Srđan Kitić

Srđan Kitić, Jérôme Daniel

We introduce and analyze Generalized Time Domain Velocity Vector (GTVV), an extension of the previously presented acoustic multipath footprint extracted from the Ambisonic recordings. GTVV is better adapted to adverse acoustic conditions, and enables efficient parameter estimation of multiple plane wave components in the recorded multichannel mixture. Experiments on simulated data confirm the predicted theoretical advantages of these new spatio-temporal features.

Pierre-Amaury Grumiaux, Srđan Kitić, Laurent Girin et al.

This article is a survey on deep learning methods for single and multiple sound source localization. We are particularly interested in sound source localization in indoor/domestic environment, where reverberation and diffuse noise are present. We provide an exhaustive topography of the neural-based localization literature in this context, organized according to several aspects: the neural network architecture, the type of input features, the output strategy (classification or regression), the types of data used for model training and evaluation, and the model training strategy. This way, an interested reader can easily comprehend the vast panorama of the deep learning-based sound source localization methods. Tables summarizing the literature survey are provided at the end of the paper for a quick search of methods with a given set of target characteristics.

Pierre-Amaury Grumiaux, Srdan Kitic, Prerak Srivastava et al.

In this work, we propose a novel self-attention based neural network for robust multi-speaker localization from Ambisonics recordings. Starting from a state-of-the-art convolutional recurrent neural network, we investigate the benefit of replacing the recurrent layers by self-attention encoders, inherited from the Transformer architecture. We evaluate these models on synthetic and real-world data, with up to 3 simultaneous speakers. The obtained results indicate that the majority of the proposed architectures either perform on par, or outperform the CRNN baseline, especially in the multisource scenario. Moreover, by avoiding the recurrent layers, the proposed models lend themselves to parallel computing, which is shown to produce considerable savings in execution time.

Pierre-Amaury Grumiaux, Srdan Kitic, Laurent Girin et al.

In this work, we propose to extend a state-of-the-art multi-source localization system based on a convolutional recurrent neural network and Ambisonics signals. We significantly improve the performance of the baseline network by changing the layout between convolutional and pooling layers. We propose several configurations with more convolutional layers and smaller pooling sizes in-between, so that less information is lost across the layers, leading to a better feature extraction. In parallel, we test the system's ability to localize up to 3 sources, in which case the improved feature extraction provides the most significant boost in accuracy. We evaluate and compare these improved configurations on synthetic and real-world data. The obtained results show a quite substantial improvement of the multiple sound source localization performance over the baseline network.

Pierre-Amaury Grumiaux, Srdan Kitic, Laurent Girin et al.

Speaker counting is the task of estimating the number of people that are simultaneously speaking in an audio recording. For several audio processing tasks such as speaker diarization, separation, localization and tracking, knowing the number of speakers at each timestep is a prerequisite, or at least it can be a strong advantage, in addition to enabling a low latency processing. In a previous work, we addressed the speaker counting problem with a multichannel convolutional recurrent neural network which produces an estimation at a short-term frame resolution. In this work, we show that, for a given frame, there is an optimal position in the input sequence for best prediction accuracy. We empirically demonstrate the link between that optimal position, the length of the input sequence and the size of the convolutional filters.

Jérôme Daniel, Srđan Kitić

We propose a conceptually and computationally simple form of sound velocity that offers a readable view of the interference between direct and indirect sound waves. Unlike most approaches in the literature, it jointly exploits both active and reactive sound intensity measurements, as typically derived from a first order ambisonics recording. This representation has a potential both as a valuable tool for directly analyzing sound multipath propagation, as well as being a new spatial feature format for machine learning algorithms in audio and acoustics. As a showcase, we demonstrate that the Direction-Of-Arrival and the range of a sound source can be estimated as a development of this approach. To the best knowledge of the authors, this is the first time that range is estimated from an ambisonics recording.

Amélie Bosca, Alexandre Guérin, Lauréline Perotin et al.

We present a CNN architecture for speech enhancement from multichannel first-order Ambisonics mixtures. The data-dependent spatial filters, deduced from a mask-based approach, are used to help an automatic speech recognition engine to face adverse conditions of reverberation and competitive speakers. The mask predictions are provided by a neural network, fed with rough estimations of speech and noise amplitude spectra, under the assumption of known directions of arrival. This study evaluates the replacing of the recurrent LSTM network previously investigated by a convolutive U-net under more stressing conditions with an additional second competitive speaker. We show that, due to more accurate short-term masks prediction, the U-net architecture brings some improvements in terms of word error rate. Moreover, results indicate that the use of dilated convolutive layers is beneficial in difficult situations with two interfering speakers, and/or where the target and interferences are close to each other in terms of the angular distance. Moreover, these results come with a two-fold reduction in the number of parameters.

Clément Gaultier, Srđan Kitić, Rémi Gribonval et al.

