Find Academic Supervisors

Niccolò PrettoView profile

Researcher

• Audio Preservation
• Cultural Heritage Informatics
• Human-Computer Interaction
• +3 more

Niccolò Pretto is a Researcher at the Faculty of Engineering, Free University of Bozen-Bolzano, Italy, based at NOI Techpark in Bolzano. He teaches Engineering of Mobile Systems for Bachelor in Computer Science students and Research Methods for Doctoral candidates in computer science. His research specializes in audio cultural heritage preservation, focusing on AI-driven solutions for analog magnetic tape restoration and international standardization efforts. Key projects include developing computer vision algorithms for audio tape anomaly detection, creating capacitive interfaces for stone artifacts, and co-authoring the MPAI/IEEE Audio Recording Preservation (ARP) standard. His work bridges musicology, archival science, and engineering to address challenges in electroacoustic music preservation and interactive heritage experiences. Analysis of his 15 most recent publications reveals three dominant themes: (1) Technical innovation in audio restoration (e.g., digital filters for speed/equalization correction), (2) Human-centered interaction design for cultural artifacts (e.g., submersible textile interfaces), and (3) Ethical AI standardization for heritage preservation. His publications consistently emphasize "active preservation" methodologies that combine philological rigor with computational approaches. Dr. Pretto maintains active collaborations with the Computational Sonology Center (CSC) at the University of Padova, where he has contributed to projects preserving Luciano Berio's audio archives and developing the FONTI 4.0 transcription system for historical oral sources. His teaching in mobile systems and research methods directly informs his applied work in heritage technology development. He operates from NOI Techpark, a leading Alpine innovation hub, where his laboratory focuses on sensor development for cultural heritage applications. Current projects include magnetoresistive textile interfaces for underwater interaction and AI-based anomaly detection systems for archival audio tapes, positioning his team at the forefront of preservation technology research.

• Signal Processing
• Remote Sensing
• Environmental Science
• +3 more

Gilles Delmaire is an Associate Professor specializing in signal processing, hyperspectral imaging, and environmental science. His research spans topics like super-resolution hyperspectral multisensor fusion , tensor decomposition , and butterfly species classification using advanced computational methods. Key research areas: Signal Processing, Remote Sensing, Environmental Science, and Machine Learning. Recent work focuses on hyperspectral data restoration , insect tracking algorithms , and air quality analysis in Mediterranean regions. Collaborations include institutions in France, Greece, Portugal, and Cyprus, with publications in IEEE, Pattern Analysis and Applications, and Science of the Total Environment.

• Computer Vision
• Generative Modeling
• Multimodal Foundation Models
• +4 more

Jiankang Deng is a Lecturer in the Department of Computing at Imperial College London, within the Faculty of Engineering. His research focuses on multi-modality foundation models, generative modeling of physical entities, and computer vision applications. He leads projects such as InsightFace.ai for facial analysis and synthesis. Previously, he earned his PhD (2020) from Imperial College under Prof. Stefanos Zafeiriou, focusing on deep face analysis and modeling. Education: PhD in Computing (2016-2020) from Imperial College London. Research interests include photorealistic facial reconstruction, generative adversarial networks, and multimodal learning. His work bridges computer vision with practical technologies for societal impact. Publications reflect expertise in 3D reconstruction, diffusion models, and cross-modal systems. Notable areas include hand motion analysis, face reflectance estimation, and tactile robotics. His work emphasizes scalability and real-world applicability. No awards listed explicitly, but his research contributions are evident through active publications and industry collaborations. Advising and lab work involve the IBUG research group, focusing on facial recognition and generative AI systems. Labs/Teams: Part of the Imaging and Biomedical Engineering Group (IBUG), collaborating on projects like FaceMAE for privacy-preserving recognition and MogFace for advanced face detection systems.

• Computer Security
• Machine Learning
• Hardware Design
• +6 more

Farinaz Koushanfar is a Professor at the University of California, San Diego (UCSD), with a former affiliation at the University of California, Berkeley. Her research focuses on advancing security, machine learning, and hardware design through interdisciplinary approaches. Key areas include adversarial defense mechanisms, cryptographic systems, federated learning, and zero-knowledge proofs. She has collaborated extensively with institutions and researchers globally, contributing to over 360 publications. Her work emphasizes practical security solutions, such as watermarking for intellectual property protection and methods to counteract adversarial attacks in neural networks. Recent trends in her publications highlight innovations in cache compression, robust watermarking for large language models, and securing wireless communication systems against modality-agnostic attacks. Collaborations with industry and academia underscore her commitment to real-world applications of theoretical advancements. Awards and grants are not explicitly listed here, but her prolific publication record and leadership in high-impact projects indicate significant recognition in her field. Advising and mentoring students and junior researchers are central to her academic contributions, though specific student names are not detailed in the provided text. Her lab’s work often intersects with emerging technologies like blockchain, edge computing, and privacy-preserving machine learning.

