Technical Program
Monday, August 28, 09:00 - 10:30
T.1A: Biomedical Image Reconstruction
Tutorial
Michael Unser
Room: PanaceaT.2A: Massive MIMO-Fundamentals and State-of-the-Art
Tutorial
Luca Sanguinetti
Room: Aegle AT.3A: Target Tracking for Radar Systems: An Historical Overview from the Alpha-Betta Filter to Random Set Filters
Tutorial
Alfonso Farina and Luigi Chisci
Room: AcessoT.4A: Deverberation and Reverberation of Audio, Music, and Speech
Tutorial
Patrick A. Naylor, Enzo De Sena, and Toon van Waterschoot
Room: Aegle BT.5A: 5G Satellites and Beyond: A New Interference-Limited Paradigm
Tutorial
Ana Pérez-Neira and Miguel A. Vázquez
Room: MelambusMonday, August 28, 10:30 - 11:00
Coffee break
Monday, August 28, 11:00 - 12:30
T.1B: Biomedical Image Reconstruction
Tutorial
Michael Unser
Room: PanaceaT.2B: Massive MIMO-Fundamentals and State-of-the-Art
Tutorial
Luca Sanguinetti,
Room: Aegle AT.3B: Target Tracking for Radar Systems: An Historical Overview from the Alpha-Betta Filter to Random Set Filters
Tutorial
Alfonso Farina and Luigi Chisci
Room: AcessoT.4B: Deverberation and Reverberation of Audio, Music, and Speech
Tutorial
Patrick A. Naylor, Enzo De Sena, and Toon van Waterschoot
Room: Aegle BT.5B: 5G Satellites and Beyond: A New Interference-Limited Paradigm
Tutorial
Ana Pérez-Neira and Miguel A. Vázquez
Room: MelambusMonday, August 28, 12:30 - 14:00
Lunch break
Monday, August 28, 14:00 - 15:30
T.10A: Bayes and Markov Listen to Music
Tutorial
George Tzanetakis
Room: Aegle AT.6A: Emerging Topics in 5G Networks: Simultaneous Wireless Information and Energy Transfer
Tutorial
Marco Maso, Marco di Renzo, Samir M. Perlaza, and Bruno Clerckx
Room: MelambusT.7A: Sparse Estimation Methods for Array Processing
Tutorial
Zai Yang, Gongguo Tang, and Petre Stoica
Room: PanaceaT.8A: Partial Difference Equations on Graphs and Networks: From Images to Graph Signal Processing
Tutorial
Abderrahim Elmoataz and Pierre Buyssens
Room: Aegle BT.9A: Exploiting Structure and Pseudo-Convexity in Iterative Parallel Optimization Algorithms for Real-Time and Large-Scale Applications
Tutorial
Yang Yang and Marius Pesavento
Room: AcessoMonday, August 28, 15:30 - 16:00
Coffee break
Monday, August 28, 16:00 - 17:30
T.10B: Bayes and Markov Listen to Music
Tutorial
George Tzanetakis
Room: Aegle AT.6B: Emerging Topics in 5G Networks: Simultaneous Wireless Information and Energy Transfer
Tutorial
Marco Maso, Marco di Renzo, Samir M. Perlaza, and Bruno Clerckx
Room: MelambusT.7B: Sparse Estimation Methods for Array Processing
Tutorial
Zai Yang, Gongguo Tang, and Petre Stoica
Room: PanaceaT.8B: Partial Difference Equations on Graphs and Networks: From Images to Graph Signal Processing
Tutorial
Abderrahim Elmoataz and Pierre Buyssens
Room: Aegle BT.9B: Exploiting Structure and Pseudo-Convexity in Iterative Parallel Optimization Algorithms for Real-Time and Large-Scale Applications
Tutorial
Yang Yang and Marius Pesavento
Room: AcessoMonday, August 28, 20:00 - 22:00
Welcome Reception
Tuesday, August 29, 08:30 - 09:30
Opening and Awards Ceremony
Room: Hippocrates
Chairs: Petros Maragos (National Technical University of Athens, Greece), Sergios Theodoridis (University of Athens, Greece)
Tuesday, August 29, 09:30 - 10:30
PLEN-1: Machine Learning Approaches for Solving Inverse Imaging Problems
EURASIP Fellow Inaugural Lecture
Prof. Aggelos Katsaggelos
Room: HippocratesChair: Stefanos Kollias (University of Lincoln/NTUA, United Kingdom (Great Britain))
Tuesday, August 29, 10:30 - 10:50
Coffee break
Room: Level 1
Tuesday, August 29, 10:50 - 12:30
AASP-L1: Acoustic Sensor Array Processing
Lecture
Room: Aegle BChair: Walter Kellermann (University Erlangen-Nuremberg, Germany)
- 10:50 Binaural Beamforming Using Pre-Determined Relative Acoustic Transfer Functions
- 11:10 Retrieval of Individualized Head-Related Transfer Functions for Hearing Aid Applications
- 11:30 Scalable Source Localization with Multichannel Alpha-Stable Distributions
- 11:50 Angle-of-Arrival-Based Gesture Recognition Using Ultrasonic Multi-Frequency Signals
- 12:10 Study of Widely Linear Multichannel Wiener Filter for Binaural Noise Reduction
BSIP-P1: Biomedical Signal and Image Processing
Poster
Room: Poster Area 2 Level 1Chair: Christophoros Nikou (University of Ioannina, Greece)
- Flexible Fusion of Electroencephalography and Functional Magnetic Resonance Imaging: Revealing Neural-Hemodynamic Coupling Through Structured Matrix-Tensor Factorization
- A Robust Algorithm for Gait Cycle Segmentation
- Volumetric Segmentation of Human Eye Blood Vessels Based on OCT Images
- Automatic Prediction of Spirometry Readings from Cough and Wheeze for Monitoring of Asthma Severity
- Pseudo-CT Generation by Conditional Inference Random Forest for MRI-based Radiotherapy Treatment Planning
- Learning Feature Extractors for AMD Classification in OCT Using Convolutional Neural Networks
- Cognitive State Signature Analyses Using Single Channel EEG Data
- Gender Classification Based on EEG Signal
- A New Method for Breast Cancer Identification Using Multi-modal Features in Quaternionic Form
IVM-L1: Image, Video and Multimedia Processing
Lecture
Room: HippocratesChair: Anastasios Tefas (Aristotle University of Thessaloniki, Greece)
- 10:50 Deep Structured Features for Semantic Segmentation
- 11:10 3D Point Cloud Segmentation Using a Fully Connected Conditional Random Field
- 11:30 Concept Detection and Face Pose Estimation Using Lightweight Convolutional Neural Networks for Steering Drone Video Shooting
- 11:50 Detecting Conversational Gaze Aversion Using Unsupervised Learning
- 12:10 Registration of Images to Unorganized 3D Point Clouds Using Contour Cues
SLP-L1: Spoofing Detection, Speaker Diarization and Recognition
Lecture
Room: AcessoChair: Tiago Falk (INRS-EMT, Canada)
- 10:50 Robust Statistical Processing of TDOA Estimates for Distant Speaker Diarization
- 11:10 Variants of Mel-frequency Cepstral Coefficients for Improved Whispered Speech Speaker Verification in Mismatched Conditions
- 11:30 Speaker Verification Anti-Spoofing Using Linear Prediction Residual Phase Features
- 11:50 Spoofing Detection Employing Infinite Impulse Response - Constant Q Transform-based Feature Representations
- 12:10 Novel Energy Separation Based Instantaneous Frequency Features for Spoof Speech Detection
SPCOM-L1: Signal Processing for Communications
Lecture
Room: PanaceaChair: Jonathon Chambers (Newcastle University, United Kingdom (Great Britain))
- 10:50 Implementation Aspects of Nonlinear Precoding for G.fast - Coding and Legacy Receivers
- 11:10 Collision Resolution and Interference Elimination in Multiaccess Communication Networks
- 11:30 Performance Analysis of PLNC Using Hierarchical Modulation
- 11:50 Topology-Aware Space-Time Network Coding
- 12:10 Path Planning and Localization for Mobile Anchor Based Wireless Sensor Networks
SPGN-L1: Signal Processing over Graphs and Networks/Optimization Methods
Lecture
Room: Aegle AChair: Alexander Bertrand (KU Leuven, Belgium)
- 10:50 Online Convex Optimization for Dynamic Network Resource Allocation
- 11:10 Exact Diffusion Strategy for Optimization by Networked Agents
- 11:30 Network Topology Inference via Elastic Net Structural Equation Models
- 11:50 A Connectedness Constraint for Learning Sparse Graphs
- 12:10 A Global Optimization Approach for Rational Sparsity Promoting Criteria
SSP-P1: Statistical Signal Processing
Poster
Room: Poster Area 1 Level 1Chair: Athanasios A. Rontogiannis (National Observatory of Athens, Greece)
- Robust Distributed Multi-Speaker Voice Activity Detection Using Stability Selection for Sparse Non-Negative Feature Extraction
- Robust Distributed Sequential Hypothesis Testing for Detecting a Random Signal in Non-Gaussian Noise
- Recycling Gibbs Sampling
- H_{infinite} Estimator for Gearbox Diagnosis in Variable Speed Conditions
- On the Number of Iterations for the Matching Pursuit Algorithm
- Performance Bounds for Cooperative RSS Emitter Tracking Using Diffusion Particle Filters
- Deconvolution-Segmentation for Textured Images
- Wheels Coating Process Monitoring in the Presence of Nuisance Parameters Using Sequential Change-Point Detection Method
- Group Metropolis Sampling
- Global Error Control Procedure for Spatially Structured Targets
- Event-based Particle Filtering with Point and Set-valued Measurements
Tuesday, August 29, 12:30 - 14:00
Lunch break
Tuesday, August 29, 14:00 - 15:40
AASP-L2: Auditory Modeling and Hearing Aids
Lecture
Room: Aegle BChair: Shoji Makino (University of Tsukuba, Japan)
- 14:00 Non-Intrusive Intelligibility Prediction Using a Codebook-Based Approach
