arXiv subjects

Benoit Champagne

Publications and source records attributed to Benoit Champagne.

At least 19 recordsLinked to original sources

arXiv2026

Parallel Time-Band Mixing with Learned Observation-Adding for Robust ASR Front-Ends

Speech enhancement is often used as a front-end for robust ASR, yet recurrent temporal and cross-band modules introduce sequential dependencies that reduce parallel efficiency. In this paper, we present a sequence-parallel band-split enhancement front-end built on a Parallel Time-Band Mixer (PTBM) block that eliminates within-block recurrent unrolling. PTBM integrates intra-band temporal mixing and per-frame cross-band attention within a unified parallel architecture, enabling efficient contextual modeling across both time and frequency dimensions. The system retains the mask-plus-residual reconstruction interface and introduces learned Observation-Adding (LOA) to suppress ASR-sensitive artifacts without development-set tuning. Experiments on DNS Challenge and CHiME-4 with frozen Whisper back-ends show that the proposed front-end consistently reduces word error rate relative to recurrent band-split baselines while requiring only 0.96 M parameters and 0.58 GMAC/s for the front-end network.

cs.SD↗

arXiv2026

Beamformed Fingerprint-Based Transformer Network for Trajectory Estimation and Path Determination in Outdoor mmWave MIMO Systems

Radio transmissions in millimeter wave (mmWave) bands have gained significant interest for applications demanding precise device localization and trajectory estimation. This paper explores novel neural network (NN) architectures suitable for trajectory estimation and path determination in a mmWave multiple-input multiple-output (MIMO) outdoor system based on localization data from beamformed fingerprint (BFF). The NN architecture captures sequences of BFF signals from different users, and through the application of learning mechanisms, subsequently estimate their trajectories. In turn, this information is employed to find the shortest path to the target, thereby enabling more efficient navigation. Specifically, we propose a two-stage procedure for trajectory estimation and optimal path finding. In the first stage, a transformer network (TN) based on attention mechanisms is developed to predict trajectories of wireless devices using BFF sequences captured in a mmWave MIMO outdoor system. In the second stage, a novel algorithm based on Informed Rapidly-exploring Random Trees (iRRT*) is employed to determine the optimal path to target locations using trajectory estimates derived in the first stage. The effectiveness of the proposed schemes is validated through numerical experiments, using a comprehensive dataset of radio measurements, generated using ray tracing simulations to model outdoor propagation at 28 GHz. We show that our proposed TN-based trajectory estimator outperforms other methods from the recent literature and can successfully generalize to new trajectories outside the training set. Furthermore, our proposed iRRT* algorithm is able to consistently provide the shortest path to the target.

eess.SP↗

arXiv2024

A BFF-Based Attention Mechanism for Trajectory Estimation in mmWave MIMO Communications

This paper explores a novel Neural Network (NN) architecture suitable for Beamformed Fingerprint (BFF) localization in a millimeter-wave (mmWave) multiple-input multiple-output (MIMO) outdoor system. The mmWave frequency bands have attracted significant attention due to their precise timing measurements, making them appealing for applications demanding accurate device localization and trajectory estimation. The proposed NN architecture captures BFF sequences originating from various user paths, and through the application of learning mechanisms, subsequently estimates these trajectories. Specifically, we propose a method for trajectory estimation, employing a transformer network (TN) that relies on attention mechanisms. This TN-based approach estimates wireless device trajectories using BFF sequences recorded within a mmWave MIMO outdoor system. To validate the efficacy of our proposed approach, numerical experiments are conducted using a comprehensive dataset of radio measurements in an outdoor setting, complemented with ray tracing to simulate wireless signal propagation at 28 GHz. The results illustrate that the TN-based trajectory estimator outperforms other methods from the existing literature and possesses the ability to generalize effectively to new trajectories outside the training dataset.