Arshdeep SinghView profile

Research Fellow

• Audio Signal Processing
• Machine Learning
• Neural Networks
• +3 more

Dr. Arshdeep Singh is a Research Fellow A at the Centre for Vision, Speech and Signal Processing (CVSSP) at the University of Surrey, specializing in AI-driven audio processing. He concurrently serves as a Sustainability Fellow at the University’s Institute for Sustainability and holds the UKAN+ Early Career Acoustic Champion title (2023). His research focuses on efficient neural network architectures for audio classification, model compression, and sustainable AI applications. Singh completed his PhD at IIT Mandi, India, with prior roles including internships at Intel Bangalore and CSIR-CSIO Chandigarh, and an M.E. from Panjab University (Gold Medal recipient). Research interests include audio signal processing, CNN compression via filter pruning, and sustainable AI. Notable contributions include developing lightweight CNN frameworks for acoustic scene classification and sound event detection, with applications in smart home technologies and industrial health monitoring. His work often targets resource-constrained devices, emphasizing real-world deployability. Publications highlight innovations like graph centrality-based filter pruning and quaternion transformations for CNN efficiency. Awards include the Panjab University Gold Medal for M.E. and recognition as an Early Career Acoustic Champion. Supervision includes MSc students (e.g., Soham Bhattacharya, Bars Szegedi) and undergraduates (Kristaps Redmers, Yan-Ping Liao). His interdisciplinary projects span audio captioning, embedded hardware deployment, and dataset creation for sound event detection in residential environments.

David SüdholtView profile

Visiting Professor

• Machine Learning
• Audio Engineering
• Sound Synthesis
• +3 more

David Südholt is a Visiting Professor at the School of Electronic Engineering and Computer Science, Queen Mary University of London, affiliated with the Centre for Digital Music (C4DM). His research focuses on machine learning integration with physical models for voice synthesis, exploring applications in text-to-speech systems, singing voice synthesis, and unconventional vocal expressions. He collaborates with industry partner Nemisindo and investigates themes like audio engineering and sound synthesis. His work bridges machine learning techniques with traditional physical modeling approaches to enhance synthesis quality and expressive capabilities. Key research interests include vocal tract modeling, timbre manipulation, real-time signal processing, and the implementation of finite difference schemes in audio synthesis. His projects aim to expand the expressive range of physical models to include non-standard vocal techniques (e.g., screams, whispers) through machine learning-driven parameter estimation. Recent publications highlight advancements in gradient-based vocal tract estimation, differentiable digital signal processing, and real-time timbre transfer using frameworks like DDSP. He also contributes to FAUST-based implementations of audio algorithms and interactive web-based sound synthesis tools for instruments like the langeleik. No academic awards or student advisement records are listed in the provided information.

Peter de WithView profile

Professor

• Video Compression
• Image Analysis
• Healthcare Applications
• +4 more

Peter de With is a Part-time Full Professor in the Department of Electrical Engineering at Eindhoven University of Technology (TU/e), leading the Video Coding & Architectures Group. His expertise spans video compression, image analysis in healthcare, surveillance, and multimedia. He holds a PhD from Delft University of Technology (1992) and has held roles at Philips Research, the University of Mannheim, and Cyclomedia Technology. His research focuses on video/image signal processing, machine learning, and healthcare applications such as esophageal cancer detection. He is an IEEE Fellow and has authored over 400 papers, receiving multiple awards for his work. Research interests include video coding, medical imaging, and system innovations in health, surveillance, and automotive sectors. Key publications address challenges in medical instrument detection, 3D ultrasound, and multiview rendering. He collaborates with industry partners like Bosch Security and hospitals for oncology research. His work bridges academic innovation with real-world applications, emphasizing practical solutions in healthcare technology and multimedia systems. Awards include IEEE Fellow status and paper awards from CE Chester Sall, SPIE, and Elsevier. He chairs program committees for IEEE conferences and holds 30 patents. His contributions to video analysis and system design have driven advancements in safety, security, and healthcare technologies.