- 14:20 New Insights into the Role of the Head Radius in Model-Based Binaural Speaker Localization
- 14:40 Sparsity Promoting LMS for Adaptive Feedback Cancellation
- 15:00 Combining Null-Steering and Adaptive Filtering for Acoustic Feedback Cancellation in a Multi-Microphone Earpiece
- 15:20 A Sparsity-Aware Proportionate Normalized Maximum Correntropy Criterion Algorithm for Sparse System Identification in Non-Gaussian Environment
BSIP-L1: Biomedical Signal and Image Processing
Lecture
Room: HippocratesChair: Francoise Peyrin (Universite de Lyon INSA Lyon & Inserm U1044 UMR CNRS 5220, France)
- 14:00 An Unsupervised Bayesian Approach for the Joint Reconstruction and Classification of Cutaneous Reflectance Confocal Microscopy Images
- 14:20 Hyperparameter Estimation in Maximum a Posteriori Regression Using Group Sparsity with an Application to Brain Imaging
- 14:40 Automatic Atlas-Guided Constrained Random Walker Algorithm for 3D Segmentation of Muscles on Water Magnetic Resonance Images
- 15:00 RSS-based Respiratory Rate Monitoring Using Periodic Gaussian Processes and Kalman Filtering
- 15:20 Recovery of Missing Samples in Fetal Heart Rate Recordings with Gaussian Processes
IFS-L1: Information Forensics and Security
Lecture
Room: Aegle AChair: Patrizio Campisi (Università degli Studi Roma Tre, Italy)
- 14:00 Malicious Users Discrimination in Organized Attacks Using Structured Sparsity
- 14:20 Log-Likelihood Score Level Fusion for Improved Cross-Sensor Smartphone Periocular Recognition
- 14:40 Joint Learning of Local Fingerprint and Content Modulation
- 15:00 Higher-Order, Adversary-Aware, Double JPEG-Detection via Selected Training on Attacked Samples
- 15:20 Electric Network Frequency Estimation Based on Linear Canonical Transform for Audio Signal Authentication
MLSP-P1: Machine Learning for Signal Processing
Poster
Room: Poster Area 1 Level 1Chair: Anastasios Tefas (Aristotle University of Thessaloniki, Greece)
- A Two-Stage Subspace Trust Region Approach for Deep Neural Network Training
- Active Learning with Cross-Dataset Validation in Event-Based Non-Intrusive Load Monitoring
- Time-series Classification Using Neural Bag-of-Features
- Qualitative Assessment of Recurrent Human Motion
- Visualization of Feature Evolution During Convolutional Neural Network Training
- An Elliptical-Shaped Density-Based Classification Algorithm for Detection of Entangled Clusters
- A General Framework for Adversarial Bandits
- A Rate Optimal Switching Bandit Algorithm
- A Post-Nonlinear Mixture Model Approach to Binary Matrix Factorization
- Classification of One-Dimensional Non-Stationary Signals Using the Wigner-Ville Distribution in Convolutional Neural Networks
- Spectral Detection and Localization of Radio Events with Learned Convolutional Neural Features
NSPGN-P1: Nonlinear Signal Processing/Signal Processing over Graphs and Networks
Poster
Room: Poster Area 2 Level 1Chair: Peter Djuric (State University of New York at Stony Brook, USA)
- Low-Rank and Nonlinear Model Approach to Image Inpainting
- Autonomous State Space Models for Recursive Signal Estimation Beyond Least Squares
- Characterization of Discrete Linear Shift-Invariant Systems
- Topology Design to Increase Network Lifetime in WSN for Graph Filtering in Consensus Processes
- Fractional Graph-based Semi-Supervised Learning
- Distributed Greedy Sparse Learning over Doubly Stochastic Networks
- Signal Processing on Kernel-Based Random Graphs
- Graph Spectral Domain Feature Representation for in-Air Drawn Number Recognition
- Graph Adjacency Matrix Learning for Irregularly Sampled Markovian Natural Images
SENS-L1: Sensor Array and Multichannel Signal Processing
Lecture
Room: AcessoChair: Martin Haardt (Ilmenau University of Technology, Germany)
- 14:00 Defending Surveillance Sensor Networks Against Data-Injection Attacks via Trusted Nodes
- 14:20 Channel Estimation and Training Design for Hybrid Multi-Carrier MmWave Massive MIMO Systems: The Beamspace ESPRIT Approach
- 14:40 Modal Beamforming for Small Circular Arrays of Particle Velocity Sensors
- 15:00 Thinned Coprime Arrays for DOA Estimation
- 15:20 Joint Frequency and 2-D DOA Recovery with sub-Nyquist Difference Space-Time Array
SPCOM-L2: Signal Processing for Communications
Lecture
Room: PanaceaChair: Eleftherios Kofidis (University of Piraeus & Computer Technology Institute (CTI), Greece)
- 14:00 Filtered Multitone Multicarrier Modulation with Partially Overlapping Sub-Channels
- 14:20 Low Complexity Channel Shortening for Discrete Multitone Modulation Systems
- 14:40 An Online Algorithm for Joint Long-Term Base Station Activation and Beamforming in Green Downlink MISO Networks
- 15:00 Gradient-based Algorithm for Designing Sequence with Low Autocorrelation Sidelobes
- 15:20 Joint Channel Estimation / Data Detection in MIMO-FBMC/OQAM Systems - A Tensor-Based Approach
Tuesday, August 29, 15:40 - 16:00
Coffee break
Room: Level 1
Tuesday, August 29, 16:00 - 18:00
BSIP-P2: Biomedical Signal and Image Processing
Poster
Room: Poster Area 2 Level 1Chair: Christophoros Nikou (University of Ioannina, Greece)
- Unmixing Dynamic PET Images with a PALM Algorithm
- Relevance of Empirical Mode Decomposition for Fetal Heartbeat Detection on Smartphone Devices
- Effect of a Humorous Audio-visual Stimulus on Autonomic Nervous System and Heart of Females
- Triaxial Rehabilitative Data Analysis Incorporating Matching Pursuit
- Three-dimensional Fluorescence Lifetime Imaging in Confocal Microscopy of Living Cells
- Characterizing Absence Epileptic Seizures from Depth Cortical Measurements
- Direct Nonparametric Estimation of the Period and the Shape of a Periodic Component in Short Duration Signals
- Investigation of Nonlinear Granger Causality in the Context of Epilepsy
- EEG Seizure Detection by Integrating Slantlet Transform with Sparse Coding
CISI-L1: Computational Imaging/Spectral Imaging
Lecture
Room: PanaceaChair: Gonzalo Arce (University of Delaware, USA)
- 16:00 High-dimensional Optimization of Color Coded Apertures for Compressive Spectral Cameras
- 16:20 Multi-Resolution Reconstruction Algorithm for Compressive Single Pixel Spectral Imaging
- 16:40 Honey Dataset Standard Using Hyperspectral Imaging for Machine Learning Problems
- 17:00 Bayesian Method with Sparsity Enforcing Prior of Dual-Tree Complex Wavelet Transform Coefficients for X-ray CT Image Reconstruction
- 17:20 A New Multiplicative Nonnegative Matrix Factorization Method for Unmixing Hyperspectral Images Combined with Multispectral Data
- 17:40 Hyperspectral Image Restoration Based on Spatio-Spectral Structure Tensor Regularization
SIPA-L1: Signal and Image Processing Applications
Lecture
Room: HippocratesChair: Athina Petropulu (Rutgers, The State University of New Jersey, USA)
- 16:00 A New Approach to Dictionary-Based Nonnegative Matrix Factorization
- 16:20 Denoising Galaxy Spectra with Coupled Dictionary Learning
- 16:40 Restoration from Multispectral Blurred Data with Non-Stationary Instrument Response
- 17:00 Landmine Detection from GPR Data Using Convolutional Neural Networks
- 17:20 A Statistical Model of Tristimulus Measurements Within and Between OLED Displays
- 17:40 Automatic Crater Detection and Age Estimation for Mare Regions on the Lunar Surface
SLP-P1: Speech Recognition and Other Speech and Language Technology Topics
Poster
Room: Poster Area 1 Level 1Chair: Gerasimos Potamianos (University of Thessaly, Greece)
- Voice Activity Detection Using Discriminative Restricted Boltzmann Machines
- Class Specific GMM Based Sparse Feature for Speech Units Classification
- Comparison of I-vector and GMM-UBM Approaches to Speaker Identification with TIMIT and NIST 2008 Databases in Challenging Environments
- Low Resource Point Process Models for Keyword Spotting Using Unsupervised Online Learning
- Residual Neural Networks for Speech Recognition
- A Curriculum Learning Method for Improved Noise Robustness in Automatic Speech Recognition
- A Reassigned Front-End for Speech Recognition
- On the Improvement of Modulation Features Using Multi-Microphone Energy Tracking for Robust Distant Speech Recognition
- VTLN-Warped Gaussian Posteriorgram for QbE-STD
- Context Incorporation Using Context - Aware Language Features
- Effectiveness of Ideal Ratio Mask for Non-intrusive Quality Assessment of Noise Suppressed Speech
- Perception and Production of L2 Mandarin Tones by Swedish Learners
SS2: Special Session on Acoustical Signal Processing for Hearables
Lecture
Session organizers: Simon Doclo and Nordholm Sven
Room: Aegle BChairs: Simon Doclo (University of Oldenburg, Germany), Nordholm Sven (Curtin University of Technology, Australia)
