Daniel Ramos is an Associate Professor at the Universidad Autónoma de Madrid and a member of the AUDIAS research group (https://audias.ii.uam.es/). His research focuses on forensic evidence evaluation and validation, speech and signal processing, machine learning, and artificial intelligence. He has visited different institutions worldwide with a strong research focus on forensic interpretation and Bayesian machine learning, including the University of Lausanne (Switzerland), the University of Stellenbosch (South Africa), the University of Edinburgh (UK), the Netherlands Forensic Institute (NFI), and the University of Cambridge (UK). He has also been a visiting professor in probabilistic machine learning at the Universidad de Buenos Aires (Argentina). Dr. Ramos has collaborated with different forensic institutions, notably in the long term with the Spanish Guardia Civil and the NFI, as well as with the Institute of Forensic Research at Krakow (Poland) and the International Forensic Research Institute at Florida International University (USA). An associate member of the ENFSI Forensic Speech and Audio Working Group, Dr. Ramos has pioneered the field of forensic speaker recognition using likelihood ratios, but also in other forensic disciplines such as forensic chemistry. His contributions to the validation of forensic likelihood ratios now serve as the basis for guidelines in different forensic institutions across Europe. He has been invited to multiple scientific events related to forensic science, notably by the NFI and the National Institute of Standards and Technology (NIST), and its Organization of Scientific Area Committees (OSAC), which drives the development of standards for forensic science in the USA.

Rigorous Forensic Automatic Speaker Recognition: Bayesian Decision Theory, Probabilistic Calibration and Case-Specific Validation

The use of automatic speaker recognition systems in forensic science has undergone a dramatic improvement in recent years in terms of scientific rigor, objectivity, and consensus. As a result, the discipline has become strongly aligned with the recommendations of the recently released ISO 21043 standard for forensic sciences. In this talk, we will identify three elements that are now essential for the proper and standardized use of automatic speaker recognition systems in forensic science. First, the adoption of a Bayesian decision-theoretical framework ensures the logical incorporation of system information, expressed as a likelihood ratio, into the decision-making process of judges or juries. Second, the probabilistic calibration of likelihood ratios ensures that decisions are made optimally by the fact finder. Third, the strict and systematic validation of systems under case-specific conditions ensures that forensic casework is conducted with sufficient quality. In this context, the contribution and impact of the speaker recognition community have been paramount, with the proposal of techniques such as score-based likelihood ratios, proper scoring rules for validation, and probabilistic calibration. These methods have since been progressively adopted in other areas, including forensic biometrics, forensic chemistry, and forensic DNA profiling, and now extend to an ever-growing range of forensic disciplines.

His talk takes place on Monday, September 14, 2026 at 13:00 in room G202.
The talk will be streamed live at https://www.youtube.com/live/5mLAG4-MkvA.

Giulia D’Angelo is an Assistant Professor at the Czech Technical University in Prague, where she develops neuromorphic algorithms for active vision. She earned a BSc in Biomedical Engineering from the University of Genoa and an MSc (with honours) in Neuroengineering. During her Master’s at King’s College London, she developed a neuromorphic system for the egocentric representation of peripersonal visual space. She completed her PhD in neuromorphic algorithms at the University of Manchester, where she received the President’s Doctoral Scholar Award, in collaboration with the Event-Driven Perception for Robotics Laboratory at the Italian Institute of Technology, proposing a biologically plausible model for event-driven, saliency-based visual attention. Following her PhD, she was awarded a Marie Skłodowska-Curie Postdoctoral Fellowship at the Czech Technical University in Prague, during which she explored sensorimotor contingency theories in neuromorphic active vision. After completing the fellowship, she joined the Czech Technical University in Prague as an Assistant Professor. Her current research bridges bio-inspired software and hardware to enable robust, efficient perception and control for low-power, low-latency autonomous systems.

What’s catching your eye? – Event-driven sensing and neuromorphic computing for active vision

Vision is an exploratory behaviour that emerges from the dynamic relationship between actions and sensory feedback. For any agent, whether biological or robotic, processing visual input efficiently is fundamental to understanding and interacting with the environment. The central challenge lies in continuously recalibrating perception through sensorimotor contingencies, where what an agent sees is shaped by how it moves. Embodiment is central to this vision: perception and action are inseparable, and intelligence emerges from their continuous interaction with the physical world, shaped by the very structure of our sensors. Selective visual attention is one of the many mechanisms by which the visual cortex meets this challenge, organizing and interpreting complex visual scenes in real time.

To address these challenges, I develop brain-inspired algorithms that harness the computational principles of biological neurons and spiking neural networks, optimized for neuromorphic hardware. These algorithms enable real-time robotic perception with microsecond latency and milliwatt power consumption, bringing the efficiency of biological vision systems within reach of autonomous systems at the edge.