eess.SP↗

arXiv2022

Energy-Efficient D2D-Aided Fog Computing under Probabilistic Time Constraints

Device-to-device (D2D) communication is an enabling technology for fog computing by allowing the sharing of computation resources between mobile devices. However, temperature variations in the device CPUs affect the computation resources available for task offloading, which unpredictably alters the processing time and energy consumption. In this paper, we address the problem of resource allocation with respect to task partitioning, computation resources and transmit power in a D2D-aided fog computing scenario, aiming to minimize the expected total energy consumption under probabilistic constraints on the processing time. Since the formulated problem is non-convex, we propose two sub-optimal solution methods. The first method is based on difference of convex (DC) programming, which we combine with chance-constraint programming to handle the probabilistic time limitations. Considering that DC programming is dependent on a good initial point, we propose a second method that relies on only convex programming, which eliminates the dependence on user-defined initialization. Simulation results demonstrate that the latter method outperforms the former in terms of energy efficiency and run-time.

eess.SP↗

arXiv2021

Channel Estimation for Hybrid Massive MIMO Systems with Adaptive-Resolution ADCs

Achieving high channel estimation accuracy and reducing hardware cost as well as power dissipation constitute substantial challenges in the design of massive multiple-input multiple-output (MIMO) systems. To resolve these difficulties, sophisticated pilot designs have been conceived for the family of energy-efficient hybrid analog-digital (HAD) beamforming architecture relying on adaptive-resolution analog-to-digital converters (RADCs). In this paper, we jointly optimize the pilot sequences, the number of RADC quantization bits and the hybrid receiver combiner in the uplink of multiuser massive MIMO systems. We solve the associated mean square error (MSE) minimization problem of channel estimation in the context of correlated Rayleigh fading channels subject to practical constraints. The associated mixed-integer problem is quite challenging due to the nonconvex nature of the objective function and of the constraints. By relying on advanced fractional programming (FP) techniques, we first recast the original problem into a more tractable yet equivalent form, which allows the decoupling of the fractional objective function. We then conceive a pair of novel algorithms for solving the resultant problems for codebook-based and codebook-free pilot schemes, respectively. To reduce the design complexity, we also propose a simplified algorithm for the codebook-based pilot scheme. Our simulation results confirm the superiority of the proposed algorithms over the relevant state-of-the-art benchmark schemes.

cs.IT↗

arXiv2021

Light-SERNet: A lightweight fully convolutional neural network for speech emotion recognition

Detecting emotions directly from a speech signal plays an important role in effective human-computer interactions. Existing speech emotion recognition models require massive computational and storage resources, making them hard to implement concurrently with other machine-interactive tasks in embedded systems. In this paper, we propose an efficient and lightweight fully convolutional neural network for speech emotion recognition in systems with limited hardware resources. In the proposed FCNN model, various feature maps are extracted via three parallel paths with different filter sizes. This helps deep convolution blocks to extract high-level features, while ensuring sufficient separability. The extracted features are used to classify the emotion of the input speech segment. While our model has a smaller size than that of the state-of-the-art models, it achieves higher performance on the IEMOCAP and EMO-DB datasets.

eess.AS↗

arXiv2021

Deep Learning Framework for Hybrid Analog-Digital Signal Processing in mmWave Massive-MIMO Systems

Hybrid analog-digital signal processing (HSP) is an enabling technology to harvest the potential of millimeter-wave (mmWave) massive-MIMO communications. In this paper, we present a general deep learning (DL) framework for efficient design and implementation of HSP-based massive-MIMO systems. Exploiting the fact that any complex matrix can be written as a scaled sum of two matrices with unit-modulus entries, a novel analog deep neural network (ADNN) structure is first developed which can be implemented with common radio frequency (RF) components. This structure is then embedded into an extended hybrid analog-digital deep neural network (HDNN) architecture which facilitates the implementation of mmWave massive-MIMO systems while improving their performance. In particular, the proposed HDNN architecture enables HSP-based massive-MIMO transceivers to approximate any desired transmitter and receiver mapping with arbitrary precision. To demonstrate the capabilities of the proposed DL framework, we present a new HDNN-based beamformer design that can achieve the same performance as fully-digital beamforming, with reduced number of RF chains. Finally, simulation results are presented confirming the superiority of the proposed HDNN design over existing hybrid beamforming schemes.