Nilesh MadhuView profile

Professor

• Machine Learning
• Audio & Speech Enhancement
• Automated Audio Scene Analysis
• +4 more

Nilesh Madhu is a Professor for Audio and Speech Processing at Ghent University and imec, Belgium, where he leads research in the Internet Technology and Data Science Lab (IDLab). His academic journey began with a Dr.-Ing. degree (summa cum laude) from Ruhr-Universität Bochum, Germany in 2009, followed by a Marie-Curie postdoctoral fellowship at KU Leuven. Prior to his academic appointment, he served as Principal Scientist and team lead at NXP Semiconductors from 2011-2017, developing advanced audio algorithms for mobile devices. His research spans multiple domains within signal processing, with a particular focus on machine learning applications for audio and speech enhancement, automated audio scene analysis, and hearing prostheses. Professor Madhu's work bridges theoretical signal processing with practical implementations in communications, healthcare, and assistive technologies. Analysis of his recent publication record reveals a strong emphasis on deep learning approaches for speech enhancement, with particular attention to phase reconstruction, multichannel processing, and efficient model architectures. His research increasingly incorporates biomedical applications, particularly in cardiovascular monitoring using advanced sensing techniques like laser Doppler vibrometry. His laboratory work centers around the Internet Technology and Data Science Lab (IDLab) at Ghent University, where his team develops innovative signal processing algorithms with applications spanning mobile communications, hearing aids, and biomedical monitoring systems. The group maintains strong industry connections, evidenced by their focus on practical implementation constraints and real-world performance metrics.

Stuart CunninghamView profile

Senior Lecturer

• Affective Technologies
• User Experience (UX)
• Human-Computer Interaction
• +6 more

Dr. Stuart Cunningham is a Senior Lecturer in Computer Science at the University of Chester, where he also serves as Programme Leader for the MSc Advanced Computer Science, REF Unit of Assessment 11 co-ordinator, and Senior Postgraduate Research Tutor. Previously, he held roles at Manchester Metropolitan University (Visiting Research Fellow and Senior Lecturer) and Glyndwr University (Reader in Audio and Affective Computing, Head of Department, and Lecturer/Senior Lecturer). With 20+ years in higher education, his expertise spans academic leadership, teaching, and research in computing and creative technology hybrids. He holds a PhD in Computer Science from the University of Wales (2009), an MSc in Multimedia Communications from the University of Paisley (2003), and a BSc in Computer Networks (2001). Cunningham’s research focuses on affective technologies, audio compression (e.g., ACER codec), and interdisciplinary applications of sound design in fields like healthcare, gaming, and film. He chairs the Audio Mostly steering committee and contributed to the MPEG-SMR working group developing ISO/IEC 14496-23:2008. His work bridges technical and creative domains, exploring biofeedback sensors for emotional state analysis, Foley artistry in 3D animation, and auditory alerts in safety systems. He advocates for practice-led research methodologies that combine creative outputs with empirical validation. Cunningham has authored numerous publications, including research articles, book chapters, and creative works, and actively participates in peer reviewing for journals like IEEE Transactions and Personal and Ubiquitous Computing . In teaching, he emphasizes interactive/collaborative learning and portfolio-based assessment across undergraduate and postgraduate courses. He has designed and delivered degree apprenticeship programs, particularly during the pandemic, and teaches courses like Web Systems, Software Development, and User Experience Design. His research also extends to UX education, esports analytics, and assistive technologies for dementia care.

Michael ArnoldView profile

Professor

• Digital Watermarking
• Audio Security
• Information Forensics
• +1 more

Michael Arnold is Professor of Business Informatics, specializing in Algorithmics and Software Development at Leibniz University of Applied Sciences. His research centers on digital watermarking, multimedia security, and information forensics, with extensive publications in IEEE Transactions and major security conferences. Professor Arnold's innovations include phase-based audio watermarking techniques robust to acoustic transmission and methods for evaluating watermark attacks. His seminal work established foundational approaches for protecting digital audio through quantization and modulation techniques. He has contributed to standardization efforts through benchmark comparisons and developed security frameworks adopted in copyright protection systems. His book 'Techniques and Applications of Digital Watermarking and Content Protection' remains a key reference in multimedia security.

• Federated Learning
• Cybersecurity
• Edge Computing
• +4 more

Dr. Meikang Qiu is a faculty member at Texas A&M University Commerce (Department of Computer Science) and Columbia University (Department of Electrical Engineering). He received his PhD in Computer Science from the University of Texas at Dallas in 2007. His research spans distributed intelligence systems with current focus areas including federated learning security, efficient AI for edge devices, and multimodal learning applications in healthcare and finance. Qiu's research integrates machine learning with systems engineering, emphasizing privacy-preserving AI , robust distributed systems , and resource-constrained optimization . His recent work explores: (1) Defenses against adversarial attacks in federated environments, (2) Quantum-classical hybrid computing frameworks, and (3) Efficient model compression techniques for large language models. Publication analysis (2024-2026) reveals three dominant themes: (1) Security enhancements for distributed learning systems, (2) Efficiency optimizations for edge AI deployment, and (3) Cross-modal applications in medical and financial domains. His work consistently addresses scalability challenges in real-world AI systems.