Her talk takes place on Thursday, March 26, 2026 at 14:00 in room A113. The talk will be streamed live at https://youtube.com/live/NuGanFmutaQ.

Daniel Robert is professor of bionanoscience at the School of Biological Sciences, University of Bristol, UK. His research generally pertains to the biophysical mechanisms used by organisms to sense and acquire information from their environment. After studies in Switzerland (Neuchâtel, MSc and Basel, PhD), he enjoyed several postdoctoral research positions in Denmark, Ivory Coast and Cornell University USA, a Schering fellowship at the Institute for Advanced Study in Berlin, and a research professorship in Zürich (CH). This is at Cornell that he discovered the third principle of directional hearing by studying the auditory nanomechanics of small flies that parasitize singing crickets. This research enabled the development of bio-inspired microscale subwavelength directional microphones. Looking at mosquitoes, Robert and his team discovered active auditory mechanics in invertebrates, a process enhancing sensitivity and tuning, emulating that of humans and other mammalian species. In Bristol, Robert’s attention extended to other small animals and their miniature sensors, revealing that bees and flowers interact using static electricity, exploring their capacity to detect weak floral electric fields. Since then, Robert and his team showed that other arthropod species, such as spiders, ticks, caterpillars and treehoppers are sensitive to and use electrostatic charge and associated electric fields in various sensory ecological contexts. Collectively, Robert’s recent work reveals the existence of an electrostatic informational ecology, and the associated detection of omnipresent electrostatic fields – aerial electroreception – a sensory modality alien to humans.

Electric ecology and electroreception in arthropods

Working together to exchange nutrition for pollination services, bees and flowers interact relying on vision, olfaction, touch and humidity sensing. We have discovered that bees can also detect and learn about the weak electric field that arises as they approach a flower. This electric field is generated because flying bees are usually electrically positively charged whilst flowers tend to be negatively charged. A third component that contributes to this electric interaction is the atmospheric potential gradient (APG) that is a consequence of the ionization of the atmosphere and the global electric circuit. I will present our current understanding of this triadic interaction (Bee-flower-APG), but also explore the role that triboelectrification and Coulomb force may play in the lives of other terrestrial arthropods and plants. As electric fields are omnipresent in the environment, it is tantalizing to suggest that their presence, detection and informational value are as ubiquitous as those of light, smell and sound. This work opens up the enticing possibility that many arthropod species, in fact the majority animal species, are capable of aerial electroreception, a sensory modality previously unknown.

His talk takes place on Thursday, February 26, 2026 at 14:00 in room A113. The talk will be streamed live at https://www.youtube.com/live/3jw3A5ZeIgE.

Jan G. Švec is a professor of biophysics at Palacký University Olomouc, Czech Republic, and an associate research scientist at the Voice and Hearing Centre Prague, dedicated to the care of patients with voice and hearing disorders. He holds an MSc degree in Fine Mechanics and Optics and a PhD in Biophysics from Palacký University Olomouc, as well as a PhD in Medical Sciences from the University of Groningen, the Netherlands. He is internationally recognized as an expert in the biomechanics and acoustics of human voice production and in clinical voice measurement. He spent three years as a research scientist at the National Center for Voice and Speech in Denver, CO, USA, and more than three years at the University of Groningen, the Netherlands. He has received both national and international awards for his scientific publications. From 2004 to 2010, he served as Chair of the Voice Committee of the International Association of Logopedics and Phoniatrics. Between 2012 and 2018, he was the European representative on the American Speech-Language-Hearing Association Committee on Instrumental Voice Assessment Protocols. Among his notable achievements, he designed videokymography, a laryngoscopic method for high-speed visualization of vocal-fold vibrations that is now used by laryngologists for advanced diagnosis of voice disorders.

Physiology, Acoustics and Biomechanics of Human Voice

In this lecture, we will review the principles of voice production in the human body. The first part will focus on the Source-Filter Theory of voice production. We will show how the primary sound of the voice is generated by the modulation of airflow resulting from vocal fold vibrations. Furthermore, we will examine how this sound changes as it passes through the acoustic cavities of the vocal tract, and how these processes together shape the acoustic waveform and resulting spectrum, determining the final quality of the human voice.
The second part will address the Myoelastic-Aerodynamic Theory of voice production, which explains how and why the vocal folds oscillate. It also describes how the acoustic resonances of the vocal and subglottal tracts influence vocal fold oscillations and provides a foundation for understanding various vocal phenomena, including voice registers, voice breaks, subharmonics, and hoarseness.

His talk takes place on Thursday, November 27, 2025 at 13:00 in “little theater” R211 (next to Kachnicka student club in “Stary Pivovar”). The talk will be streamed live at https://www.youtube.com/live/VCc5Y3w3Uj4.

