Efficient Machine Learning Systems for Signal Processing

Signal‑Processing Frontiers: Humanistic AI Solutions for Digital Forensics, Health, Well‑Being, and Fighting Disinformation

In this episode of the IEEE Signal Processing Society podcast, Dr. Rogério Augusto Bordini, a Post-doctoral Researcher and Science Journalist at the Artificial Intelligence Lab., Recod.ai, University of Campinas (Unicamp), interviews Dr. Anderson Rocha, Full Professor at the University of Campinas (Unicamp) specializing in Artificial Intelligence, Digital Forensics, and Reasoning for Complex Data. Their conversation explores how modern signal-processing techniques have been explored in various social sectors. Dr. Anderson Rocha   Professor Anderson Rocha, Former Director of Unicamp's Institute of Computing and two-time Chair of the IEEE Information Forensics and Security Technical Committee, was named an IEEE Fellow in 2023, an IEEE SPS Distinguished Lecturer in 2025, and an IEEE Biometrics Council Distinguished Lecturer also in 2025. Closing a remarkable year, he was awarded the prestigious Zeferino Vaz Prize—Unicamp's highest recognition. Recognized as one of the world's top scientists by Stanford, PLOS ONE, and Research.com, he holds fellowships from Microsoft and Google and co-founded the Recod.ai AI Lab at Unicamp over 16 years ago. In this episode, Dr. Rocha discusses applications of signal processing spanning digital forensics, wearable sensors, deepfake detection, and misinformation mitigation, while highlighting core algorithms, real-world healthcare applications, and emerging AI-driven forensic tools, and also provides insights into his research group's key differentiator—a humanistic, expert-in-the-loop approach to solution design.

Stopping Counterfeiting with QR Codes and AI

In this episode of the IEEE Signal Processing Society Podcast, Hemang Chawla, Solutions Lead at Scantrust, speaks with Justin Picard, Co-founder and CTO of Scantrust. Their conversation explores how modern signal processing, printing physics, and machine learning are being combined to combat the global problem of product counterfeiting through secure QR codes and copy detection technology. Dr. Justin Picard Dr. Justin Picard is the Co-founder and Chief Technology Officer of Scantrust, a company specializing in product authentication and traceability solutions. Originally from Canada and now based in Switzerland, Dr. Picard completed his Ph.D. in artificial intelligence before moving into digital watermarking and image security. After working in research and development roles across North America and Europe, Dr. Picard co-founded Scantrust to develop smartphone-based authentication systems that empower consumers and brands to verify product authenticity in real time. In this episode, Dr. Picard discusses the trillion-dollar global impact of counterfeiting, which now affects not only luxury goods but also everyday products such as food, industrial components, health supplements, and consumer goods—an issue intensified by e-commerce and global supply chains. He explains that traditional anti-counterfeiting methods, including holograms, UV inks, and forensic testing, struggle to scale in today’s digital marketplace because they rely on specialized equipment or human inspection.

Functional Brain Imaging: Signals, Imaging, and Graphs

Functional Brain Imaging: Signals, Imaging, and Graphs In this episode of the IEEE Signal Processing Society Podcast, Professor Borbála Hunyadi from the Mental Health and Neuroscience Research Institute, Maastricht University, The Netherlands interviews Dr. Dimitri Van De Ville, Full Professor at the École Polytechnique Fédérale de Lausanne (EPFL) and the University of Geneva, Switzerland. Their conversation explores how modern neuroimaging modalities, combined with advanced signal processing and computational methods, are transforming our understanding of brain function in health and disorder.   Dr. Dimitri Van De Ville Dr. Dimitri Van De Ville received his M.S. and Ph.D. degrees from Ghent University, Belgium, in 1998 and 2002, respectively. He was a postdoctoral fellow at EPFL before leading the Signal Processing Unit at the University Hospital of Geneva as part of the CIBM Center for Biomedical Imaging. Since 2024, he has been a Full Professor at EPFL’s Neuro-X Institute with a joint appointment at the University of Geneva. His interdisciplinary research focuses on computational neuroimaging, wavelets, sparsity, and graph signal processing, applied to MRI and M/EEG data. In this episode, he discusses current and emerging neuroimaging modalities such as intracranial recordings, fMRI, fNIRS, M/EEG, and functional ultrasound (fUS). He highlights how signal processing plays a vital role in data formation, preprocessing, and analysis, enabling researchers to extract meaningful information about brain activity. The discussion also touches on innovations such as independent component analysis, connectomics, and the growing influence of AI and deep learning in neuroimaging. Dr. Van De Ville concludes by reflecting on the field’s future—emphasizing multimodal integration, brain–body connectivity, and targeted neuromodulation as key directions for advancing both neuroscience research and clinical applications.

Audio Signal Processing in the Era of AI

In this episode of the IEEE Signal Processing Society podcast, Felicia Lim, a staff software engineer at Google, where she works on audio signal processing and machine learning, interviews Dr. Ivan Tashev, Partner Software Architect at Microsoft Research (MSR) – Redmond USA, where he leads the Audio and Acoustics Research Group. Their conversation explores the rapid development of novel algorithms in AI and their impact on the audio processing domain.    Dr. Ivan Tashev  Dr. Ivan Tashev is a Partner Software Architect at MSR in Redmond, WA, USA, where he leads the Audio and Acoustics Research Group and also coordinates the Brain-Computer Interfaces project. He is an Affiliate Professor in the Department of Electrical and Computer Engineering at the University of Washington in Seattle, USA, and an Honorary Professor at the Technical University of Sofia, Bulgaria. He is also an IEEE Fellow and a member of the Audio Engineering Society (AES) and the Acoustical Society of America (ASA). In this episode, Dr. Tashev discusses the unique challenges of audio signal processing as a specialized domain, examining why traditional statistical methods have limitations and how machine learning and AI approaches offer new solutions. He also talks about the future trajectory of machine learning and AI in transforming audio signal processing capabilities.

Trustworthy Machine Learning and Artificial Intelligence

In this episode of the IEEE Signal Processing Society podcast, Dr. Lav Varshney, Associate Professor of Electrical and Computer Engineering at the University of Illinois Urbana-Champaign interviews Dr. Kush Varshney, an IBM Fellow and globally recognized expert in trustworthy machine learning. Their conversation explores the multifaceted landscape of trustworthy AI.   Kush Varshney Kush R. Varshney is an IBM Fellow at IBM Research and a leading authority on trustworthy AI. His work focuses on making AI systems not only accurate but also fair, robust, explainable, transparent, inclusive, and beneficial. He is the author of a book entitled “Trustworthy Machine Learning” and creator of widely used toolkits like AI Fairness 360 and AI Explainability 360. In this episode, Dr. Varshney outlines the core principles of trustworthy AI and distinguishes it from related concepts such as AI ethics, AI safety, and responsible AI. He shares how signal processing techniques—like Boolean compressed sensing and continued fraction representations, and short-time Fourier transforms—inform his approach. The conversation covers the societal impact of AI, the shift toward generative and agentic models, the importance of governance and policy, and new research directions aimed at building more empowering and accountable AI systems.