Jeff BradburyView profile

Lecturer

• Sound Design
• Audio Production
• Video Production
• +3 more

Jeff Bradbury is a Lecturer and Internship Coordinator at the Department of Communication Studies, State University of New York at Oswego. He specializes in sound design for radio, television, film, and multimedia, with expertise in location sound recording, single-camera video production, music recording, and video compression technologies. MS in Television Radio and Film, S.I. Newhouse School, Syracuse University BS in Music Production and Recording, Ithaca College Contact: Office location 165 Hewitt Hall, email jeffrey.bradbury@oswego.edu . Office hours: Wednesdays 10:30 am–12:30 pm or by appointment.

• Digital Twins
• Augmented Reality/Virtual Reality (AR/VR)
• Wireless Sensor Networks (WSN)
• +4 more

KAMDJOU Hugues-Marie is a Researcher-Lecturer at CESI, affiliated with the Engineering & Numerical Tools research team within the LINEACT laboratory. He holds a PhD in Fundamental Computer Science from the University of Dschang (2022), a Master’s in Research (2017), and a Bachelor’s in Mathematics & Computer Science (2013), all from the University of Dschang. His research focuses on Digital Twins , Augmented Reality/Virtual Reality (AR/VR) , Wireless Sensor Networks (WSN) , and Data Compression . He leads the CDOP Project on optimizing AR/VR performance through data compression in resource-constrained environments. His work integrates Belief Function Theory for uncertainty management in network reliability. Teaching responsibilities include Computer Engineering cycles (3rd/4th years) and the Integrated Preparatory Cycle (1st/2nd years), covering Networks & Telecom , System Programming , and Statistics . Key publications include advancements in secure digital twin architectures, distributed data compression for low-resource WSNs, and failure prediction using belief models. His research bridges theoretical computer science with practical IoT/Industrial applications.

Elisabeth LAHALLEView profile

Associate Professor

• Signal Processing
• Medical Imaging
• Mechanical Vibration Analysis
• +3 more

Elisabeth LAHALLE is an Associate Professor at CentraleSupélec, affiliated with the Laboratoire des signaux et systèmes (L2S). Her research focuses on signal processing, medical imaging, mechanical vibration analysis, environmental monitoring, and compressed sensing. She leads projects in systems control, telecommunications, and data science applications in energy, Industry 4.0, and healthcare. Her work includes developing sparse spectral analysis techniques for blade vibration diagnostics, compressed sensing algorithms for medical imaging, and AI-driven environmental monitoring systems. She supervises PhD students such as Lisa Poirier-Herbeck (environmental surveillance), Antoine Bouchain (blade vibration analysis), and Grégory Baral-Baron (3D speed measurement). Teaching responsibilities include signal processing, data science, and biomedical imaging courses for engineering students at CentraleSupélec. She is part of the Inverse Problems Group and Modeling & Estimation Team within L2S, collaborating on projects like SYCOMORE and COMEDY. Active in international conferences and journal publications since 2008, her research bridges theoretical signal processing with practical applications in aerospace, healthcare, and environmental safety. Elisabeth holds a patent for Doppler-based aircraft speed measurement (EP 2720066 A1, 2014). She contributes to seminars like the UQSay and Energy@L2S, maintaining L2S’s reputation in interdisciplinary engineering research.

Radu Patrice HoraudView profile

Researcher

• Computer Vision
• Audio Signal Processing
• Robotics
• +5 more

Radu Patrice Horaud is a Researcher at Inria Grenoble Rhône-Alpes and a member of the RobotLearn team at Laboratoire Jean Kuntzmann, Université Grenoble Alpes. He holds a PhD from 1981 and has been a director of research since 1998. His work focuses on computational vision, audio-visual fusion, robotics, and machine learning, with applications in human-robot interaction and multimodal perception. Notable achievements include coordinating European projects, receiving two ERC grants (Advanced and Proof of Concept), and founding the Perception team. His research spans over 200 publications and includes contributions to 3D sensors, embodied audition, and Bayesian methods in inverse problems. Education: PhD (1981), postdoctoral work at SRI International (1982-1984), and CNRS researcher (1984-1998). Research Interests: Audio-visual scene analysis, robotics, machine learning, and multimodal fusion. His work emphasizes integrating audio and visual data for robotics and healthcare applications, such as the SPRING project in gerontological healthcare. Key Awards: ERC Advanced Grant (2014-2019), ERC Proof of Concept (2018-2019). His lab has also secured funding for projects like Socially Pertinent Robots in Gerontological Healthcare (SPRING). Labs/Teams: Formerly led the Perception team (2007-2021), now part of RobotLearn. Active in the Multidisciplinary Institute in Artificial Intelligence (MIAI) since 2019.