Lenka Zdeborová is a Professor of Physics and of Computer Science in École Polytechnique Fédérale de Lausanne where she leads the Statistical Physics of Computation Laboratory. She received a PhD in physics from University Paris-Sud and from Charles University in Prague in 2008. She spent two years in the Los Alamos National Laboratory as the Director’s Postdoctoral Fellow. Between 2010 and 2020 she was a researcher at CNRS working in the Institute of Theoretical Physics in CEA Saclay, France. In 2014, she was awarded the CNRS bronze medal, in 2016 Philippe Meyer prize in theoretical physics and an ERC Starting Grant, in 2018 the Irène Joliot-Curie prize, in 2021 the Gibbs lectureship of AMS. She is an editorial board member for Journal of Physics A, Physical Review E, Physical Review X, SIMODS, Machine Learning: Science and Technology, and Information and Inference. Lenka’s expertise is in applications of concepts from statistical physics, such as advanced mean field methods, replica method and related message-passing algorithms, to problems in machine learning, signal processing, inference and optimization. She enjoys erasing the boundaries between theoretical physics, mathematics and computer science.

Towards Understanding of Scaling, Emergence and Transformers

For over four decades, statistical physics has studied exactly solvable models of artificial neural networks. In this talk, we will explore how these models offer insights into deep learning and large language models. Specifically, we will examine a research strategy that trades distributional assumptions about data for precise control over learning behavior in high-dimensional settings. We will discuss several types of phase transitions that emerge in this limit, particularly as a function of data quantity. In particular, we will highlight how discontinuous phase transitions are linked to algorithmic hardness, impacting the behavior of gradient-based learning algorithms. Finally, we will cover recent progress in learning from sequences and advances in understanding generalization in modern architectures, including the role of dot-product attention layers in transformers.

Her talk takes place on Tuesday, May 20, 2025 at 13:00 in E112. The talk will be streamed live at https://www.youtube.com/live/FCvPhHm5uJw.

Hervé Lombaert is Associate Professor at Polytechnique Montreal; holder of the Canada Research Chair in Shape Analysis in Medical Imaging at ETS Montreal; and Associate Member of Mila. His research focuses on the statistical analysis of geometry in the context of machine learning and medical imaging. His achievements include early image segmentation methods with graph cuts, installed in hospitals around the world; surface analysis with spectral graphs and graph convolutional networks, used in various neuro institutes; and the first human atlas of the cardiac fibers, a major contribution to cardiology. Hervé has authored over 80 articles, 5 patents, and been recognized by several awards, including the Erbsmann Prize. Herve serves on the editorial boards of the journals IEEE TMI and MedIA. In the past, he has worked in multiple research centers, including Inria, Microsoft Research, Siemens Research, and McGill.

Geometric Deep Learning – Examples on Brain Surfaces

How to analyze the shapes of complex organs, such as the highly folded surface of the brain? This talk will show how spectral shape analysis can benefit general learning problems where data fundamentally lives on surfaces. We exploit spectral coordinates derived from the Laplacian eigenfunctions of shapes. Spectral coordinates have the advantage over Euclidean coordinates, to be geometry aware, invariant to isometric deformations, and to parameterize surfaces explicitly. This change of paradigm, from Euclidean to spectral representations, enables a classifier to be applied *directly* on surface data, via spectral coordinates. Brain matching and learning of surface data will be shown as examples. The talk will focus, first, on the spectral representations of shapes, with an example on brain surface matching; second, on the basics of geometric deep learning; and finally, on the learning of surface data, with an example on automatic brain surface parcellation.

His talk takes place on Thursday, April 17, 2025 at 14:00 in E105. The talk will be streamed live at https://www.youtube.com/live/0LOLhW3TjFA.

Gijs Luijten holds a Master’s degree in Technical Medicine, specializing in Medical Imaging and Intervention, from the Technical University of Twente. He focused on Augmented Reality (AR) applications for oral-maxillofacial (OMF) and Free Flap Surgery. At the Institute for Artificial Intelligence in Medicine (IKIM), Gijs conducts research with the University Hospital Essen (UKE). The research aims to improve (surgical) diagnosis and intervention using state-of-the-art 3D technologies, particularly Virtual and Augmented Reality (VR/AR). As a visiting scientist, Gijs collaborated closely with the Technical University of Graz (Institute for Computer Graphics and Vision) and the Medical University of Graz. This collaboration aimed to investigate the effectiveness and usability of AR tools in real clinical settings and to explore interesting combinations of machine learning (ML) and AR. Recently, Gijs has explored diminishing reality in synthetic data of surgeries and created an extensive database and API for 3D medical shapes for machine learning, eye tracking to improve diagnosis, and more. Currently, Gijs is co-managing the XR-Lab at IKIM while working on a combination of ultrasound, machine learning, and augmented reality. A strong desire for continuous learning and improvement in related fields, including machine learning, workflow planning, modeling, and programming is what drives Gijs. A strong desire for continuous learning and improvement in related fields, including machine learning, workflow planning, modeling, and programming is what drives Gijs. Gijs’ work aims to empower researchers, improve patient care, and inspire clinicians, patients, and companies to push the boundaries of current possibilities.