eess.SP↗

arXiv2020

Deep Convolutional Neural Network-based Inverse Filtering Approach for Speech De-reverberation

In this paper, we introduce a spectral-domain inverse filtering approach for single-channel speech de-reverberation using deep convolutional neural network (CNN). The main goal is to better handle realistic reverberant conditions where the room impulse response (RIR) filter is longer than the short-time Fourier transform (STFT) analysis window. To this end, we consider the convolutive transfer function (CTF) model for the reverberant speech signal. In the proposed framework, the CNN architecture is trained to directly estimate the inverse filter of the CTF model. Among various choices for the CNN structure, we consider the U-net which consists of a fully-convolutional auto-encoder network with skip-connections. Experimental results show that the proposed method provides better de-reverberation performance than the prevalent benchmark algorithms under various reverberation conditions.

cs.SD↗

arXiv2020

On the Use of Audio Fingerprinting Features for Speech Enhancement with Generative Adversarial Network

The advent of learning-based methods in speech enhancement has revived the need for robust and reliable training features that can compactly represent speech signals while preserving their vital information. Time-frequency domain features, such as the Short-Term Fourier Transform (STFT) and Mel-Frequency Cepstral Coefficients (MFCC), are preferred in many approaches. While the MFCC provide for a compact representation, they ignore the dynamics and distribution of energy in each mel-scale subband. In this work, a speech enhancement system based on Generative Adversarial Network (GAN) is implemented and tested with a combination of Audio FingerPrinting (AFP) features obtained from the MFCC and the Normalized Spectral Subband Centroids (NSSC). The NSSC capture the locations of speech formants and complement the MFCC in a crucial way. In experiments with diverse speakers and noise types, GAN-based speech enhancement with the proposed AFP feature combination achieves the best objective performance while reducing memory requirements and training time.

eess.AS↗

arXiv2018

On the Security Analysis of a Cooperative Incremental Relaying Protocol in the Presence of an Active Eavesdropper

Physical layer security offers an efficient means to decrease the risk of confidential information leakage through wiretap links. In this paper, we address the physical-layer security in a cooperative wireless subnetwork that includes a source-destination pair and multiple relays, exchanging information in the presence of a malevolent eavesdropper. Specifically, the eavesdropper is active in the network and transmits artificial noise (AN) with a multiple-antenna transmitter to confound both the relays and the destination. We first analyse the secrecy capacity of the direct source-to-destination transmission in terms of intercept probability (IP) and secrecy outage probability (SOP). A decode-and-forward incremental relaying (IR) protocol is then introduced to improve reliability and security of communications in the presence of the active eavesdropper. Within this context, and depending on the availability of channel state information, three different schemes (one optimal and two sub-optimal) are proposed to select a trusted relay to improve the achievable secrecy rate. For each one of these schemes, and for both selection and maximum ratio combining at the destination and eavesdropper, we derive new and exact closed-form expressions for the IP and SOP. Our analysis and simulation results demonstrate the superior performance of the proposed IR-based selection schemes for secure communication. They also confirm the existence of a floor phenomenon for the SOP in the absence of AN.

cs.NI↗

arXiv2018

Performance Analysis of User-centric Virtual Cell Dense Networks over mmWave Channels

This paper analyzes the ergodic capacity of a user-centric virtual cell (VC) dense network, where multiple access points (APs) form a VC for each user equipment (UE) and transmit data cooperatively over millimeter wave (mmWave) channels. Different from traditional microwave radio communications, blockage phenomena have an important effect on mmWave transmissions. Accordingly, we adopt a distance-dependent line-of-sight (LOS) probability function and model the locations of the LOS and non-line-of-sight (NLOS) APs as two independent non-homogeneous Poisson point processes (PPP). Invoking this model in a VC dense network, new expressions are derived for the downlink ergodic capacity, accounting for: blockage, small-scale fading and AP cooperation. In particular, we compare the ergodic capacity for different types of fading distributions, including Rayleigh and Nakagami. Numerical results validate our analytical expressions and show that AP cooperation can provide notable capacity gain, especially in low-AP-density regions.

