Download Generative timbre spaces: regularizing variational auto-encoders with perceptual metrics Timbre spaces have been used in music perception to study the perceptual relationships between instruments based on dissimilarity ratings. However, these spaces do not generalize to novel examples and do not provide an invertible mapping, preventing audio synthesis. In parallel, generative models have aimed to provide methods for synthesizing novel timbres. However, these systems do not provide an understanding of their inner workings and are usually not related to any perceptually relevant information. Here, we show that Variational Auto-Encoders (VAE) can alleviate all of these limitations by constructing generative timbre spaces. To do so, we adapt VAEs to learn an audio latent space, while using perceptual ratings from timbre studies to regularize the organization of this space. The resulting space allows us to analyze novel instruments, while being able to synthesize audio from any point of this space. We introduce a specific regularization allowing to enforce any given similarity distances onto these spaces. We show that the resulting space provide almost similar distance relationships as timbre spaces. We evaluate several spectral transforms and show that the Non-Stationary Gabor Transform (NSGT) provides the highest correlation to timbre spaces and the best quality of synthesis. Furthermore, we show that these spaces can generalize to novel instruments and can generate any path between instruments to understand their timbre relationships. As these spaces are continuous, we study how audio descriptors behave along the latent dimensions. We show that even though descriptors have an overall non-linear topology, they follow a locally smooth evolution. Based on this, we introduce a method for descriptor-based synthesis and show that we can control the descriptors of an instrument while keeping its timbre structure.
Download Solid State Bus-Comp: A Large-Scale and Diverse Dataset for Dynamic Range Compressor Virtual Analog Modeling Virtual Analog (VA) modeling aims to simulate the behavior
of hardware circuits via algorithms to replicate their tone digitally.
Dynamic Range Compressor (DRC) is an audio processing module
that controls the dynamics of a track by reducing and amplifying
the volumes of loud and quiet sounds, which is essential in music
production. In recent years, neural-network-based VA modeling has
shown great potential in producing high-fidelity models. However,
due to the lack of data quantity and diversity, their generalization
ability in different parameter settings and input sounds is still limited. To tackle this problem, we present Solid State Bus-Comp, the
first large-scale and diverse dataset for modeling the classical VCA
compressor — SSL 500 G-Bus. Specifically, we manually collected
175 unmastered songs from the Cambridge Multitrack Library. We
recorded the compressed audio in 220 parameter combinations,
resulting in an extensive 2528-hour dataset with diverse genres, instruments, tempos, and keys. Moreover, to facilitate the use of our
proposed dataset, we conducted benchmark experiments in various
open-sourced black-box and grey-box models, as well as white-box
plugins. We also conducted ablation studies in different data subsets to illustrate the effectiveness of the improved data diversity and
quantity. The dataset and demos are on our project page: https:
//www.yichenggu.com/SolidStateBusComp/.
Download Distortion Recovery: A Two-Stage Method for Guitar Effect Removal Removing audio effects from electric guitar recordings makes it easier for post-production and sound editing. An audio distortion recovery model not only improves the clarity of the guitar sounds but also opens up new opportunities for creative adjustments in mixing and mastering. While progress have been made in creating such models, previous efforts have largely focused on synthetic distortions that may be too simplistic to accurately capture the complexities seen in real-world recordings. In this paper, we tackle the task by using a dataset of guitar recordings rendered with commercial-grade audio effect VST plugins. Moreover, we introduce a novel two-stage methodology for audio distortion recovery. The idea is to firstly process the audio signal in the Mel-spectrogram domain in the first stage, and then use a neural vocoder to generate the pristine original guitar sound from the processed Mel-spectrogram in the second stage. We report a set of experiments demonstrating the effectiveness of our approach over existing methods, through both subjective and objective evaluation metrics.
Download Classification Of Music Signals In The Visual Domain With the huge increase in the availability of digital music, it has become more important to automate the task of querying a database of musical pieces. At the same time, a computational solution of this task might give us an insight into how humans perceive and classify music. In this paper, we discuss our attempts to classify music into three broad categories: rock, classical and jazz. We discuss the feature extraction process and the particular choice of features that we used- spectrograms and mel scaled cepstral coefficients (MFCC). We use the texture-of- texture models to generate feature vectors out of these. Together, these features are capable of capturing the frequency-power profile of the sound as the song proceeds. Finally, we attempt to classify the generated data using a variety of classifiers. we discuss our results and the inferences that can be drawn from them.