XR Projects in Medicine at the smart-XR Lab of the AI-Guided Therapies Group

The smart XR Lab of the Artificial Intelligence Guided Therapies (AIT) group within the Institute of Institute of Artificial Intelligence in Medicine (IKIM) is located at Essen University Hospital (AöR). Our team develops applications to support researchers, patients, and clinicians.
After an overview of the hospital, institute, and XR Lab, we will present some past and ongoing projects. For education, we developed MultiAR—a multi-user, cross-device platform for collaborative anatomy education—and recently received a grant to further develop virtual reality for educational purposes. For diagnostics, we are measuring eye tracking during the HINTS exam in clinical settings. For patients, we have a project to help them relax during chemotherapy. For clinicians and medical students, we stream ultrasound images to multiple headsets and incorporate automated length and width measurements. In surgery, we are working on several markerless registration projects for CT-to-patient superimposition using both standard and custom algorithms. With the recently acquired Apple Vision Pro and Siemens Cinematic Reality application, we are investigating its added value for surgical planning. To support researchers, we created a 3D surgical instrument collection used to generate synthetic scenes for object detection, segmentation, and diminished reality. We have also developed several facial and skull datasets based on CT scans—datasets that support the training of algorithms for patient-specific implants. All these datasets, along with those from our collaboration partners, have been integrated into MedShapeNet, a database available via API. We hope MedShapeNet will impact medical computer vision research as ShapeNet did for general computer vision. We look forward to sharing our projects for researchers, patients, and clinicians and to collaborating on translating our research into meaningful applications.

His talk takes place on Thursday, April 3, 2025 at 14:00 in E105. The talk will be streamed live at https://www.youtube.com/live/e0_bIDkVr8E.

Dr. Julia Berezutskaya is a researcher at University Medical Center Utrecht (the Netherlands) specializing in neurotechnology, brain-computer interfaces, and artificial intelligence. With expertise in neuroscience, AI, and linguistics, her work focuses on decoding brain activity to enable communication for individuals with severe paralysis. A recipient of national and international research grants, Julia is dedicated to translating her research into medical technology that could reduce healthcare costs and significantly enhance quality of life for people with paralysis.

Restoring Communication with Brain Implants

Brain-computer interfaces (BCIs) hold promise for restoring communication in people with severe paralysis. BCIs bypass damaged neural pathways, allowing individuals who can’t move or speak to express themselves directly through brain activity. In our lab we work with brain implants—devices placed under the skull to record directly from the brain tissue. Using advanced algorithms, we analyze these signals in real-time, interpreting them to generate words or sentences on a computer screen.

In this talk, I’ll explore the process of decoding brain signals, from the role of intracranial implants to the machine learning techniques we use to translate neural activity into communication. I’ll highlight real-world applications, showing how BCIs are enabling people with paralysis to regain their voices and reestablish connections with loved ones.

Her talk takes place on Thursday, December 5, 2024 at 14:00 in E112. The talk will be streamed live at https://www.youtube.com/live/XvIihi5MeCI.

Shuai Wang obtained a Ph.D. degree at Shanghai Jiao Tong University in 2020.09, under the supervision of Kai Yu and Yanmin Qian. During his Ph.D., his research interests included deep learning-based approaches for speaker recognition, speaker diarization, and voice activity detection. After graduation, he joined Tencent Games as a senior researcher, where he (informally) led a speech group and extended his research interest to speech synthesis, voice conversion, music generation, and audio retrieval. Currently, he is with the SpeechLab at Shenzhen Research Institute of Big Data, Chinese University of Hong Kong (Shenzhen), led by Haizhou Li.

Speaker Representation Learning: Theories, Applications and Practice

Speaker individuality information is one of the most critical elements of speech signals. By thoroughly and accurately modeling this information, it can be applied in various intelligent speech applications, such as speaker recognition, speaker diarization, speech synthesis, and target speaker extraction. In this talk, I would like to approach the speaker characterization problem from a broader perspective, extending beyond just speaker recognition. First, I will present the developmental history and paradigm shifts in speaker modeling within the framework of deep representation learning. Next, I will discuss recent advances in pre-trained model-based methods and self-supervised training techniques. I will also cover topics such as robustness, efficiency, and interpretability, as well as the various applications of speaker modeling technologies. Finally, I will introduce two open-source toolkits I developed: wespeaker and wesep. Wespeaker is currently one of the most popular toolkits for speaker embedding learning, while wesep extends its capabilities to target speaker extraction, seamlessly integrating with wespeaker. You can find related works and recommended references in my overview paper titled “Overview of Speaker Modeling and Its Applications: >From the Lens of Deep Speaker Representation Learning”.

