design elements intended to simulate environmental occurrences. In a listening test conducted with over 50 participants, t…
We propose GANStrument, a generative adversarial model for instrument sound synthesis. Given a one-shot sound as input, it is able to generate pitched instrument sounds that reflect the timbre of the input within an interactive time. By exploiting instance conditioning, GANStrument achieves better fidelity and diversity of synthesized sounds and generalization ability to various inputs. In addition, we introduce an adversarial training scheme for a pitch-invariant feature extractor that significantly improves the pitch accuracy and timbre consistency. Experimental results show that GANStrument…
Peking University（北京大学）；University of Maryland at College Park（马里兰大学帕克分校）
We present a novel learning-based modal sound synthesis approach that includes a mixed vibration solver for modal analysis and an end-to-end sound radiation network for acoustic transfer. Our mixed vibration solver consists of a 3D sparse convolution network and a Locally Optimal Block Preconditioned Conjugate Gradient module (LOBPCG) for iterative optimization. Moreover, we highlight the correlation between a standard modal vibration solver and our network architecture. Our radiation network predicts the Far-Field Acoustic Transfer maps (FFAT Maps) from the surface vibration of the object. Th…
Tianjin University（天津大学）；University of Maryland at College Park（马里兰大学帕克分校）
Sound, as a crucial sensory channel, plays a vital role in improving the reality and immersiveness of a virtual environment, following only vision in importance. Sound can provide important clues such as sound directionality and spatial size. This paper gives a broad overview of research works on sound simulation in virtual reality, games, multimedia, computer-aided design. We first survey various sound synthesis methods, including harmonic synthesis, texture synthesis, spectral analysis, and physics-based synthesis. Then, we summarize popular sound propagation techniques, namely wave-based me…
Lecture notes of a tutorial on topology in sound synthesis and digital signal processing held at international conference for digital audio effects (DAFx-22) in Vienna, Austria.
Physical models of rigid bodies are used for sound synthesis in applications from virtual environments to music production. Traditional methods such as modal synthesis often rely on computationally expensive numerical solvers, while recent deep learning approaches are limited by post-processing of their results. In this work we present a novel end-to-end framework for training a deep neural network to generate modal resonators for a given 2D shape and material, using a bank of differentiable IIR filters. We demonstrate our method on a dataset of synthetic objects, but train our model using an …
A new impulse response (IR) dataset called "MeshRIR" is introduced. Currently available datasets usually include IRs at an array of microphones from several source positions under various room conditions, which are basically designed for evaluating speech enhancement and distant speech recognition methods. On the other hand, methods of estimating or controlling spatial sound fields have been extensively investigated in recent years; however, the current IR datasets are not applicable to validating and comparing these methods because of the low spatial resolution of measurement points. MeshRIR …
In this paper we introduce StyleWaveGAN, a style-based drum sound generator that is a variation of StyleGAN, a state-of-the-art image generator. By conditioning StyleWaveGAN on both the type of drum and several audio descriptors, we are able to synthesize waveforms faster than real-time on a GPU directly in CD quality up to a duration of 1.5s while retaining a considerable amount of control over the generation. We also introduce an alternative to the progressive growing of GANs and experimented on the effect of dataset balancing for generative tasks. The experiments are carried out on an augme…
Massachusetts Institute of Technology（麻省理工学院）；University of Iowa（爱荷华大学）
Sustained contact interactions like scraping and rolling produce a wide variety of sounds. Previous studies have explored ways to synthesize these sounds efficiently and intuitively but could not fully mimic the rich structure of real instances of these sounds. We present a novel source-filter model for realistic synthesis of scraping and rolling sounds with physically and perceptually relevant controllable parameters constrained by principles of mechanics. Key features of our model include non-linearities to constrain the contact force, naturalistic normal force variation for different motion…
Sony CSL（索尼计算机科学实验室）；CentraleSupélec（巴黎中央理工-高等电力学院）
In this paper, we propose a novel score-base generative model for unconditional raw audio synthesis. Our proposal builds upon the latest developments on diffusion process modeling with stochastic differential equations, which already demonstrated promising results on image generation. We motivate novel heuristics for the choice of the diffusion processes better suited for audio generation, and consider the use of a conditional U-Net to approximate the score function. While previous approaches on diffusion models on audio were mainly designed as speech vocoders in medium resolution, our method …