- 16:00 Decorrelation Measures for Stabilizing Adaptive Feedback Cancellation in Hearing Aids
- 16:20 Real Time Noise Suppression in Social Settings Comprising a Mixture of Non-stationary and Transient Noise
- 16:40 Time-Domain Kalman Filter for Active Noise Cancellation Headphones
- 17:00 Binaural Speech Enhancement with Spatial Cue Preservation Utilising Simultaneous Masking
- 17:20 Sensitivity Analysis of the Multi-Frame MVDR Filter for Single-Microphone Speech Enhancement
- 17:40 Real-Time Adaptive Equalization for Headphone Listening
SS20: Special Session on Signal Processing Challenges in 5G Mobile Communications
Lecture
Session organizers: Stefan Schwarz and Markus Rupp
Room: AcessoChair: Markus Rupp (TU Wien, Austria)
- 16:00 Throughput-Based Performance Evaluation of 5G-Candidate Waveforms in High Speed Scenarios
- 16:20 Analysis of the Performance of a Non-Coherent Large Scale SIMO System Based on M-DPSK Under Rician Fading
- 16:40 A Mutual Coupling Model for Massive MIMO Applied to the 3GPP 3D Channel Model
- 17:00 Covariance Estimation with Projected Data: Applications to CSI Covariance Acquisition and Tracking
- 17:20 Sensor-based Predictive Communication for Highly Dynamic Multi-Hop Vehicular Networks
- 17:40 A Study on the Physical Layer Performance of GFDM for High Throughput Wireless Communication
SS3: Special Session on Advanced Tensor Methods for Big Data Processing
Lecture
Session organizers: Gérard Favier, André L.F. de Almeida, and Rémy Boyer
Room: Aegle AChair: George Tzanetakis (University of Victoria, Canada)
- 16:00 ACMTF for Fusion of Multi-Modal Neuroimaging Data and Identification of Biomarkers
- 16:20 Tensor-Based Sparsity Order Estimation for Big Data Applications
- 16:40 A Novel Non-Iterative Algorithm for Low-Multilinear-Rank Tensor Approximation
- 17:00 Large Deviation Analysis of the CPD Detection Problem Based on Random Tensor Theory
- 17:20 Nonlinear Least Squares Updating of the Canonical Polyadic Decomposition
- 17:40 Low Rank Canonical Polyadic Decomposition of Tensors Based on Group Sparsity
Wednesday, August 30, 08:40 - 09:40
PLEN-2: On Learning Invariants and Representation Spaces of Shapes and Forms
Prof. Ron Kimmel
Room: HippocratesChair: Petros Maragos (National Technical University of Athens, Greece)
Wednesday, August 30, 09:40 - 10:00
Coffee break
Room: Level 1
Wednesday, August 30, 10:00 - 12:00
3MT: 3 Minute Thesis
Room: Melambus
Chairs: Petros T. Boufounos (Mitsubishi Electric Research Laboratories & Rice University, USA), Aggelos Pikrakis (University of Piraeus, Greece)
- 10:00 3MT Introductory Remarks
- 10:03 Biometric Recognition using Brain Signals
- 10:06 Mind reading via fMRI data analysis and higher order tensor representations
- 10:09 Privacy protection in video surveillance
- 10:12 Diagnosing neurological diseases by fusing EEG and fMRI
- 10:15 Deposition of diamond on silicon carbide for high power electronics
- 10:18 Speech Separation and Recognition Using CASA Segmentation and Language-Based Grouping
- 10:21 Low Complexity Cooperative Estimation for through the Wall Radar Imaging
- 10:24 Beating Atrial Fibrillation
- 10:27 Context-aware Adaptive Biometrics using Multiagents
AASP-L3: Modeling, Analysis, and Synthesis of Acoustic Environments
Lecture
Room: Aegle BChair: Augusto Sarti (Politecnico di Milano, Italy)
- 10:00 Synthesis of a Spatially Band-Limited Plane Wave in the Time-Domain Using Wave Field Synthesis
- 10:20 Sparse Parametric Modeling of the Early Part of Acoustic Impulse Responses
- 10:40 An Image-Inspired Audio Sharpness Index
- 11:00 Time-Domain Realisation of Model-Based Rendering for 2.5D Local Wave Field Synthesis Using Spatial Bandwidth-Limitation
- 11:20 Investigation of Electric Network Frequency for Synchronization of Low Cost and Wireless Sound Cards
- 11:40 Optimizing Acoustic Feature Extractor for Anomalous Sound Detection Based on Neyman-Pearson Lemma
CSSM-L1: Sparse Representations in Signal/Image Processing and Imaging
Lecture
Room: PanaceaChair: Karen Egiazarian (Tampere University of Technology, Finland)
- 10:00 Joint Active Device Identification and Symbol Detection Using Sparse Constraints in Massive MIMO Systems
- 10:20 Restoration of Multilayered Single-Photon 3D LiDAR Images
- 10:40 Sparse Reconstruction Algorithms for Nonlinear Microwave Imaging
- 11:00 Complex Domain Nonlocal Block-Matching Denoising Based on High-Order Singular Value Decomposition (HOSVD)
- 11:20 Learning Fast Sparsifying Overcomplete Dictionaries
- 11:40 Spatio-Spectro-Temporal Coded Aperture Design for Multiresolution Compressive Spectral Video Sensing
IVM-P1: Image, Video and Multimedia Processing
Poster
Room: Poster Area 1 Level 1Chair: Nikos Nikolaidis (Aristotle University of Thessaloniki, Greece)
- Weighted MSE Based Spatially Adaptive BM3D
- EMOEEG: a New Multimodal Dataset for Dynamic EEG-based Emotion Recognition with Audiovisual Elicitation
- Human Crowd Detection for Drone Flight Safety Using Convolutional Neural Networks
- Learning Local Feature Aggregation Functions with Backpropagation
- User Adaptation of Convolutional Neural Network for Human Activity Recognition
- Semi-Unsupervised Bayesian Convex Image Restoration with Location Mixture of Gaussian
- Graph-Based Interpolation for Zooming in 3D Scenes
- A Multi-Objective Optimization for Video Orchestration
- Person Identity Recognition on Motion Capture Data Using Label Propagation
- Oriented Asymmetric Kernels for Corner Detection
- Expression Recognition for Severely Demented Patients in Music Reminiscence-Therapy
- Local Frame Match Distance: A Novel Approach for Exemplar Gesture Recognition
- Graph Scaling Cut with L1-Norm for Classification of Hyperspectral Images
- CNN-Based Transform Index Prediction in Multiple Transforms Framework to Assist Entropy Coding
- Convolutional Neural Network-Based Infrared Image Super Resolution Under Low Light Environment
- A Novel Global Image Description Approach for Long Term Vehicle Localization
- A Normalized Mirrored Correlation Measure for Data Symmetry Detection
MLSP-L1: Machine Learning for Signal Processing
Lecture
Room: Aegle AChair: Ahmed Tewfik (University of Texas, Austin, USA)
- 10:00 Variational Stabilized Linear Forgetting in State-Space Models
- 10:20 Probabilistic Cross-Validation Estimators for Gaussian Process Regression
- 10:40 Evaluating the RBM Without Integration Using PDF Projection
- 11:00 Data Subset Selection for Efficient SVM Training
- 11:20 Unsupervised Feature Extraction, Signal Labeling, and Blind Signal Separation in a State Space World
- 11:40 Clustering and Causality Inference Using Algorithmic Complexity
SPCOM/5G-P1: Signal Processing for Communications/Challenges in 5G Mobile Communications
Poster
Room: Poster Area 2 Level 1Chair: Markus Rupp (TU Wien, Austria)
- Unsupervised Time Domain Nonlinear Post-Equalization for ACO-OFDM Visible Light Communication Systems
- Optimized Block-Diagonalization Precoding Technique Using Givens Rotations QR Decomposition
- On Differential Modulation in Downlink Multiuser MIMO Systems
- Precoding Under Instantaneous Per-Antenna Peak Power Constraint
- Joint Carrier Frequency Offset and Channel Impulse Response Estimation for Linear Periodic Channels
- Low-Complexity Detection Based on Landweber Method in the Uplink of Massive MIMO Systems
- Adaptive Zero Padded CB-FMT for LTE Uplink Transmission in the High Mobility Scenario
- Low Complexity Hybrid Precoding in Finite Dimensional Channel for Massive MIMO Systems
- Inter-Carrier Interference of Multiple Access UFMC with Flexible Subcarrier Spacings
- Highly Efficient Representation of Reconfigurable Code Based on a Radio Virtual Machine: Optimization to Any Target Platform
- Reconfiguration of 5G Radio Interface for Positioning and Communication
- Adaptive Automotive Communications Solutions of 10 Years Lifetime Enabled by ETSI RRS Software Reconfiguration Technology
SPTM-L1: Signal Processing Theory and Methods
Lecture
Room: HippocratesChair: Antonio Napolitano (Universita di Napoli Parthenope, Italy)
- 10:00 The Scaled Reassigned Spectrogram Adapted for Detection and Localisation of Transient Signals
- 10:20 Designing Optimal Sampling Schemes
- 10:40 Sub-band Equalization Filter Design for Improving Dynamic Range Performance of Modulated Wideband Converter
- 11:00 Non-iterative Filter Bank Phase (Re)Construction
- 11:20 A Closed-Form Transfer Function of 2-D Maximally Flat Half-Band FIR Digital Filters with Arbitrary Filter Orders
- 11:40 Co-Prime Arrays and Difference Set Analysis
SS5: Special Session on Biometrics and Privacy Protection
Lecture
Session organizers: Paulo Lobato Correia, Patrizio Campisi, and Andreas Uhl