His talk takes place on Tuesday, September 10, 2024 at 13:00 in A112. The talk will be streamed live at https://youtube.com/live/FMY5_smgrYY.

Sriram Ganapathy is an Associate Professor at the Electrical Engineering, Indian Institute of Science, Bangalore, where he heads the activities of the Learning and Extraction of Acoustic Patterns (LEAP) lab. He is also a visiting research scientist at Google Research India, Bangalore. His research interests include signal processing, machine learning methodologies for speech and speaker recognition and auditory neuroscience. Prior to joining the Indian Institute of Science, he was a research staff member at the IBM Watson Research Center, Yorktown Heights. He received his Doctor of Philosophy from the Center for Language and Speech Processing, Johns Hopkins University. He obtained his Bachelor of Technology from College of Engineering, Trivandrum, India and Master of Engineering from the Indian Institute of Science, Bangalore. He has also worked as a Research Assistant in Idiap Research Institute, Switzerland. Over the past 15 years, he has published more than 120 peer-reviewed journal/conference publications in the areas of deep learning, and speech/audio processing. Dr. Ganapathy currently serves as the IEEE Sigport Chief Editor, member of the IEEE Education Board, and functions as subject editor for Elsevier Speech Communication Journal. He is also a recipient of several awards including Department of Science and Technology (DST) Early Career Award in India, Department of Atomic Energy (DAE), India Young Scientist Award and Verisk AI Faculty Award. He is a senior member of the IEEE Signal Processing Society and a member of the International Speech Communication Association (ISCA).

Factorized self-supervision models for speech representation learning

In recent years, self-supervised learning (SSL) of speech has enabled substantial advances in downstream applications by generating succinct representations of the speech signal. The paradigm in most of these works involve the frame-level (20-30ms) contrastive or predictive modeling of speech representations. However, speech signal entails information sources at multiple levels – semantic information encoded at frame-level, non-semantic information at utterance-level and channel/ambient information encoded at the recording session level. In this talk, I will describe efforts undertaken by our group on learning representations at multiple scales in a factorized manner.

In the first part, I will elaborate an approach to self-supervised representation learning from raw audio using a hidden unit clustering (HUC) framework. The input “time-frequency” representations from the convolutional neural network (CNN) module are processed with long short term memory (LSTM) layers, which are smaller in computational requirements compared to other models. We explore techniques that improve the speaker invariance of the learned representations and illustrate the effectiveness of the proposed approach on two settings, i) completely unsupervised speech applications on the sub-tasks described as part of the ZeroSpeech 2021 challenge and ii) semi-supervised automatic speech recognition (ASR) applications on the TIMIT dataset and on the GramVaani challenge Hindi dataset. In these experiments, we achieve state-of-art results for various Zero-speech tasks (as of 2023). In the second part of the talk, I will discuss our recent proposal on a framework to Learning Disentangled (Learn2Diss) representations of speech, which consists of frame-level and an utterance-level encoder modules. The two encoders are initially learned independently, where the frame-level model is inspired by existing self supervision techniques, thereby learning pseudo-phonemic representations, while the utterance-level encoder is inspired by contrastive learning of pooled embeddings, thereby learning pseudo-speaker representations. The joint learning of these two modules consists of disentangling the two encoders using a mutual information based criterion. With several downstream evaluation experiments, we show that the proposed Learn2Diss framework achieves state-of-the-art results on a variety of tasks, including those in SUPERB challenge. Finally, I will highlight a related effort towards zero-shot emotion conversion and conclude the talk with a discussion of future prospects for these work streams.

His talk takes place on Wednesday, June 26, 2024 at 13:00 in E112. The talk will be streamed live at https://youtube.com/live/2IcAJmFH4Ys.

Preslav Nakov is Professor at Mohamed bin Zayed University of Artificial Intelligence. Previously, he was Principal Scientist at the Qatar Computing Research Institute, HBKU, where he led the Tanbih mega-project, developed in collaboration with MIT, which aims to limit the impact of “fake news”, propaganda and media bias by making users aware of what they are reading, thus promoting media literacy and critical thinking. He received his PhD degree in Computer Science from the University of California at Berkeley, supported by a Fulbright grant. He is Chair-Elect of the European Chapter of the Association for Computational Linguistics (EACL), Secretary of ACL SIGSLAV, and Secretary of the Truth and Trust Online board of trustees. Formerly, he was PC chair of ACL 2022, and President of ACL SIGLEX. He is also member of the editorial board of several journals including Computational Linguistics, TACL, ACM TOIS, IEEE TASL, IEEE TAC, CS&L, NLE, AI Communications, and Frontiers in AI. He authored a Morgan & Claypool book on Semantic Relations between Nominals, two books on computer algorithms, and 250+ research papers. He received a Best Paper Award at ACM WebSci’2022, a Best Long Paper Award at CIKM’2020, a Best Demo Paper Award (Honorable Mention) at ACL’2020, a Best Task Paper Award (Honorable Mention) at SemEval’2020, a Best Poster Award at SocInfo’2019, and the Young Researcher Award at RANLP’2011. He was also the first to receive the Bulgarian President’s John Atanasoff award, named after the inventor of the first automatic electronic digital computer. His research was featured by over 100 news outlets, including Forbes, Boston Globe, Aljazeera, DefenseOne, Business Insider, MIT Technology Review, Science Daily, Popular Science, Fast Company, The Register, WIRED, and Engadget, among others.