Download Differentiable MIMO Feedback Delay Networks for Multichannel Room Impulse Response Modeling Recently, with the advent of new performing headsets and goggles, the demand for Virtual and Augmented Reality applications has experienced a steep increase. In order to coherently navigate the virtual rooms, the acoustics of the scene must be emulated in the most accurate and efficient way possible. Amongst others, Feedback Delay Networks (FDNs) have proved to be valuable tools for tackling such a task. In this article, we expand and adapt a method recently proposed for the data-driven optimization of single-inputsingle-output FDNs to the multiple-input-multiple-output (MIMO) case for addressing spatial/space-time processing applications. By testing our methodology on items taken from two different datasets, we show that the parameters of MIMO FDNs can be jointly optimized to match some perceptual characteristics of given multichannel room impulse responses, overcoming approaches available in the literature, and paving the way toward increasingly efficient and accurate real-time virtual room acoustics rendering.
Download Audio-Visual Talker Localization in Video for Spatial Sound Reproduction Object-based audio production requires the positional metadata to be defined for each point-source object, including the key elements in the foreground of the sound scene. In many media production use cases, both cameras and microphones are employed to make recordings, and the human voice is often a key element. In this research, we detect and locate the active speaker in the video, facilitating the automatic extraction of the positional metadata of the talker relative to the camera’s reference frame. With the integration of the visual modality, this study expands upon our previous investigation focused solely on audio-based active speaker detection and localization. Our experiments compare conventional audio-visual approaches for active speaker detection that leverage monaural audio, our previous audio-only method that leverages multichannel recordings from a microphone array, and a novel audio-visual approach integrating vision and multichannel audio. We found the role of the two modalities to complement each other. Multichannel audio, overcoming the problem of visual occlusions, provides a double-digit reduction in detection error compared to audio-visual methods with single-channel audio. The combination of multichannel audio and vision further enhances spatial accuracy, leading to a four-percentage point increase in F1 score on the Tragic Talkers dataset. Future investigations will assess the robustness of the model in noisy and highly reverberant environments, as well as tackle the problem of off-screen speakers.
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 Dimensionality Reduction Techniques for Fear Emotion Detection from Speech In this paper, we propose to reduce the relatively high-dimension of pitch-based features for fear emotion recognition from speech. To do so, the K-nearest neighbors algorithm has been used to classify three emotion classes: fear, neutral and ’other emotions’. Many techniques of dimensionality reduction are explored. First of all, optimal features ensuring better emotion classification are determined. Next, several families of dimensionality reduction, namely PCA, LDA and LPP, are tested in order to reveal the suitable dimension range guaranteeing the highest overall and fear recognition rates. Results show that the optimal features group permits 93.34% and 78.7% as overall and fear accuracy rates respectively. Using dimensionality reduction, Principal Component Analysis (PCA) has given the best results: 92% as overall accuracy rate and 93.3% as fear recognition percentage.
Download Automatic Recognition of Cascaded Guitar Effects This paper reports on a new multi-label classification task for guitar effect recognition that is closer to the actual use case of guitar effect pedals. To generate the dataset, we used multiple clean guitar audio datasets and applied various combinations of 13 commonly used guitar effects. We compared four neural network structures: a simple Multi-Layer Perceptron as a baseline, ResNet models, a CRNN model, and a sample-level CNN model. The ResNet models achieved the best performance in terms of accuracy and robustness under various setups (with or without clean audio, seen or unseen dataset), with a micro F1 of 0.876 and Macro F1 of 0.906 in the hardest setup. An ablation study on the ResNet models further indicates the necessary model complexity for the task.
Download Study of Regularizations and Constraints in NMF-Based Drums Monaural Separation Drums modelling is of special interest in musical source separation because of its widespread presence in western popular music. Current research has often focused on drums separation without specifically modelling the other sources present in the signal. This paper presents an extensive study of the use of regularizations and constraints to drive the factorization towards the separation between percussive and non-percussive music accompaniment. The proposed regularizations control the frequency smoothness of the basis components and the temporal sparseness of the gains. We also evaluated the use of temporal constraints on the gains to perform the separation, using both ground truth manual annotations (made publicly available) and automatically extracted transients. Objective evaluation of the results shows that, while optimal regularizations are highly dependent on the signal, drum event position contains enough information to achieve a high quality separation.