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 NBU: Neural Binaural Upmixing of Stereo Content While immersive music productions have become popular in recent years, music content produced during the last decades has been predominantly mixed for stereo. This paper presents a datadriven approach to automatic binaural upmixing of stereo music. The network architecture HDemucs, previously utilized for both source separation and binauralization, is leveraged for an endto-end approach to binaural upmixing. We employ two distinct datasets, demonstrating that while custom-designed training data enhances the accuracy of spatial positioning, the use of professionally mixed music yields superior spatialization. The trained networks show a capacity to process multiple simultaneous sources individually and add valid binaural cues, effectively positioning sources with an average azimuthal error of less than 11.3 ◦ . A listening test with binaural experts shows it outperforms digital signal processing-based approaches to binauralization of stereo content in terms of spaciousness while preserving audio quality.
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 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 Wave Digital Modeling of Circuits with Multiple One-Port Nonlinearities Based on Lipschitz-Bounded Neural Networks Neural networks have found application within the Wave Digital Filters (WDFs) framework as data-driven input-output blocks for modeling single one-port or multi-port nonlinear devices in circuit systems. However, traditional neural networks lack predictable bounds for their output derivatives, essential to ensure convergence when simulating circuits with multiple nonlinear elements using fixed-point iterative methods, e.g., the Scattering Iterative Method (SIM). In this study, we address such issue by employing Lipschitz-bounded neural networks for regressing nonlinear WD scattering relations of one-port nonlinearities.
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 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.
Download Binaural Dark-Velvet-Noise Reverberator Binaural late-reverberation modeling necessitates the synthesis of frequency-dependent inter-aural coherence, a crucial aspect of spatial auditory perception. Prior studies have explored methodologies such as filtering and cross-mixing two incoherent late reverberation impulse responses to emulate the coherence observed in measured binaural late reverberation. In this study, we introduce two variants of the binaural dark-velvet-noise reverberator. The first one uses cross-mixing of two incoherent dark-velvet-noise sequences that can be generated efficiently. The second variant is a novel time-domain jitter-based approach. The methods’ accuracies are assessed through objective and subjective evaluations, revealing that both methods yield comparable performance and clear improvements over using incoherent sequences. Moreover, the advantages of the jitter-based approach over cross-mixing are highlighted by introducing a parametric width control, based on the jitter-distribution width, into the binaural dark velvet noise reverberator. The jitter-based approach can also introduce timedependent coherence modifications without additional computational cost.
Download Audio Effect Chain Estimation and Dry Signal Recovery From Multi-Effect-Processed Musical Signals In this paper we propose a method that can address a novel task, audio effect (AFX) chain estimation and dry signal recovery. AFXs are indispensable in modern sound design workflows. Sound engineers often cascade different AFXs (as an AFX chain) to achieve their desired soundscapes. Given a multi-AFX-applied solo instrument performance (wet signal), our method can automatically estimate the applied AFX chain and recover its unprocessed dry signal, while previous research only addresses one of them. The estimated chain is useful for novice engineers in learning practical usages of AFXs, and the recovered signal can be reused with a different AFX chain. To solve this task, we first develop a deep neural network model that estimates the last-applied AFX and undoes its AFX at a time. We then iteratively apply the same model to estimate the AFX chain and eventually recover the dry signal from the wet signal. Our experiments on guitar phrase recordings with various AFX chains demonstrate the validity of our method for both the AFX-chain estimation and dry signal recovery. We also confirm that the input wet signal can be reproduced by applying the estimated AFX chain to the recovered dry signal.
Download Hyper Recurrent Neural Network: Condition Mechanisms for Black-Box Audio Effect Modeling Recurrent neural networks (RNNs) have demonstrated impressive results for virtual analog modeling of audio effects. These networks process time-domain audio signals using a series of matrix multiplication and nonlinear activation functions to emulate the behavior of the target device accurately. To additionally model the effect of the knobs for an RNN-based model, existing approaches integrate control parameters by concatenating them channel-wisely with some intermediate representation of the input signal. While this method is parameter-efficient, there is room to further improve the quality of generated audio because the concatenation-based conditioning method has limited capacity in modulating signals. In this paper, we propose three novel conditioning mechanisms for RNNs, tailored for black-box virtual analog modeling. These advanced conditioning mechanisms modulate the model based on control parameters, yielding superior results to existing RNN- and CNN-based architectures across various evaluation metrics.