Room: AcessoChair: Paulo Lobato Correia (Instituto Superior Tecnico - Universidade Tecnica Lisboa & Instituto de Telecomunicacoes, Portugal)
- 10:00 Gait Recognition Using Normalized Shadows
- 10:20 Biometric Symmetry: Implications on Template Protection
- 10:40 ASePPI, an Adaptive Scrambling Enabling Privacy Protection and Intelligibility in H.264/AVC
- 11:00 Visually Evoked Potential for EEG Biometrics Using Convolutional Neural Network
- 11:20 Private Authentication Keys Based on Wearable Device EEG Recordings
- 11:40 Privacy-Safe Linkage Analysis with Homomorphic Encryption
Wednesday, August 30, 12:00 - 13:30
Lunch break
MathWorks Workshop: Real-Time Prototyping of DSP Algorithms on Live Real-World RF, Vision, and Audio Signals
Gabriele Bunkheila and Stefano Olivieri
Room: PanaceaWednesday, August 30, 13:30 - 14:30
PLEN-3: Linearly-Convergent Stochastic Gradient Algorithms
Dr. Francis Bach
Room: HippocratesChair: Sergios Theodoridis (University of Athens, Greece)
Wednesday, August 30, 14:30 - 16:10
AASP-L4: Music Signal Processing
Lecture
Room: Aegle BChair: Richard Hendriks (Delft University of Technology, The Netherlands)
- 14:30 End-to-End Musical Key Estimation Using a Convolutional Neural Network
- 14:50 A Model for Music Complexity Applied to Music Preprocessing for Cochlear Implants
- 15:10 Phase Vocoder Done Right
- 15:30 Stereophonic Music Separation Based on Non-negative Tensor Factorization with Cepstrum Regularization
- 15:50 Predominant Vocal Melody Extraction from Enhanced Partial Harmonic Content
DISPPS-L1: Design and implementation of SP Systems/SP for Power Systems
Lecture
Room: MelambusChair: Daniele Angelosante (ABB Corporate Research Center, Switzerland)
- 14:30 An Optimized Embedded Target Detection System Using Acoustic and Seismic Sensors
- 14:50 A Nonuniform Quantization Scheme for High Speed SAR ADC Architecture
- 15:10 Impact of Temporal Subsampling on Accuracy and Performance in Practical Video Classification
- 15:30 An Adaptive Clarke Transform Based Estimator for the Frequency of Balanced and Unbalanced Three-Phase Power Systems
- 15:50 Motor Parameters Estimation from Industrial Electrical Measurements
IVM-L2: Image, Video and Multimedia Processing
Lecture
Room: HippocratesChair: Fernando Pereira (Instituto Superior Técnico - Instituto de Telecomunicações & Universidade de Lisboa, Portugal)
- 14:30 Improvement of HEVC Inter-coding Mode Using Multiple Transforms
- 14:50 Trapezoidal Block Split Using Orthogonal C2 Transforms for HEVC Video Coding
- 15:10 Depth Modeling Modes Complexity Control System for the 3D-HEVC Video Encoder
- 15:30 Reducing Computational Complexity in HEVC Decoder for Mobile Energy Saving
- 15:50 Complexity Reduction of 3D-HEVC Based on Depth Analysis for Background and ROI Classification
MLOPT-P1: Machine Learning and Optimization Methods
Poster
Room: Poster Area 1 Level 1Chair: H. Vincent Poor (Princeton University, USA)
- Airfare Prices Prediction Using Machine Learning Techniques
- Hand Gesture Recognition Using Machine Learning and the Myo Armband
- Multimodal Detection of Fake Social Media Use Through a Fusion of Classification and Pairwise Ranking Systems
- Boosted Multiple Kernel Learning for First-Person Activity Recognition
- Precoder Design in User-Centric Virtual Cell Networks
- A Sequential Constraint Relaxation Algorithm for Rank-One Constrained Problems
- A Primal-Dual Line Search Method and Applications in Image Processing
- Bayesian Framework for Mobility Pattern Discovery Using Mobile Network Events
SPTM-P1: Signal Processing Theory and Methods
Poster
Room: Poster Area 2 Level 1Chair: Andreas Jakobsson (Lund University, Sweden)
- Radar Detection Schemes for Joint Temporal and Spatial Correlated Clutter Using Vector ARMA Models
- Separation of Delayed Parameterized Sources
- CFO Estimation over Complex-Valued Non-Circular AR(1) Modeling for Rayleigh Flat Fading Channel
- Jeffrey's Divergence Between Autoregressive Moving-Average Processes
- New Model Order Selection in Large Dimension Regime for Complex Elliptically Symmetric Noise
- A Bootstrap Method for Sinusoid Detection in Colored Noise and Uneven Sampling. Application to Exoplanet Detection
- A Multimodal Asymmetric Exponential Power Distribution: Application to Risk Measurement for Financial High-Frequency Data
- A Fast and Accurate Chirp Rate Estimation Algorithm Based on the Fractional Fourier Transform
- Linear Complex Iterative Frequency Estimation of Sparse and Non-Sparse Pulse and Point Processes
- Convergence Acceleration of Alternating Least Squares with a Matrix Polynomial Predictive Model for PARAFAC Decomposition of a Tensor
- Comparing a Complex-Valued Sinusoidal Process with an Autoregressive Process Using Jeffrey's Divergence
- Canonical Piecewise-Linear Representation of Curves in the Wave Digital Domain
- The ASTRES Toolbox for Mode Extraction of Non-Stationary Multicomponent Signals
- Sparse Frequency Extrapolation of Spectrograms
- Co-Prime Sampling Jitter Analysis
- Full Proportionate Functional Link Adaptive Filters for Nonlinear Acoustic Echo Cancellation
SS14: Special Session on Multivariate Analysis for Audio Signal Source Enhancement
Lecture
Session organizers: Francesco Nesta and Zbyněk Koldovský
Room: Aegle AChairs: Francesco Nesta (Conexant Systems, USA), Zbynek Koldovsky (Technical University of Liberec, Czech Republic)
- 14:30 Audio/Video Supervised Independent Vector Analysis Through Multimodal Pilot Dependent Components
- 14:50 Orthogonally Constrained Independent Component Extraction: Blind MPDR Beamforming
- 15:10 EEG-based Attention-Driven Speech Enhancement for Noisy Speech Mixtures Using N-fold Multi-Channel Wiener Filters
- 15:30 Data-driven and Physical Model-based Designs of Probabilistic Spatial Dictionary for Online Meeting Diarization and Adaptive Beamforming
- 15:50 Experimental Analysis of Optimal Window Length for Independent Low-Rank Matrix Analysis
SS8: Special Session on Component Analysis for Computer Vision
Lecture
Session organizers: Stefanos Zafeiriou, Yannis Panagakis, and Mihalis Nicolaou
Room: PanaceaChair: Stefanos Zafeiriou (Imperial College London, United Kingdom (Great Britain))
- 14:30 Initializing Probabilistic Linear Discriminant Analysis
- 14:50 Complex Representations for Learning Statistical Shape Priors
- 15:10 Robust Low-rank Tensor Modelling Using Tucker and CP Decomposition
- 15:30 Lightweight Two-Stream Convolutional Face Detection
- 15:50 A Robust Ellipse Fitting Algorithm Based on Sparsity of Outliers
SSP-L1: Statistical Signal Processing
Lecture
Room: AcessoChair: Lee Swindlehurst (University of California at Irvine, USA)
- 14:30 Constrained Subspace Estimation via Convex Optimization
- 14:50 Analog Transmit Signal Optimization for Undersampled Delay-Doppler Estimation
- 15:10 Robust Trajectory-based Density Estimation for Geometric Structure Recovery
- 15:30 Crowdsource-based Signal Strength Field Estimation by Gaussian Processes
- 15:50 A General Non-Smooth Hamiltonian Monte Carlo Scheme Using Bayesian Proximity Operator Calculation
Wednesday, August 30, 16:10 - 16:30
Coffee break
Room: Level 1
Wednesday, August 30, 16:30 - 18:10
AASP-P1: Acoustic Sensor Array Processing/Signal Enhancement and Restoration
Poster
Room: Poster Area 1 Level 1Chair: Sharon Gannot (Bar-Ilan University, Israel)
- 3D Exterior Soundfield Capture Using Pressure and Gradient Microphone Array on 2D Plane
- TDOA Estimation Based on Phase-Voting Cross Correlation and Circular Standard Deviation
- Successive Relative Transfer Function Identification Using Single Microphone Speech Enhancement
- Multiple DOA Estimation Based on Estimation Consistency and Spherical Harmonic Multiple Signal Classification
- Design and Analysis of Second-order Steerable Differential Microphone Arrays
- Zadoff-Chu Coded Ultrasonic Signal for Accurate Range Estimation
- Time-difference of Arrival Model for Spherical Microphone Arrays and Application to Direction of Arrival Estimation
- ADMM-Based Audio Reconstruction for Low-Cost-Sound-Monitoring
- AUDASCITY: AUdio Denoising by Adaptive Social CosparsITY
- A Perceptually-Weighted Deep Neural Network for Monaural Speech Enhancement in Various Background Noise Conditions
- Low-Complexity Non-Uniform Penalized Affine Projection Algorithms for Active Noise Control
- Amplitude and Phase Dereverberation of Monocomponent Signals
BSIP-L2: Biomedical Signal and Image Processing
Lecture
Room: PanaceaChair: Dimitri Van De Ville (Ecole Polytechnique Fédérale de Lausanne, Switzerland)
- 16:30 Analysis of the Photic Driving Effect via Joint EEG and MEG Data Processing Based on the Coupled CP Decomposition