Recent advances in audio declipping have substantially improved the state of the art.% in certain saturation regimes. Yet, practitioners need guidelines to choose a method, and while existing benchmarks have been instrumental in advancing the field, larger-scale experiments are needed to guide such choices. First, we show that the clipping levels in existing small-scale benchmarks are moderate and call for benchmarks with more perceptually significant clipping levels. We then propose a general algorithmic framework for declipping that covers existing and new combinations of variants of state-of-the-art techniques exploiting time-frequency sparsity: synthesis vs. analysis sparsity, with plain or structured sparsity. Finally, we systematically compare these combinations and a selection of state-of-the-art methods. Using a large-scale numerical benchmark and a smaller scale formal listening test, we provide guidelines for various clipping levels, both for speech and various musical genres. The code is made publicly available for the purpose of reproducible research and benchmarking.

Srđan Kitić, Gilles Puy, Patrick Pérez et al.

We consider the problem of identifying people on the basis of their walk (gait) pattern. Classical approaches to tackle this problem are based on, e.g., video recordings or piezoelectric sensors embedded in the floor. In this work, we rely on acoustic and vibration measurements, obtained from a microphone and a geophone sensor, respectively. The contribution of this work is twofold. First, we propose a feature extraction method based on an (untrained) shallow scattering network, specially tailored for the gait signals. Second, we demonstrate that fusing the two modalities improves identification in the practically relevant open set scenario.

Srđan Kitić, Clément Gaultier, Grégory Pallone

In this article we analyze the state-of-the-art in multilateration - the family of localization methods enabled by the range difference observations. These methods are computationally efficient, signal-independent, and flexible with regards to the number of sensing nodes and their spatial arrangement. However, the multilateration problem does not admit a closed-form solution in the general case, and the localization performance is conditioned on the accuracy of range difference estimates. For that reason, we consider a simplified use case where multiple distributed microphones capture the signal coming from a near field sound source, and discuss their robustness to the estimation errors. In addition to surveying the relevant bibliography, we present the results of a small-scale benchmark of few "mainstream" multilateration algorithms, based on an in-house Room Impulse Response dataset.

Srđan Kitić, Alexandre Guérin

This article presents a multiple sound source localization and tracking system, fed by the Eigenmike array. The First Order Ambisonics (FOA) format is used to build a pseudointensity-based spherical histogram, from which the source position estimates are deduced. These instantaneous estimates are processed by a wellknown tracking system relying on a set of particle filters. While the novelty within localization and tracking is incremental, the fully-functional, complete and real-time running system based on these algorithms is proposed for the first time. As such, it could serve as an additional baseline method of the LOCATA challenge.

Clément Gaultier, Nancy Bertin, Srđan Kitić et al.

We propose a unified modeling and algorithmic framework for audio restoration problem. It encompasses analysis sparse priors as well as more classical synthesis sparse priors, and regular sparsity as well as various forms of structured sparsity embodied by shrinkage operators (such as social shrinkage). The versatility of the framework is illustrated on two restoration scenarios: denoising, and declipping. Extensive experimental results on these scenarios highlight both the speedups of 20% or even more offered by the analysis sparse prior, and the substantial declipping quality that is achievable with both the social and the plain flavor. While both flavors overall exhibit similar performance, their detailed comparison displays distinct trends depending whether declipping or denoising is considered.

Gilles Puy, Srdan Kitic, Patrick Pérez

This paper deals with the unification of local and non-local signal processing on graphs within a single convolutional neural network (CNN) framework. Building upon recent works on graph CNNs, we propose to use convolutional layers that take as inputs two variables, a signal and a graph, allowing the network to adapt to changes in the graph structure. In this article, we explain how this framework allows us to design a novel method to perform style transfer.

Srđan Kitić, Nancy Bertin, Rémi Gribonval

This work investigates the empirical performance of the sparse synthesis versus sparse analysis regularization for the ill-posed inverse problem of audio declipping. We develop a versatile non-convex heuristics which can be readily used with both data models. Based on this algorithm, we report that, in most cases, the two models perform almost similarly in terms of signal enhancement. However, the analysis version is shown to be amenable for real time audio processing, when certain analysis operators are considered. Both versions outperform state-of-the-art methods in the field, especially for the severely saturated signals.

Srdjan Kitić, Laurent Jacques, Nilesh Madhu et al.

Clipping or saturation in audio signals is a very common problem in signal processing, for which, in the severe case, there is still no satisfactory solution. In such case, there is a tremendous loss of information, and traditional methods fail to appropriately recover the signal. We propose a novel approach for this signal restoration problem based on the framework of Iterative Hard Thresholding. This approach, which enforces the consistency of the reconstructed signal with the clipped observations, shows superior performance in comparison to the state-of-the-art declipping algorithms. This is confirmed on synthetic and on actual high-dimensional audio data processing, both on SNR and on subjective user listening evaluations.