Factuality Challenges in the Era of Large Language Models

We will discuss the risks, the challenges, and the opportunities that Large Language Models (LLMs) bring regarding factuality. We will then delve into our recent work on using LLMs to assist fact-checking (e.g., claim normalization, stance detection, question-guided fact-checking, program-guided reasoning, and synthetic data generation for fake news and propaganda identification), on checking and correcting the output of LLMs, on detecting machine-generated text (blackbox and whitebox), and on fighting the ongoing misinformation pollution with LLMs. Finally, we will discuss work on safeguarding LLMs, and the safety mechanisms we incorporated in Jais-chat, the world’s best open Arabic-centric foundation and instruction-tuned LLM.

His talk takes place on Thursday, February 29, 2024 at 16:00 in A112. The talk will be streamed live at https://www.youtube.com/live/niT_shR8jbU.

Michael Buchholz earned his diploma degree in electrical engineering and information technology as well as his Ph.D. degree from the Faculty of Electrical Engineering and Information Technology at today’s Karlsruhe Institute of Technology. Since 2009, he is a research group leader and lecturer at the Institute of Measurement, Control, and Microtechnology, Ulm University, Germany, where he finished his “Habilitation” (post-doctoral lecturing qualification) in the field of automation engineering based on his research on cooperative, connected automated mobility in 2022. His further research interests include electric mobility, the modelling and control of mechatronic systems, and system identification.

Connected, Cooperative Automated Mobility Supported by Intelligent Infrastructure

Fully automated driving of vehicles in mixed traffic is a complex task with dynamically changing conditions, e.g., due to weather and other road users. Urban areas are especially challenging, showing a high traffic density and limited field of view (FOV) of the on-board sensors of an automated vehicle (AV). The latter is caused by occlusions, e.g., due to buildings, vegetation, or other traffic participants. To overcome the these FOV limitations, in the first part, this talk presents a supporting solution by intelligent infrastructure connected with the AVs via mobile communication realized as a test site in real traffic in Ulm, Germany. In the second part, a solution is proposed to enhance this system by an additional cooperative planner, which proposes manoeuvres to cooperative connected road users that ensure safety for vulnerable road users and can enhance traffic efficiency. Results from a proof of concept in mixed traffic at the test site in Ulm will be shown to demonstrate the possibilities of this approach.

His talk takes place on Friday, January 19, 2024 at 9:30 in G108.

Ondřej Klejch is a senior researcher in the Centre for Speech Technology Research in the School of Informatics at the University of Edinburgh. He obtained his Ph.D. from the University of Edinburgh in 2020 and received his M.Sc. and B.Sc. from Charles University in Prague. He has been working on building automatic speech recognition systems with limited training data and supervision within several large projects funded by EPSRC, H2020, and IARPA. His recent work investigated semi-supervised and unsupervised training methods for automatic speech recognition in low-resource languages.

Deciphering Speech: a Zero-Resource Approach to Cross-Lingual Transfer in ASR

Automatic speech recognition technology has achieved outstanding performance in recent years. This progress has been possible thanks to the advancements in deep learning and the availability of large training datasets. The production models are typically trained on thousands of hours of manually transcribed speech recordings to achieve the best possible accuracy. Unfortunately, due to the expensive and time-consuming manual annotation process, automatic speech recognition is available only for a fraction of all languages and their speakers.

In this talk, I will describe methods we have successfully used to improve the language coverage of automatic speech recognition. I will describe semi-supervised training approaches for building systems with only a few hours of manually transcribed training data and large amounts of crawled audio and text. Subsequently, I will discuss training dynamics of semi-supervised training approaches and why a good language model is necessary for their success. I will then present a novel decipherment approach for training an automatic speech recognition system for a new language without any manually transcribed data. This method can “decipher” speech in a new language using as little as 20 minutes of audio and paves the way for providing automatic speech recognition in many more languages in the future. Finally, I will talk about open challenges when training and evaluating automatic-speech-recognition models for low-resource languages.