- 16:50 Beat-to-beat ECG Features for Time Resolution Improvements in Stress Detection
- 17:10 A Page-Hinkley Based Method for HFOs Detection in Epileptic Depth-EEG
- 17:30 Cyclostationary Analysis of ECG Signals Acquired Inside an Ultra-High Field MRI Scanner
- 17:50 Automatic Characterization of Sleep Need Dissipation Using a Single Hidden Layer Neural Network
CSSM-L2: Compressed Sensing
Lecture
Room: Aegle BChair: Georgios B. Giannakis (University of Minnesota, USA)
- 16:30 Pathwise Least Angle Regression and A Significance Test for the Elastic Net
- 16:50 Compressive Sensing and Sparse Antenna Arrays for Indoor 3-D Microwave Imaging
- 17:10 Optimal Number of Measurements for Compressed Sensing with Quadratically Decreasing SNR
- 17:30 Distributed Compressive Sensing: Performance Analysis with Diverse Signal Ensembles
- 17:50 Transform Learning Algorithm Based on the Probability of Representation of Signals
DISPPS-P1: Design and Implementation of SP Systems/SP for Power Systems and Internet of Things
Poster
Room: Poster Area 2 Level 1Chair: Vassilis Paliouras (University of Patras, Greece)
- Multiplierless Unified Architecture for Mixed Radix-2/3/4 FFTs
- Buffer Dimensioning for Throughput Improvement of Dynamic Dataflow Signal Processing Applications on Multi-Core Platforms
- An Embedded Solution for Multispectral Palmprint Recognition
- Parametrisable Digital Design of a Sphere Decoder with High-Level Synthesis
- An Approximate Hardware Check Node for $\lambda$-min-based LDPC Decoders
- Smart Signal Interconnection by the Use of a Photosensitive Polymer
- Compact Framework for Reproducible Analysis of Finite Wordlength Effects in Linear Digital Networks
- The Design of a Homotopy-based 1-D Seismic FIR F-X Wavefield Extrapolation Filters
- The Design of Seismic Migration Complex-Valued Finite Impulse Response Filters
- Classification of Partial Discharge EMI Conditions Using Permutation Entropy-based Features
- Wind Turbine Gearbox Vibration Signal Signature and Fault Development Through Time
- Distributed Computational Load Balancing for Real-Time Applications
- Non-intrusive Condition Monitoring for Manufacturing Systems
SENS-L2: Sensor Array and Multichannel Signal Processing
Lecture
Room: Aegle AChair: Maria S. Greco (University of Pisa, Italy)
- 16:30 A GLRT Approach for Detecting Correlated Signals in White Noise in Two MIMO Channels
- 16:50 Low Cost Subspace Tracking Algorithms for Sparse Systems
- 17:10 Source Enumeration in Large Arrays Using Corrected Rao's Score Test and Relatively Few Samples
- 17:30 Bayesian Restoration of Reflectivity and Range Profiles from Subsampled Single-Photon Multispectral Lidar Data
- 17:50 On the Use of Tight Frames for Optimal Sensor Placement in Time-Difference of Arrival Localization
SS13: Special Session on Machine and Signal learning for Big Data
Lecture
Session organizers: Jean-Luc Starck and Panos Tsakalides
Room: HippocratesChair: Panagiotis Tsakalides (FORTH-ICS and University of Crete, Greece)
- 16:30 Solving Large-scale Systems of Random Quadratic Equations via Stochastic Truncated Amplitude Flow
- 16:50 Dictionary Learning from Incomplete Data for Efficient Image Restoration
- 17:10 Low-rank and Sparse NMF for Joint Endmembers' Number Estimation and Blind Unmixing of Hyperspectral Images
- 17:30 Multi-Frequency Image Reconstruction for Radio-Interferometry with Self-Tuned Regularization Parameters
- 17:50 A Distributed Learning Architecture for Big Imaging Problems in Astrophysics
SSP-L2: Statistical Signal Processing
Lecture
Room: AcessoChairs: Kostas Berberidis (University of Patras, Greece), Ercan Kuruoğlu (CNR, Pisa, Italy)
- 16:30 Fisher Information Matrix for Non-Circular Complex Elliptical Symmetric Distributions with Application to DOA Estimation
- 16:50 Robust Object Characterization from Lensless Microscopy Videos
- 17:10 Nonparametric Detection Using Empirical Distributions and Bootstrapping
- 17:30 ON THE EFFICIENCY OF MAXIMUM-LIKELIHOOD ESTIMATORS of MISSPECIFIED MODELS
- 17:50 On Joint Order and Bandwidth Selection for Identification of Nonstationary Autoregressive Processes
Wednesday, August 30, 20:30 - 23:59
Conference Banquet
Thursday, August 31, 08:40 - 09:40
PLEN-4: The Power of Low Rank Tensor Approximations in Smart Patient Monitoring
Prof. Sabine Van Huffel
Room: HippocratesChair: Michael Unser (Ecole Polytechnique Fédérale de Lausanne, Switzerland)
Thursday, August 31, 09:40 - 10:00
Coffee break
Room: Level 1
Thursday, August 31, 10:00 - 12:00
IVM-P2: Image, Video and Multimedia Processing
Poster
Room: Poster Area 2 Level 1Chair: Athanasios A. Rontogiannis (National Observatory of Athens, Greece)
- Efficient Parallel Architecture for a Real-time UHD Scalable HEVC Encoder
- Prediction Mode Based Reference Line Synthesis for Intra Prediction of Video Coding
- Low Complexity Intra Mode Decision Algorithm for 3D-HEVC
- Visual Color Difference Evaluation of Standard Color Pixel Representations for High Dynamic Range Video Compression
- A Machine Learning Approach to Reducing Image Coding Artifacts
- Patch-based Image Denoising: Probability Distribution Estimation vs. Sparsity Prior
- Parameter Estimation in Spike and Slab Variational Inference for Blind Image Deconvolution
- Billboard Deformation via 3D Voxel by Using Optimization for Free-viewpoint System
- A New Adaptive Video SRR Algorithm with Improved Robustness to Innovations
- Phase Contrast Computed Tomography Using Continuous THz Source
- Heuristics for Tile Parallelism in HEVC
- Performance and Energy Consumption Analysis of the X265 Video Encoder
- Edge-Aware Depth Motion Estimation - A Complexity Reduction Scheme for 3D-HEVC
- Frequency Spectrum Regularization for Pattern Noise Removal Based on Image Decomposition
- Adaptive Colour-Space Selection in High Efficiency Video Coding
- HDR Image Compression with Optimized JPEG Coding
- The Iterative 2D Windowed Fourier Transform: A SOS Approach to Speckle Noise Reduction in Digital Holography
- MAP Tomographic Reconstruction with a Spatially Adaptive Hierarchical Image Model
- Topographical Pattern Analysis Using Wavelet Based Coherence Connectivity Estimation in the Distinction of Meditation and Non-meditation EEG
MLSP-L2: Machine Learning for Signal Processing
Lecture
Room: HippocratesChairs: Konstantinos Diamantaras (TEI of Thessaloniki, Greece), Ercan Kuruoğlu (CNR, Pisa, Italy)
- 10:00 Person Re-identification Based on Deep Multi-instance Learning
- 10:20 SparkDict: A Fast Dictionary Learning Algorithm
- 10:40 Penalty Learning for Changepoint Detection
- 11:00 An Effective Feature Selection Method Based on Pair-Wise Feature Proximity for High Dimensional Low Sample Size Data
- 11:20 Dictionary Learning for Spontaneous Neural Activity Modeling
- 11:40 Computationally Efficient Online Regression via LSTM Neural Networks
NSP-L1: Nonlinear Signal Processing
Lecture
Room: Aegle AChair: Ali Taylan Cemgil (Bogazici University, Turkey)
- 10:00 Distributed Particle Filtering Under Real-Time Constraints
- 10:20 An Approximate Minimum Variance Filter for Nonlinear Systems with Randomly Delayed Observations
- 10:40 Online Learning in L2 Space with Multiple Gaussian Kernels
- 11:00 Maxout Filter Networks Referencing Morphological Filters
- 11:20 Solution of the Inverse Frobenius-Perron Problem for Semi-Markov Chaotic Maps via Recursive Markov State Disaggregation
SLP-L2: Speech Analysis and Coding
Lecture
Room: PanaceaChair: Tomoki Toda (Nagoya University, Japan)
- 10:00 Flexible and Scalable Transform-Domain Codebook for High Bit Rate CELP Coders
- 10:20 Performance Analysis of Several Pitch Detection Algorithms on Simulated and Real Noisy Speech Data
- 10:40 Modeling Formant Dynamics in Speech Spectral Envelopes
- 11:00 A Novel Filterbank for Epoch Estimation
- 11:20 Pitch Prediction from Mel-generalized Cepstrum — a Computationally Efficient Pitch Modeling Approach for Speech Synthesis
- 11:40 Multi-Channel Estimation of Power Spectral Density Matrix Using Inter-Frame and Inter-Band Information
SPTM-L2: Signal and System Modeling and Estimation
Lecture
Room: Aegle BChair: Steve McLaughlin (Heriot Watt University, United Kingdom (Great Britain))
- 10:00 Optimal High-Dimensional Shrinkage Covariance Estimation for Elliptical Distributions
- 10:20 Misspecified Cramér-Rao Bounds for Complex Unconstrained and Constrained Parameters
- 10:40 The Outlier-Corrected-Data-Adaptive Lasso: A New Robust Estimator for the Independent Contamination Model
- 11:00 On Characterization and Application of Oscillatory Almost-Cyclostationary Processes
- 11:20 Jeffrey's Divergence Between Complex-Valued Sinusoidal Processes