IRCAM（法国声学音乐协调及研究中心）；CNRS（法国国家科学研究中心）；The University of Tokyo（东京大学）；RIKEN（日本理化学研究所）
Granular sound synthesis is a popular audio generation technique based on rearranging sequences of small waveform windows. In order to control the synthesis, all grains in a given corpus are analyzed through a set of acoustic descriptors. This provides a representation reflecting some form of local similarities across the grains. However, the quality of this grain space is bound by that of the descriptors. Its traversal is not continuously invertible to signal and does not render any structured temporality. We demonstrate that generative neural networks can implement granular synthesis while a…
University of York（约克大学）；Sony Interactive Entertainment Europe（索尼互动娱乐欧洲公司）；Music Artificial Intelligence Algorithms, Inc.（音乐人工智能算法公司）
Single-image generative adversarial networks learn from the internal distribution of a single training example to generate variations of it, removing the need of a large dataset. In this paper we introduce SpecSinGAN, an unconditional generative architecture that takes a single one-shot sound effect (e.g., a footstep; a character jump) and produces novel variations of it, as if they were different takes from the same recording session. We explore the use of multi-channel spectrograms to train the model on the various layers that comprise a single sound effect. A listening study comparing our m…
A Recurrent Neural Network (RNN) for audio synthesis is trained by augmenting the audio input with information about signal characteristics such as pitch, amplitude, and instrument. The result after training is an audio synthesizer that is played like a musical instrument with the desired musical characteristics provided as continuous parametric control. The focus of this paper is on conditioning data-driven synthesis models with real-valued parameters, and in particular, on the ability of the system a) to generalize and b) to be responsive to parameter values and sequences not seen during tra…
Ritsumeikan University（立命馆大学）；Doshisha University（同志社大学）；The University of Tokyo（东京大学）
Although several methods of environmental sound synthesis have been proposed, there has been no discussion on how synthesized environmental sounds should be evaluated. Only either subjective or objective evaluations have been conducted in conventional evaluations, and it is not clear what type of evaluation should be carried out. In this paper, we investigate how to evaluate synthesized environmental sounds. We also propose a subjective evaluation methodology to evaluate whether the synthesized sound appropriately represents the information input to the environmental sound synthesis system. In…
Spatial Analysis and Synthesis Methods: Subjective and Objective Evaluations Using Various Microphone Arrays in the Auralization of a Critical Listening Room
University of Huddersfield（哈德斯菲尔德大学）；Genelec OY（吉力科技公司）
Sound synthesiser controls typically correspond to technical parameters of signal processing algorithms rather than intuitive sound descriptors that relate to human perception of sound. This makes it difficult to realise sound ideas in a straightforward way. Cross-modal mappings, for example between gestures and sound, have been suggested as a more intuitive control mechanism. A large body of research shows consistency in human associations between sounds and shapes. However, the use of drawings to drive sound synthesis has not been explored to its full extent. This paper presents an explorato…
Kyungpook National University（庆北国立大学）；Electronics and Telecommunications Research Institute（韩国电子通信研究院）
Deep generative models for audio synthesis have recently been significantly improved. However, the task of modeling raw-waveforms remains a difficult problem, especially for audio waveforms and music signals. Recently, the realtime audio variational autoencoder (RAVE) method was developed for high-quality audio waveform synthesis. The RAVE method is based on the variational autoencoder and utilizes the two-stage training strategy. Unfortunately, the RAVE model is limited in reproducing wide-pitch polyphonic music sound. Therefore, to enhance the reconstruction performance, we adopt the pitch a…
Quantum computing is emerging as an alternative computing technology, which is built on the principles of subatomic physics. In spite of continuing progress in developing increasingly more sophisticated hardware and software, access to quantum computing still requires specialist expertise that is largely confined to research laboratories. Moreover, the target applications for these developments remain primarily scientific. This chapter introduces research aimed at improving this scenario. Our research is aimed at extending the range of applications of quantum computing towards the arts and cre…