cs.IT↗

arXiv2017

A Novel Approach for Ellipsoidal Outer-Approximation of the Intersection Region of Ellipses in the Plane

In this paper, a novel technique for tight outer-approximation of the intersection region of a finite number of ellipses in 2-dimensional (2D) space is proposed. First, the vertices of a tight polygon that contains the convex intersection of the ellipses are found in an efficient manner. To do so, the intersection points of the ellipses that fall on the boundary of the intersection region are determined, and a set of points is generated on the elliptic arcs connecting every two neighbouring intersection points. By finding the tangent lines to the ellipses at the extended set of points, a set of half-planes is obtained, whose intersection forms a polygon. To find the polygon more efficiently, the points are given an order and the intersection of the half-planes corresponding to every two neighbouring points is calculated. If the polygon is convex and bounded, these calculated points together with the initially obtained intersection points will form its vertices. If the polygon is non-convex or unbounded, we can detect this situation and then generate additional discrete points only on the elliptical arc segment causing the issue, and restart the algorithm to obtain a bounded and convex polygon. Finally, the smallest area ellipse that contains the vertices of the polygon is obtained by solving a convex optimization problem. Through numerical experiments, it is illustrated that the proposed technique returns a tighter outer-approximation of the intersection of multiple ellipses, compared to conventional techniques, with only slightly higher computational cost.

cs.CG↗

arXiv2016

Secure MIMO Relaying Network: An Artificial Noise Aided Robust Design Approach

Owing to the vulnerability of relay-assisted and device-to-device (D2D) communications, improving wireless security from a physical layer signal processing perspective is attracting increasing interest. Hence we address the problem of secure transmission in a relay-assisted network, where a pair of legitimate user equipments (UEs) communicate with the aid of a multiple-input multiple output (MIMO) relay in the presence of multiple eavesdroppers (eves). Assuming imperfect knowledge of the eves' channels, we jointly optimize the power of the source UE, the amplify-and-forward (AF) relaying matrix and the covariance of the artificial noise (AN) transmitted by the relay, in order to maximize the received signal-to-interference-plus-noise ratio (SINR) at the destination, while imposing a set of robust secrecy constraints. To tackle the resultant nonconvex optimization problem, a globally optimal solution based on a bi-level optimization framework is proposed, but with high complexity. Then a low-complexity sub-optimal method relying on a new penalized difference-of-convex (DC) algorithmic framework is proposed, which is specifically designed for non-convex semidefinite programs (SDPs). We show how this penalized DC framework can be invoked for solving our robust secure relaying problem with proven convergence. Our extensive simulation results show that both proposed solutions are capable of ensuring the secrecy of the relay-aided transmission and significantly improve the robustness towards the eves' channel uncertainties as compared to the non-robust counterparts. It is also demonstrated the penalized DC-based method advocated yields a performance close to the globally optimal solution.

cs.IT↗

arXiv2015

Joint Transceiver Design Algorithms for Multiuser MISO Relay Systems with Energy Harvesting

In this paper, we investigate a multiuser relay system with simultaneous wireless information and power transfer. Assuming that both base station (BS) and relay station (RS) are equipped with multiple antennas, this work studies the joint transceiver design problem for the BS beamforming vectors, the RS amplify-and-forward transformation matrix and the power splitting (PS) ratios at the single-antenna receivers. Firstly, an iterative algorithm based on alternating optimization (AO) and with guaranteed convergence is proposed to successively optimize the transceiver coefficients. Secondly, a novel design scheme based on switched relaying (SR) is proposed that can significantly reduce the computational complexity and overhead of the AO based designs while maintaining a similar performance. In the proposed SR scheme, the RS is equipped with a codebook of permutation matrices. For each permutation matrix, a latent transceiver is designed which consists of BS beamforming vectors, optimally scaled RS permutation matrix and receiver PS ratios. For the given CSI, the optimal transceiver with the lowest total power consumption is selected for transmission. We propose a concave-convex procedure based and subgradient-type iterative algorithms for the non-robust and robust latent transceiver designs. Simulation results are presented to validate the effectiveness of all the proposed algorithms.