- 11:40 A Kernel Density-Based Particle Filter for State and Time-Varying Parameter Estimation in Nonlinear State-Space Models
SS11: Special Session on Graph Signal Processing
Lecture
Session organizers: Antonio G. Marques and Geert Leus
Room: AcessoChairs: Geert Leus (Delft University of Technology, The Netherlands), Antonio G. Marques (Universidad Rey Juan Carlos, Spain)
- 10:00 Graph Clustering for Localization Within a Sensor Array
- 10:20 Graph Sampling with Determinantal Processes
- 10:40 Inference of Spatiotemporal Processes over Graphs via Kernel Kriged Kalman Filtering
- 11:00 Optimal Sampling Strategies for Adaptive Learning of Graph Signals
- 11:20 Coordinate Descent Accelerations for Signal Recovery on Scale-free Graphs Based on Total Variation Minimization
- 11:40 Collaborative Filtering via Graph Signal Processing
SS12: Special Session on Hybrid Analog/Digital Signal Processing for Hardware-Efficient Large Scale Antenna Arrays
Lecture
Session organizers: Christos Masouros, Mathini Sellathurai, and Constantinos Papadias
Room: MelambusChairs: Christos Masouros (University College London, United Kingdom (Great Britain)), Constantinos B. Papadias (Athens Information Technology, Greece)
- 10:00 Tunable Load MIMO with Quantized Loads
- 10:20 Multi-Way Massive MIMO with Maximum-Ratio Processing and Imperfect CSI
- 10:40 Scheduling and Precoding in Hybrid Analog-Digital Multiantenna Spectrum Sharing Systems
- 11:00 A Novel Hybrid Analog-Digital Transmitter for Multi-antenna Base Stations
- 11:20 Multi-Antenna Transmission Using ESPAR with Peak Power Constraints
- 11:40 Large Load-Controlled Multiple-Active Multiple-Passive Antenna Arrays: Transmit Beamforming and Multi-User Precoding
SS6: Special Session on Bird Audio Signal Processing
Poster
Session organizers: Dan Stowell, Hervé Glotin, Yannis Stylianou, and Mike Wood
Room: Poster Area 1 Level 1Chairs: Dan Stowell (Queen Mary - University of London, United Kingdom (Great Britain)), Hervé Glotin (Université du Sud Toulon-Var / LSIS, France)
- Stacked Convolutional and Recurrent Neural Networks for Bird Audio Detection
- Densely Connected CNNs for Bird Audio Detection
- Classification of Bird Song Syllables Using Wigner-Ville Ambiguity Function Cross-Terms
- Convolutional Recurrent Neural Networks for Bird Audio Detection
- Joint Detection and Classification Convolutional Neural Network on Weakly Labelled Bird Audio Detection
- Rapid Bird Activity Detection Using Probabilistic Sequence Kernels
- Automatic Frequency Feature Extraction for Bird Species Delimitation
- Two Convolutional Neural Networks for Bird Detection in Audio Signals
- Masked Non-negative Matrix Factorization for Bird Detection Using Weakly Labeled Data
- Archetypal Analysis Based Sparse Convex Sequence Kernel for Bird Activity Detection
- Automatic Detection of Bird Species from Audio Field Recordings Using HMM-based Modelling of Frequency Tracks
Thursday, August 31, 12:00 - 13:30
Lunch break
Thursday, August 31, 13:30 - 14:30
PLEN-5: Speech Synthesis: Where Did the Signal Processing Go?
Prof. Simon King
Room: HippocratesChair: Shrikanth Narayanan (University of Southern California, USA)
Thursday, August 31, 14:30 - 16:10
AASP-P2: Audio and Acoustic Signal Processing Applications
Poster
Room: Poster Area 1 Level 1Chair: Tomoki Toda (Nagoya University, Japan)
- A Variational EM Method for Pole-Zero Modeling of Speech with Mixed Block Sparse and Gaussian Excitation
- Order Adaptive Golomb Rice Coding for High Variability Sources
- Time-Scale Wavelet Scattering Using Hyperbolic Tangent Function for Vessel Sound Classification
- Non-Intrusive Bit-Rate Detection of Coded Speech
- Harmonic and Percussive Source Separation Using a Convolutional Auto Encoder
- Novel TEO-based Gammatone Features for Environmental Sound Classification
- Automatic Organisation and Quality Analysis of User-Generated Content with Audio Fingerprinting
- A Subjective Evaluation on Mixtures of Crowdsourced Audio Recordings
- Discriminant Kernel Learning for Acoustic Scene Classification with Multiple Observations
- Dual-band PWM Audio Coding for Ultrasound Artefact Reduction
- Feasibility of Vocal Emotion Conversion on Modulation Spectrogram for Simulated Cochlear Implants
- Detection of Alarm Sounds in Noisy Environments
- Voice Pathology Distinction Using Autoassociative Neural Networks
- Automatic Music Transcription Using Low Rank Non-Negative Matrix Decomposition
- Feature-based Characterization of Violin Timbre
- Empirical Study of Drone Sound Detection in Real-Life Environment with Deep Neural Networks
- An Approach for Self-Training Audio Event Detectors Using Web Data
- Automated Detection of Geometric Defects on Connecting Rod via Acoustic Resonance Testing
- Frequency Estimation for Monophonical Music by Using a Modified VMD Method
BIO-L1: Signal Processing for BioInformatics
Lecture
Room: HippocratesChair: Erchin Serpendin (Texas A&M University, USA)
- 14:30 Learning Directed-Acyclic-Graphs from Multiple Genomic Data Sources
- 14:50 Sparse-Low Rank Matrix Decomposition Framework for Identifying Potential Biomarkers for Inflammatory Bowel Disease
- 15:10 Reconstructing the Forest of Lineage Trees of Diverse Bacterial Communities Using Bio-inspired Image Analysis
- 15:30 Your Gaze Betrays Your Age
- 15:50 Automatic Characterization of Ambulatory Patterns of Utilitarian and Leisure Trips
IVM-L3: Image, Video and Multimedia Processing
Lecture
Room: PanaceaChair: Anastasios Delopoulos (Aristotle University of Thessaloniki, Greece)
- 14:30 Image Coding Based on Patch-Driven Inpainting
- 14:50 Microlens Image Sparse Modelling for Lossless Compression of Plenoptic Camera Sensor Images
- 15:10 A Preprocessing Technique for Improving the Compression Performance of JPEG 2000 for Images with Sparse or Locally Sparse Histograms
- 15:30 PharmaPack: Mobile Fine-Grained Recognition of Pharma Packages
- 15:50 Two-layer Tracking for Occlusion Handling and Inter-sensor Identification in Multiple Depth Sensors-based Object Detection and Tracking
RADAR-P1: Radar Signal Processing
Poster
Room: Poster Area 2 Level 1Chair: Constantinos B. Papadias (Athens Information Technology, Greece)
- An Approach to Power Allocation in MIMO Radar with Sparse Modeling for Coherence Minimization
- A New Height-Estimation Method Using FMCW Radar Doppler Beam Sharpening
- Multi-Doppler Resolution Automotive Radar
- Multivariate Change Detection on High Resolution Monovariate SAR Image Using Linear Time-Frequency Analysis
- Data-Driven Method of Reverse Modelling for Multi-Function Radar
- Optimal Design of Sparse MIMO Arrays for Near-Field Ultrawideband Imaging
- Design of Multi-Carrier MIMO Radar Array for DOA Estimation
- Target Detection by GPS Forward-Scattering System
- Spectrum Reconstruction with Nonuniform Fast Fourier Transform for MIMO SAR Azimuth Nonuniform Sampling
SENS-L3: Sensor Array and Multichannel Signal Processing
Lecture
Room: AcessoChair: Marius Pesavento (Technische Universität Darmstadt & Merckstr. 25, Germany)
- 14:30 Projector's Weighting for W-MUSIC: An Alternative to RMT
- 14:50 Refinement of Time-Difference-Of-Arrival Measurements via Rank Properties in Two-Dimensional Space
- 15:10 Sparse Linear Nested Array for Active Sensing
- 15:30 Near-Optimal Greedy Sensor Selection for MVDR Beamforming with Modular Budget Constraint
- 15:50 Gridless Compressed Sensing for Fully Augmentable Arrays
SPCOM-L3: Signal Processing for Communications
Lecture
Room: Aegle BChair: Christoph F Mecklenbräuker (Vienna University of Technology, Austria)
- 14:30 Frequency Domain Multipath Fading Channel Simulator Integrated with OFDM Transmitter for E-UTRAN Baseband Traffic Generator
- 14:50 Optimal Compression of Vibration Data with Lifting Wavelet Transform and Context-based Arithmetic Coding
- 15:10 Hybrid Digital-Analog Joint Source Channel Coding for Broadcast Multiresolution Communications
- 15:30 Simplified Analysis of HARQ Cooperative Networks Using Finite-State Markov Chains
- 15:50 Spatial Peak Power Minimization for Relaxed Phase M-PSK MIMO Directional Modulation Transmitter
SS4: Special Session on Automatic Detection of Defects in Images of Road Pavement Surface
Lecture
Session organizers: Paulo Lobato Correia and Henrique Oliveira
Room: MelambusChair: Henrique Oliveira (Instituto de Telecomunicações & Instituto Politécnico de Beja, Portugal)
- 14:30 Ongoing Tests and Improvements of the MPS Algorithm for the Automatic Crack Detection Within Grey Level Pavement Images
- 14:50 Pseudo-Ground Truth Data Collection on Pavement Images