His talk takes place on Thursday, December 14, 2023 at 14:00 in A113.

His talk takes place Wednesday, November 22, 2023 at 14:00 in E105.

Hynek Hermansky has been active in speech research for over 40 years, is a Life Fellow of IEEE, Fellow of the International Speech Communication Association, authored or co-authored more than 350 papers with over 20,000 citations, holds more than 20 patents and received IEEE James L. Flanagan Speech and Audio Processing Award, and ISCA Medal for Scientific Achievements. He started his career in 1972 at Brno University of Technology, obtained his D.Eng.. degree from the University of Tokyo, worked for Panasonic Technologies, U S WEST Advanced Technologies, the Oregon Graduate Institute, IDIAP Martigny, the Johns Hopkins University, and Google Deep Mind. Currently, he is a Researcher at Speech@FIT BUT, and an Emeritus Professor at the Johns Hopkins University.

Learning: It’s not just for machines anymore

Machine recognition of speech requires training on a large amount of speech training data. Subsequently, research in machine recognition of speech consists mainly of getting hands-on large amounts of speech training data combined, often by a try-and-error, with the appropriate combination of processing modules. Advances are mostly being evaluated by error rates observed in recognition of test data. Such a process may be missing one of the prime goals of scientific endeavor, which is to obtain new knowledge, applicable to other applications. We argue that speech data can be used to obtain relevant hearing knowledge, which is used in decoding messages in speech, and report on some experiments, which support this notion.

His talk takes place Wednesday, November 22, 2023 at 14:00 in E105.

Video recording of the talk is publicly available.

Sébastien Lefèvre is currently a Full Professor in Computer Science at the University of South Brittany (Vannes Institute of Technology) since September 2010. He founded the OBELIX group from IRISA laboratory, and led the group from 2013 to 2021 (Prof. Nicolas Courty is leading the group since March 2021). He is also coordinating the GeoData Science track within the Erasmus Mundus Copernicus Master in Digital Earth. His main research topics are image analysis/processing, pattern recognition and indexing, machine learning, deep learning and data mining with applications in remote sensing for Earth observation.

Deep Learning in Computer Vision: Are Numerous Labels the Holy Grail?

Deep Learning has been successful in a wide range of computer vision tasks, at the cost of high computational resources and large labeled datasets required to train the models. The latter is a strong bottleneck in numerous applications where collecting annotated data is challenging.
In this talk, I will present some of our works attempting to alleviate our need for large annotated datasets. More precisely, the methods we develop rely on semi-supervised, weakly-supervised, unsupervised settings, domain adaptation, data simulation, active learning, among other frameworks. Various applications in Earth Observation will be provided to illustrate the relevance of these solutions for a wide range of problems such as semantic segmentation, image classification, or object detection.

His talk takes place in Thursday, June 15, 2023 at 14:00 in G108.

Jiri Mekyska is head of the BDALab (Brain Diseases Analysis Laboratory) at the Brno University of Technology, where he leads a multidisciplinary team of researchers (signal processing engineers, data scientists, neuroscientists, psychologists) with a special focus on the development of new digital biomarkers facilitating understanding, diagnosis and monitoring of neurodegenerative (e.g. Parkinson’s disease) and neurodevelopmental (e.g. dysgraphia) disorders.

Acoustic analysis of speech and voice disorders in patients with Parkinson’s disease

Parkinson’s disease (PD) is the second most frequent neurodegenerative disease, which is associated with several motor and non-motor features. Up to 90 % of PD patients develop a motor speech disorder called hypokinetic dysarthria (HD). HD manifests in the field of phonation (e.g. increased instability of articulatory organs, microperturbation in pitch and amplitude), articulation (e.g. rigidity of tongue and jaw, slow alternating motion rate), prosody (e.g. monopitch, monoloudness), and respiration (e.g. airflow insufficiency). Acoustic analysis of these specific speech/voice disorders enables neurologists and speech-language therapists to effectively monitor the progress of PD as well as to diagnose it. In the frame of this talk, we will present a concept of acoustic HD analysis. Consequently, we will present some recent findings focused on the prediction of motor (freezing of gait) and non-motor (cognitive) deficits based on the acoustic analysis, we will discuss an application of acoustic HD analysis in treatment effect monitoring (based on high-frequency repetitive transcranial magnetic stimulation), and in PD diagnosis. Finally, we will present some future directions in terms of integration into Health 4.0 systems.

His talk takes place in Tuesday, May 16, 2023 at 15:00 in E105.

