Download Polyphonic music analysis by signal processing and support vector machines
In this paper an original system for the analysis of harmony and polyphonic music is introduced. The system is based on signal processing and machine learning. A new multi-resolution, fast analysis method is conceived to extract time-frequency energy spectrum at the signal processing stage, while support vector machine is used as machine learning technology. Aiming at the analysis of rather general audio content, experiments are made on a huge set of recorded samples, using 19 music instruments combined together or alone, with different polyphony. Experimental results show that fundamental frequencies are detected with a remarkable success ratio and that the method can provide excellent results in general cases.
Download Differentiable grey-box modelling of phaser effects using frame-based spectral processing
Machine learning approaches to modelling analog audio effects have seen intensive investigation in recent years, particularly in the context of non-linear time-invariant effects such as guitar amplifiers. For modulation effects such as phasers, however, new challenges emerge due to the presence of the low-frequency oscillator which controls the slowly time-varying nature of the effect. Existing approaches have either required foreknowledge of this control signal, or have been non-causal in implementation. This work presents a differentiable digital signal processing approach to modelling phaser effects in which the underlying control signal and time-varying spectral response of the effect are jointly learned. The proposed model processes audio in short frames to implement a time-varying filter in the frequency domain, with a transfer function based on typical analog phaser circuit topology. We show that the model can be trained to emulate an analog reference device, while retaining interpretable and adjustable parameters. The frame duration is an important hyper-parameter of the proposed model, so an investigation was carried out into its effect on model accuracy. The optimal frame length depends on both the rate and transient decay-time of the target effect, but the frame length can be altered at inference time without a significant change in accuracy.
Download A Real-Time Synthesis Oriented Tanpura Model
Physics-based synthesis of tanpura drones requires accurate simulation of stiff, lossy string vibrations while incorporating sustained contact with the bridge and a cotton thread. Several challenges arise from this when seeking efficient and stable algorithms for real-time sound synthesis. The approach proposed here to address these combines modal expansion of the string dynamics with strategic simplifications regarding the string-bridge and stringthread contact, resulting in an efficient and provably stable timestepping scheme with exact modal parameters. Attention is given also to the physical characterisation of the system, including string damping behaviour, body radiation characteristics, and determination of appropriate contact parameters. Simulation results are presented exemplifying the key features of the model.
Download Fast Temporal Convolutions for Real-Time Audio Signal Processing
This paper introduces the possibilities of optimizing neural network convolutional layers for modeling nonlinear audio systems and effects. Enhanced methods for real-time dilated convolutions are presented to achieve faster signal processing times than in previous work. Due to the improved implementation of convolutional layers, a significant decrease in computational requirements was observed and validated on different configurations of single layers with dilated convolutions and WaveNet-style feedforward neural network models. In most cases, equivalent signal processing times were achieved to those using recurrent neural networks with Long Short-Term Memory units and Gated Recurrent Units, which are considered state-of-the-art in the field of black-box virtual analog modeling.
Download A Physical String Model with Adjustable Boundary Conditions
The vibration of strings in musical instruments depends not only on their geometry and material but also on their fixing at the ends of the string. In physical terms it is described by impedance boundary conditions. This contribution presents a functional transformation model for a vibrating string which is coupled to an external boundary circuit. Delay-free loops in the synthesis algorithm are avoided by a state-space formulation. The value of the boundary impedance can be adjusted without altering the core synthesis algorithm.
Download Real-time Physical Model of a Wurlitzer and Rhodes Electronic Piano
Two well known examples of electro-acoustical keyboards played since the 60s to the present day are the Wurlitzer electric piano and the Rhodes piano. They are used in such diverse musical genres as Jazz, Funk, Fusion or Pop as well as in modern Electronic and Dance music. Due to the popularity of their unique sound and timbre, there exist various hardware and software emulations which are either based on a physical model or consist of a sample based method for sound generation. In this paper, a real-time physical model implementation of both instruments using field programmable gate array (FPGA) hardware is presented. The work presented herein is an extension of simplified models published before. Both implementations consist of a physical model of the main acoustic sound production parts as well as a model for the electromagnetic pickup system. Both models are compared to a series of measurements and show good accordance with their analog counterparts.
Download Automatic Decomposition of Non-linear Equation Systems in Audio Effect Circuit Simulation
In the digital simulation of non-linear audio effect circuits, the arising non-linear equation system generally poses the main challenge for a computationally cheap implementation. As the computational complexity grows super-linearly with the number of equations, it is beneficial to decompose the equation system into several smaller systems, if possible. In this paper we therefore develop an approach to determine such a decomposition automatically. We limit ourselves to cases where an exact decomposition is possible, however, and do not consider approximate decompositions.
Download MOSPALOSEP: A Platform for the Binaural Localization and Separation of Spatial Sounds using Models of Interaural Cues and Mixture Models
In this paper, we present the MOSPALOSEP platform for the localization and separation of binaural signals. Our methods use short-time spectra of the recorded binaural signals. Based on a parametric model of the binaural mix, we exploit the joint evaluation of interaural cues to derive the location of each time-frequency bin. Then we describe different approaches to establish localization: some based on an energy-weighted histogram in azimuth space, and others based on an unsupervised number of sources identification of Gaussian mixture model combined with the Minimum Description Length. In this way, we use the revealed Gaussian Mixture Model structure to identify the particular region dominated by each source in a multi-source mix. A bank of spatial masks allows the extraction of each source according to the posterior probability or to the Maximum Likelihood binary masks. An important condition is the Windowed-Disjoint Orthogonality of the sources in the time-frequency domain. We assess the source separation algorithms specifically on instruments mix, where this fundamental condition is not satisfied.
Download Harmonic/Percussive Separation using Median Filtering
In this paper, we present a fast, simple and effective method to separate the harmonic and percussive parts of a monaural audio signal. The technique involves the use of median filtering on a spectrogram of the audio signal, with median filtering performed across successive frames to suppress percussive events and enhance harmonic components, while median filtering is also performed across frequency bins to enhance percussive events and supress harmonic components. The two resulting median filtered spectrograms are then used to generate masks which are then applied to the original spectrogram to separate the harmonic and percussive parts of the signal. We illustrate the use of the algorithm in the context of remixing audio material from commercial recordings.
Download Sound Source Separation: Preprocessing For Hearing Aids And Structured Audio Codin
In this paper we consider the problem of separating different sound sources in multichannel audio signals. Different approaches to the problem of Blind Source Separation (BSS), e.g. the Independent Component Analysis (ICA) originally proposed by Herault and Jutten, and extensions to this including delays, work fine for artificially mixed signals. However the quality of the separated signals is severely degraded for real sound recordings when there is reverberation. We consider the system with 2 sources and 2 sensors, and show how we can improve the quality of the separation by a simple model of the audio scene. More specifically we estimate the delays between the sensor signals, and put constraints on the deconvolution coefficients.