- 15:10 Road Surface Crack Detection: Improved Segmentation with Pixel-based Refinement
- 15:30 Challenges and Lessons from the Successful Implementation of Automated Road Condition Surveys on a Large Highway System
- 15:50 3D Laser Imaging and Sparse Points Grouping for Pavement Crack Detection
SSP-L3: Statistical Signal Processing
Lecture
Room: Aegle AChair: Abdelhak M Zoubir (Darmstadt University of Technology, Germany)
- 14:30 Pairwise Markov Models for Stock Index Forecasting
- 14:50 Distributed Object Tracking Based on Information Weighted UAV Selection with Priory Objects
- 15:10 Robust Distributed Sequential Detection via Robust Estimation
- 15:30 Nonlinear Model Selection for PARMA Processes Using RJMCMC
- 15:50 Measure-Transformed Gaussian Quasi Score Test
Thursday, August 31, 16:10 - 16:30
Coffee break
Room: Level 1
Thursday, August 31, 16:30 - 18:10
BSIP-L3: Biomedical Signal and Image Processing
Lecture
Room: PanaceaChair: Alexander Bertrand (KU Leuven, Belgium)
- 16:30 Blind Parallel Interrogation of Ultrasonic Neural Dust Motes Based on Canonical Polyadic Decomposition: a Simulation Study
- 16:50 Error Correction Output Codding Coupled with the CSP for Motor Imagery BCI
- 17:10 Finger and Forehead PPG Signal Comparison for Respiratory Rate Estimation Based on Pulse Amplitude Variability
- 17:30 PARAFAC2 and Its Block Term Decomposition Analog for Blind fMRI Source Unmixing
- 17:50 ESTIMATION OF THE BLURRING KERNEL IN EXPERIMENTAL HR-pQCT IMAGES BASED ON MUTUAL INFORMATION
CSSM-P1: Applications of Sparse Representations; Sparse/Low-dimensional Parameter Estimation and Signal Recovery
Poster
Room: Poster Area 2 Level 1Chair: Athina Petropulu (Rutgers, The State University of New Jersey, USA)
- Unveiling Bias Compensation in Turbo-Based Algorithms for (discrete) Compressed Sensing
- A Gridless Sparse Method for Super-Resolution of Harmonics
- Online Group-Sparse Estimation Using the Covariance Fitting Criterion
- Wideband DoA Estimation Based on Joint Optimisation of Array and Spatial Sparsity
- Structurally Random Fourier Domain Compressive Sampling and Frequency Domain Beamforming for Ultrasound Imaging
- Time-Data Trade-off in the Sparse Fourier Transform
- Improved Image Discrimination Using Fast Non-linear Orthogonal Dictionary Learning
- Code Properties Analysis for the Implementation of a Modulated Wideband Converter
- A Two-term Penalty Function for Inverse Problems with Sparsity Constrains
- Multi Denoising Approximate Message Passing for Optimal Recovery with Lower Computational Cost
- Recovery of Boolean Sparse-Signals with Unknown Sparsity Level
- A Minimax Dictionary Expansion for Sparse Continuous Reconstruction
- A New Algorithm for Training Sparse Autoencoders
- A Generalization of Weighted Sparse Decomposition to Negative Weights
- A Micro-Motion Information Reconstruction Method Based on Compressed Sensing for Precession Ballistic Targets
- Multivariate Iterative Hard Thresholding for Sparse Decomposition with Flexible Sparsity Patterns
- Block Sparse Vector Recovery via Weighted Generalized Range Space Property
IFS-P1: Biometrics and Security-related Applications
Poster
Room: Poster Area 1 Level 1Chair: Jean Luc Dugelay (Eurecom, France)
- Frequency Diverse Array Beamforming for Physical-Layer Security with Directionally-Aligned Legitimate User and Eavesdropper
- Botnet Identification in Multi-Clustered DDoS Attacks
- Exploring Deep Learning Image Super-Resolution for Iris Recognition
- Video Phylogeny Tree Reconstruction Using Aging Measures
- Improved Reversible Data Hiding in Encrypted Images Based on Reserving Room After Encryption and Pixel Prediction
- Trust the Biometric Mainstream: Multi-biometric Fusion and Score Coherence
- Multi-Way Regression for Age Prediction Exploiting Speech and Face Image Information
- Age Group Detection Using Smartphone Motion Sensors
- Secure Communication Protocol for a Low-Bandwidth Audio Channel
RADAR-L1: Radar and Sonar Signal Processing
Lecture
Room: AcessoChair: Maria S. Greco (University of Pisa, Italy)
- 16:30 Design of Binary Sequences with Low PSL/ISL
- 16:50 Range Migrating Target Detection in Correlated Compound-Gaussian Clutter
- 17:10 Random Phase Center Motion Technique for Enhanced Angle-Doppler Discrimination Using MIMO Radars
- 17:30 Hybrid Optimization Method for Cognitive and MIMO Radar Code Design
- 17:50 Array Spatial Thinning for Interference Mitigation by Semidefinite Programming
SPCOM-L4: Signal Processing for Communications
Lecture
Room: HippocratesChair: David Luengo (Universidad Politecnica de Madrid (UPM), Spain)
- 16:30 Boosting LINC Systems Combiners Efficiency Through Ring-type Magnitude Modulation
- 16:50 A Novel Channel Estimation Scheme for Multicarrier Communications with the Type-I Even Discrete Cosine Transform
- 17:10 Prequalification of VDSL2 Customers for G.fast Services
- 17:30 Traffic-Aware Transmission Mode Selection in D2D-enabled Cellular Networks with Token System
- 17:50 Toward Green Communications Using Semi-Blind Channel Estimation
SS1: Special Session on Acoustic Scene Analysis and Signal Enhancement using Microphone Array
Lecture
Session organizers: Shoji Makino and Nobutaka Ono
Room: Aegle AChairs: Shoji Makino (University of Tsukuba, Japan), Nobutaka Ono (National Institute of Informatics, Japan)
- 16:30 Semi-Blind Student's t Source Separation for Multichannel Audio Convolutive Mixtures
- 16:50 Exploring Sound Source Separation for Acoustic Condition Monitoring in Industrial Scenarios
- 17:10 Analysis of the Robustness of Neural Network-Based Target Activity Detection
- 17:30 Speaker Extraction Using LCMV Beamformer with DNN-based SPP and RTF Identification Scheme
- 17:50 Acoustic Scene Classification Based on Generative Model of Acoustic Spatial Words for Distributed Microphone Array
SS10: Special Session on Cooperative and Distributed Algorithms for Signal Processing and Self-Organization over Wireless Ad-Hoc/Sensor Networks
Lecture
Session organizers: Michael Muma and Dimitris Ampeliotis
Room: Aegle BChair: Michael Muma (Darmstadt University of Technology, Germany)
- 16:30 Coordinate-Descent Adaptation over Networks
- 16:50 Distributed Recursive Least Squares Strategies for Adaptive Reconstruction of Graph Signals
- 17:10 Distributed Dictionary Learning via Projections onto Convex Sets
- 17:30 Adaptive Diffusion-Based Track Assisted Multi-Object Labeling in Distributed Camera Networks
- 17:50 Distributed Efficient Multimodal Data Clustering
Friday, September 1, 08:30 - 10:10
AASP-L5: Audio and Speech Source Separation/Signal Enhancement and Restoration
Lecture
Room: PanaceaChair: Constantine Kotropoulos (Aristotle University of Thessaloniki, Greece)
- 08:30 Speech Enhancement Using Modulation-Domain Kalman Filtering with Active Speech Level Normalized Log-Spectrum Global Priors
- 08:50 Multiple Far Noise Suppression in a Real Environment Using Transfer-Function-Gain NMF
- 09:10 Antarctic Blue Whale Calls Detection Based on an Improved Version of the Stochastic Matched Filter
- 09:30 Performance Evaluation of Nonlinear Speech Enhancement Based on Virtual Increase of Channels in Reverberant Environments
- 09:50 Independent Vector Analysis with Frequency Range Division and Prior Switching
BSIP-L4: Biomedical Signal and Image Processing
Lecture
Room: Aegle AChair: Daniel Wesierski (Gdansk University of Technology, Poland)
- 08:30 Surgical Tool Tracking by On-line Selection of Structural Correlation Filters
- 08:50 MoveHN-A Database to Support the Development of Motion Based Biosignal Processing Systems
- 09:10 Nonconvulsive Epileptic Seizures Detection Using Multiway Data Analysis
- 09:30 Prognostic Prediction of Histopathological Images by Local Binary Patterns and RUSBoost
- 09:50 Differential SART for sub-Nyquist Tomographic Reconstruction in Presence of Misalignments
EDU-L1: Signal Processing for Education
Lecture
Room: MelambusChair: Vassilis Paliouras (University of Patras, Greece)
IVM-L4: Image, Video and Multimedia Processing
Lecture
Room: Aegle BChair: Karen Egiazarian (Tampere University of Technology, Finland)
- 08:30 Unmixing Multitemporal Hyperspectral Images Accounting for Smooth and Abrupt Variations
- 08:50 Image Deblurring Using a Perturbation-Based Regularization Approach
- 09:10 Design of Orthonormal Haar-like Features for Fast Pattern Matching
- 09:30 Machine Learning for Automatic Classification of Volcano-Seismic Signatures
- 09:50 Skill Robot Library: Intelligent Path Planning Framework for Object Manipulation
SENS-P1: Sensor Array and Multichannel Signal Processing
Poster
Room: Poster Area 1 Level 1Chair: Athanasios A. Rontogiannis (National Observatory of Athens, Greece)