András Lőrincz, a professor and senior researcher, has been teaching at the Faculty of Informatics at Eötvös University, Budapest since 1998. His research focuses on human-machine interaction and their applications in neurobiological and cognitive modeling, as well as medicine. He has founded the Neural Information Processing Group of Eötvös University and he directs a multidisciplinary team of mathematicians, programmers, computer scientists and physicists. He has acted as the PI of several successful international projects in collaboration with Panasonic, Honda Future Technology Research and the Information Directorate of the US Air Force, Robert Bosch, Ltd. Hungary, among others. He took part in several EU Framework Program projects.

He is a habilitated professor at the University of Szeged (1998) on laser physics and habilitated in the field of Informatics at the Eötvös Loránd University in 2008. He conducted research and taught quantum control, photoacoustics and artificial intelligence at the Hungarian Academy of Sciences, University of Chicago, Brown University, Princeton University, the Illinois Institute of Technology, University of Szeged, and Eötvös Loránd University. He authored about 300 peer reviewed scientific publications.

He has become an elected Fellow of the European Coordinating Committee for Artificial Intelligence (EurAI) for his pioneering work in the field of artificial intelligence in 2006. He has received the Innovative Researcher Prize of the University in 2009 and in 2019.

Partners: Barcelona University (on personality estimation and human-human interaction), Technical University of Delft (on human-human interaction), Rush Medical School, Chicago, on autism diagnosis and PTSD therapy.

Towards human-machine and human-robot interactions “with a little help from my friends”

Our work in the Neural Information Processing Group focuses on human-machine interactions. The first part of the talk will be an introduction to the technologies that we can or should use for effective iterations, such as the detection of environmental context, ongoing activity, including body movement, manipulation, and hidden parameters, i.e. intention, mood and personality state, as well as communication signals: body, head, hand, hand, face and gaze gestures, plus the body parameters that can be measured optically or by intelligent means, i.e., the temperature, blood pressure and stress levels, among others.

In the second part of the talk, I will review (a) what body and environment estimation methods we have, (b) what we can say about human-human interactions, which will also give insights into the requirements of human-machine and human-robot interactions, (c) what applications we have or can target in the areas of autism, “continuous healthcare” and “home and public safety”. (d) I will also list what technologies are missing and what we are looking for partners in.

His talk takes place on Tuesday, November 1, 2022 at 13:00 in “little theater” R211 (next to Kachnicka student club in “Stary Pivovar”).

Heikki Kälviäinen has been a Professor of Computer Science and Engineering since 1999. He is the head of the Computer Vision and Pattern Recognition Laboratory (CVPRL) at the Department of Computational Engineering of Lappeenranta-Lahti University of Technology LUT, Finland. Prof. Kälviäinen’s research interests include computer vision, machine vision, pattern recognition, machine learning, and digital image processing and analysis. Besides LUT, Prof. Kälviäinen has worked as a Visiting Professor at the Faculty of Information Technology of Brno University of Technology, Czech Republic, the Center for Machine Perception (CMP) of Czech Technical University, and the Centre for Vision, Speech, and Signal Processing (CVSSP) of University of Surrey, UK, and as a Professor of Computing at Monash University Malaysia.

Computer Vision Applications

The presentation considers computer vision, especially a point of view of applications. Digital image processing and analysis with machine learning methods enable efficient solutions for various areas of useful data-centric engineering applications. Challenges with image acquisition, data annotation with expert knowledge, and clustering and classification, including deep learning method training are discussed. Different applications are given as examples based on the fresh novel data available: planktons in the Baltic Sea, Saimaa ringed seals in Lake Saimaa, and logs in the sawmill industry. In the first application the motivation is that distributions of plankton types give much information about the condition of the sea water system, e.g., about the climate change. An imaging flow cytometer can produce a lot of plankton images which should be classified into different plankton types. Manual classification of these images is very laborious, and thus, a CNN-based method has been developed to automatically recognize the plankton types in the Baltic Sea. In the second application the Saimaa ringed seals are automatically identified individually using camera trap images for assisting this very small population to survive in nature. CNN-based re-identification methods are based on pelage patterns of the seals. The third application is related to the sawmill industry. The digitalization of the sawmill industry is important for optimizing material flows and the quality. The research is focused on seeing inside the log to be able to predict which kinds of sawn boards are produced after cutting the log.

His talk takes place on Wednesday, May 11, 2022 at 13:00 in room A112.

Augustin Žídek works as a Research Engineer at DeepMind and has been a member of the protein folding team since 2017. He studied Computer Science at the University of Cambridge. He enjoys working at the boundary of research and engineering, hiking, playing musical instruments and fixing things.

Protein Structure Prediction with AlphaFold

In this talk, we will discuss what proteins are, what is the protein folding problem and why it is an important scientific challenge. We will then talk about AphaFold, a machine learning model developed by DeepMind that is able to predict protein 3D structure with high accuracy, its architecture and applications.

His talk takes place on Tuesday, March 1, 2022 at 13:00 in room A112. The talk will be streamed live at https://youtu.be/udyjZXtUuDw.