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 Modeling the Frequency-Dependent Sound Energy Decay of Acoustic Environments with Differentiable Feedback Delay Networks Differentiable machine learning techniques have recently proved effective for finding the parameters of Feedback Delay Networks (FDNs) so that their output matches desired perceptual qualities of target room impulse responses. However, we show that existing methods tend to fail at modeling the frequency-dependent behavior of sound energy decay that characterizes real-world environments unless properly trained. In this paper, we introduce a novel perceptual loss function based on the mel-scale energy decay relief, which generalizes the well-known time-domain energy decay curve to multiple frequency bands. We also augment the prototype FDN by incorporating differentiable wideband attenuation and output filters, and train them via backpropagation along with the other model parameters. The proposed approach improves upon existing strategies for designing and training differentiable FDNs, making it more suitable for audio processing applications where realistic and controllable artificial reverberation is desirable, such as gaming, music production, and virtual reality.
Download A Hierarchical Deep Learning Approach for Minority Instrument Detection Identifying instrument activities within audio excerpts is vital in music information retrieval, with significant implications for music cataloging and discovery. Prior deep learning endeavors in musical instrument recognition have predominantly emphasized instrument classes with ample data availability. Recent studies have demonstrated the applicability of hierarchical classification in detecting instrument activities in orchestral music, even with limited fine-grained annotations at the instrument level. Based on the Hornbostel-Sachs classification, such a hierarchical classification system is evaluated using the MedleyDB dataset, renowned for its diversity and richness concerning various instruments and music genres. This work presents various strategies to integrate hierarchical structures into models and tests a new class of models for hierarchical music prediction. This study showcases more reliable coarse-level instrument detection by bridging the gap between detailed instrument identification and group-level recognition, paving the way for further advancements in this domain.
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 Guitar Tone Stack Modeling with a Neural State-Space Filter In this work, we present a data-driven approach to modeling tone stack circuits in guitar amplifiers and distortion pedals. To this aim, the proposed modeling approach uses a feedforward fully connected neural network to predict the parameters of a coupledform state-space filter, ensuring the numerical stability of the resulting time-varying system. The neural network is conditioned on the tone controls of the target tone stack and is optimized jointly with the coupled-form state-space filter to match the target frequency response. To assess the proposed approach, we model three popular tone stack schematics with both matched-order and overparameterized filters and conduct an objective comparison with well-established approaches that use cascaded biquad filters. Results from the conducted experiments demonstrate improved accuracy of the proposed modeling approach, especially in the case of over-parameterized state-space filters while guaranteeing numerical stability. Our method can be deployed, after training, in realtime audio processors.
Download A Deep Learning Approach to the Prediction of Time-Frequency Spatial Parameters for Use in Stereo Upmixing This paper presents a deep learning approach to parametric timefrequency parameter prediction for use within stereo upmixing algorithms. The approach presented uses a Multi-Channel U-Net with Residual connections (MuCh-Res-U-Net) trained on a novel dataset of stereo and parametric time-frequency spatial audio data to predict time-frequency spatial parameters from a stereo input signal for positions on a 50-point Lebedev quadrature sampled sphere. An example upmix pipeline is then proposed which utilises the predicted time-frequency spatial parameters to both extract and remap stereo signal components to target spherical harmonic components to facilitate the generation of a full spherical representation of the upmixed sound field.
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.
Download HRTF Spatial Upsampling in the Spherical Harmonics Domain Employing a Generative Adversarial Network A Head-Related Transfer Function (HRTF) is able to capture alterations a sound wave undergoes from its source before it reaches the entrances of a listener’s left and right ear canals, and is imperative for creating immersive experiences in virtual and augmented reality (VR/AR). Nevertheless, creating personalized HRTFs demands sophisticated equipment and is hindered by time-consuming data acquisition processes. To counteract these challenges, various techniques for HRTF interpolation and up-sampling have been proposed. This paper illustrates how Generative Adversarial Networks (GANs) can be applied to HRTF data upsampling in the spherical harmonics domain. We propose using Autoencoding Generative Adversarial Networks (AE-GAN) to upsample lowdegree spherical harmonics coefficients and get a more accurate representation of the full HRTF set. The proposed method is benchmarked against two baselines: barycentric interpolation and HRTF selection. Results from log-spectral distortion (LSD) evaluation suggest that the proposed AE-GAN has significant potential for upsampling very sparse HRTFs, achieving 17% improvement over baseline methods.
Download LTFATPY: Towards Making a Wide Range of Time-Frequency Representations Available in Python LTFATPY is a software package for accessing the Large Time Frequency Analysis Toolbox (LTFAT) from Python. Dedicated to time-frequency analysis, LTFAT comprises a large number of linear transforms for Fourier, Gabor, and wavelet analysis along with their associated operators. Its filter bank module is a collection of computational routines for finite impulse response and band-limited filters, allowing for the specification of constant-Q and auditory-inspired transforms. While LTFAT has originally been written in MATLAB/GNU Octave, the recent popularity of the Python programming language in related fields, such as signal processing and machine learning, makes it desirable to have LTFAT available in Python as well. We introduce LTFATPY, describe its main features, and outline further developments.
Download Sound Matching Using Synthesizer Ensembles Sound matching allows users to automatically approximate existing sounds using a synthesizer. Previous work has mostly focused on algorithms for automatically programming an existing synthesizer. This paper proposes a system for selecting between different synthesizer designs, each one with a corresponding automatic programmer. An implementation that allows designing ensembles based on a template is demonstrated. Several experiments are presented using a simple subtractive synthesis design. Using an ensemble of synthesizer-programmer pairs is shown to provide better matching than a single programmer trained for an equivalent integrated synthesizer. Scaling to hundreds of synthesizers is shown to improve match quality.