- Near Field Targets Localization Using Bistatic MIMO System with Symmetric Arrays
- Near Field Targets Localization Using Bistatic MIMO System with Spherical Wavefront Based Model
- Sub-Antenna Sparse Processing for Coherence Loss in Underwater Source Localization
- Precision Analysis of the Imaging Pipeline in the Square Kilometre Array
- Joint Sensor Placement and Power Rating Selection in Energy Harvesting Wireless Sensor Networks
- Separation of Vibration-Derived Sound Signals Based on Fusion Processing of Vibration Sensors and Microphones
- Performance Improvement for Wideband Beamforming with White Noise Reduction Based on Sparse Arrays
- Blind Spatial Sound Source Clustering and Activity Detection Using Uncalibrated Microphone Array
- Space-Time CUSUM for Distributed Quickest Detection Using Randomly Spaced Sensors Along a Path
- An Auto-Calibration Method for Uniform Linear Array Subject to Phase Errors
- Enhancing Polynomial MUSIC Algorithm for Coherent Broadband Sources Through Spatial Smoothing
- A Low-Complexity Equalizer for Massive MIMO Systems Based on Array Separability
- Design of Pre-coding and Combining in Hybrid Analog-Digital Massive MIMO with Phase Noise
SIPA-P1: Signal and Image Processing Applications
Room: Poster Area 3 Level 1
Chair: Ilianna Kollia (IBM, Greece)
- Distributed Approach for Deblurring Large Images with Shift-Variant Blur
- Astronomical Image Reconstruction with Convolutional Neural Networks
- A Smartphone-based Indoor Localisation System Using FM and Wi-Fi Signals
- Computationally Efficient Heart Rate Estimation During Physical Exercise Using Photoplethysmographic Signals
- Adaptive Time Corrected Gain for Ultrasound Through Time-Varying Wiener Deconvolution
- Joint Subsample Time Delay and Echo Template Estimations for Ultrasound Signals
- SAR Deception Jamming Target Recognition Based on the Shadow Feature
- A Blind Deconvolution Approach to Discontinuity Location and Characterization in Ultrasonic Nondestructive Testing
- Conjugate-Prior-Regularized Multinomial pLSA for Collaborative Filtering
- Pyramid Encoding for Fast Additive Quantization
- Using Deep Learning to Detect Price Change Indications in Financial Markets
- Sound-Environment Monitoring Technique Based on Computational Auditory Scene Analysis
SPCOM/IOT-P1: Signal Processing for Communications/Internet of Things
Poster
Room: Poster Area 2 Level 1Chair: Kostas Berberidis (University of Patras, Greece)
- CFO and Channel Estimation for MISO-OFDM Systems
- Rapid Prototyping and FPGA-in-the-Loop Verification of a DFrFT-based OFDM System
- Optimal Decentralized Coded Caching for Heterogeneous Files
- Interference MAC: Impact of Improper Gaussian Signaling on the Rate Region Pareto Boundary
- Constant Modulus Beamforming for Large-Scale MISOME Wiretap Channel
- Robust Precoding Scheme for Multi-user MIMO Visible Light Communication System
- A Continuous Cost Function for the Reconstruction of Wired Networks from Reflection Measurements
- A New SA-PNC Scheme for Uplink HetNets
- A Robust Signal Quantization System Based on Error Correcting Codes
- Multi-TOA Based Position Estimation for IR-UWB
- Compressive Multispectral Model for Spectrum Sensing in Cognitive Radio Networks
- Non-Binary Turbo-Coded OFDM-PLC System in the Presence of Impulsive Noise
- RAKE: a Simple and Efficient Lossless Compression Algorithm for the Internet of Things
- Collision and Packet Loss Analysis in a LoRaWAN Network
- Trust-based Strategies for Wireless Networks Under Partial Monitoring
SS22: Special Session on Sparsity and Low Rank Minimization Based Techniques for Wireless Communictions
Lecture
Session organizer: Masoumeh Azghani
Room: AcessoChair: Masoumeh Azghani (Sahand University of Technology, Iran)
- 08:30 Modeling and Estimation of Massive MIMO Channel Non-Reciprocity: Sparsity-aided Approach
- 08:50 Performance Evaluation of Adaptive Filters for Sparse Wireless Channel Estimation
- 09:10 A Fast Matrix Completion Method for Index Coding
- 09:30 Compressed Sensing Technique for Synchronization and Channel Estimation in OFDMA Uplink Transmissions
- 09:50 Sparsity-based Direction of Arrival Estimation in the Presence of Gain/Phase Uncertainty
Friday, September 1, 10:10 - 10:30
Coffee break
Room: Level 1
Friday, September 1, 10:30 - 12:30
SPTM-L3: Adaptive Signal Processing Algorithms
Lecture
Room: MelambusChair: Constantin Paleologu (University Politehnica of Bucharest, Romania)
- 10:30 An NLMS Algorithm for the Identification of Bilinear Forms
- 10:50 Quaternion Adaptive Line Enhancer
- 11:10 Low-complexity Approximation to the Kalman Filter Using Convex Combinations of Adaptive Filters from Different Families
- 11:30 A Design Methodology for the Gaussian KLMS Algorithm
- 11:50 Quasi-Newton Least-Mean Fourth Adaptive Algorithm
SS16: Special Session on Networks in Bio-imaging
Lecture
Session organizers: David Rousseau and Francoise Peyrin
Room: PanaceaChair: Francoise Peyrin (Universite de Lyon INSA Lyon & Inserm U1044 UMR CNRS 5220, France)
- 10:30 The Impact of Diverse Preprocessing Pipelines on Brain Functional Connectivity
- 10:50 Fine-scale Patterns Driving Dynamic Functional Connectivity Provide Meaningful Brain Parcellations
- 11:10 Lattice Boltzmann Method for Modelling of Biological Phenomena
- 11:30 Automated Analysis of Collagen Networks via Microscopy
- 11:50 On the Value of Graph-based Segmentation for the Analysis of Structural Networks in Life Sciences
SS17: Special Session on Novel Advances on Linear-in-the-Parameters Nonlinear Filters and Their Applications
Lecture
Session organizers: Alberto Carini, Danilo Comminiello, and Luis A. Azpicueta-Ruiz
Room: AcessoChairs: Luis Azpicueta-Ruiz (Universidad Carlos III de Madrid, Spain), Alberto Carini (University of Urbino, Italy)
- 10:30 Generalized CMAC Adaptive Ensembles for Concept-Drifting Data Streams
- 10:50 Recursive Multikernel Filters Exploiting Nonlinear Temporal Structure
- 11:10 Multivariance Nonlinear System Identification Using Wiener Basis Functions and Perfect Sequences
- 11:30 Modification of Second-Order Nonlinear IIR Filter for Compensating Linear and Nonlinear Distortions of Electrodynamic Loudspeaker
- 11:50 Steady-State Analysis of the Maximum Correntropy Volterra Filter with Application to Nonlinear Channel Equalization
- 12:10 Collaborative Adaptive Exponential Linear-in-the-parameters Nonlinear Filters
SS19: Special Session on Positioning in Challenging Environments
Lecture
Session organizers: Marco Luise and Pau Closas
Room: Aegle BChair: Marco Luise (University of Pisa, Italy)
- 10:30 Performance Analysis of Multi-frequency GNSS Carrier Tracking for Strong Ionospheric Scintillation Mitigation
- 10:50 NLOS Identification and Compensation for UWB Ranging Based on Obstruction Classification
- 11:10 An Empirical Study on Gamma Shadow Fading Based Localization
- 11:30 A Collaborative Method for Positioning Based on GNSS Inter Agent Range Estimation
- 11:50 Ranging Precision Analysis of LTE Signals
- 12:10 Robust Time-Of-Arrival Estimation in Multipath Channels with OFDM Signals
SS9: Special Session on Computational Methods for Audio Analysis
Lecture
Session organizers: Michele Scarpiniti, Jen-Tzung Chien, and Stefano Squartini
Room: Aegle AChair: Michele Scarpiniti (Sapienza University of Rome, Italy)
- 10:30 On the Feasibility of Personal Audio Systems over a Network of Distributed Loudspeakers
- 10:50 Glottal Mixture Model (GLOMM) for Speaker Identification on Telephone Channels
- 11:10 What Makes Audio Event Detection Harder than Classification?
- 11:30 Timbre Analysis of Music Audio Signals with Convolutional Neural Networks
- 11:50 A Hybrid Approach with Multi-channel I-Vectors and Convolutional Neural Networks for Acoustic Scene Classification
- 12:10 A Neural Network Approach for Sound Event Detection in Real Life Audio
Saturday, September 2, 09:00 - 17:00
W1: IWCIM: International Workshop on Computational Intelligence for Multimedia Understanding
Workshop
Workshop organizers: Enis Cetin, Behçet Ugur Töreyin, and Davide Moroni
Room: PanaceaW2: Multi-Learn 2017: Multimodal Processing, Modeling, and Learning Approaches for Human-Computer/Robot Interaction
Workshop
Workshop organizers: Vassilis Pitsikalis, Anastasios Roussos, Athanasia Zlatintsi, Xanthi Papageorgiou, and Mehdi Khamassi
Room: Aegle BW3: Deep Learning and Geometry
Workshop
Workshop organizers: Or Litany, Emanuele Rodolà, Michael Bronstein, Alex Bronstein, and Ron Kimmel
Room: Aegle AW4: Creative Design and Advanced Manufacturing: An Emerging Application Area for Signals and Systems
Workshop
Workshop organizers: Iestyn Jowers and Sibel Tari
Room: Acesso