cs.IT↗

arXiv2015

Centralized Adaptation for Parameter Estimation over Wireless Sensor Networks

We study the performance of centralized least mean-squares (CLMS) algorithms in wireless sensor networks where nodes transmit their data over fading channels to a central processing unit (e.g., fusion center or cluster head), for parameter estimation. Wireless channel impairments, including fading and path loss, distort the transmitted data, cause link failure and degrade the performance of the adaptive solutions. To address this problem, we propose a novel CLMS algorithm that uses a refined version of the transmitted data and benefits from a link failure alarm strategy to discard severely distorted data. Furthermore, to remove the bias due to communication noise from the estimate, we introduce a bias-elimination scheme that also leads to a lower steady-state mean-square error. Our theoretical findings are supported by numerical simulation results.

eess.SY↗

arXiv2015

Diffusion Adaptation over Multi-Agent Networks with Wireless Link Impairments

We study the performance of diffusion least-mean-square algorithms for distributed parameter estimation in multi-agent networks when nodes exchange information over wireless communication links. Wireless channel impairments, such as fading and path-loss, adversely affect the exchanged data and cause instability and performance degradation if left unattended. To mitigate these effects, we incorporate equalization coefficients into the diffusion combination step and update the combination weights dynamically in the face of randomly changing neighborhoods due to fading conditions. When channel state information (CSI) is unavailable, we determine the equalization factors from pilot-aided channel coefficient estimates. The analysis reveals that by properly monitoring the CSI over the network and choosing sufficiently small adaptation step-sizes, the diffusion strategies are able to deliver satisfactory performance in the presence of fading and path loss.

eess.SY↗

arXiv2015

Diffusion LMS Strategies in Sensor Networks with Noisy Input Data

We investigate the performance of distributed least-mean square (LMS) algorithms for parameter estimation over sensor networks where the regression data of each node are corrupted by white measurement noise. Under this condition, we show that the estimates produced by distributed LMS algorithms will be biased if the regression noise is excluded from consideration. We propose a bias-elimination technique and develop a novel class of diffusion LMS algorithms that can mitigate the effect of regression noise and obtain an unbiased estimate of the unknown parameter vector over the network. In our development, we first assume that the variances of the regression noises are known a-priori. Later, we relax this assumption by estimating these variances in real-time. We analyze the stability and convergence of the proposed algorithms and derive closed-form expressions to characterize their mean-square error performance in transient and steady-state regimes. We further provide computer experiment results that illustrate the efficiency of the proposed algorithms and support the analytical findings.

eess.SY↗

arXiv2015

Estimation of Space-Time Varying Parameters Using a Diffusion LMS Algorithm

We study the problem of distributed adaptive estimation over networks where nodes cooperate to estimate physical parameters that can vary over both space and time domains. We use a set of basis functions to characterize the space-varying nature of the parameters and propose a diffusion least mean-squares (LMS) strategy to recover these parameters from successive time measurements. We analyze the stability and convergence of the proposed algorithm, and derive closed-form expressions to predict its learning behavior and steady-state performance in terms of mean-square error. We find that in the estimation of the space-varying parameters using distributed approaches, the covariance matrix of the regression data at each node becomes rank-deficient. Our analysis reveals that the proposed algorithm can overcome this difficulty to a large extent by benefiting from the network stochastic matrices that are used to combine exchanged information between nodes. We provide computer experiments to illustrate and support the theoretical findings.

eess.SY↗