Find Academic Supervisors

Dr. Amélie M. Achim is an Associate Professor in the Department of Psychiatry and Neuroscience at Université Laval's School of Medicine, and a researcher at the CERVO Brain Research Centre's Clinical and Cognitive Neuroscience axis. Her work focuses on understanding social cognition deficits in schizophrenia and social anxiety disorders through behavioral testing and functional neuroimaging. Current appointments: Associate Professor (2025), Researcher (2025) Key methodologies: fMRI, behavioral testing, cognitive remediation Dr. Achim's research explores the neural mechanisms underlying social cognition, theory of mind, and communication deficits in schizophrenia spectrum disorders. She develops interactive behavioral assessments and investigates non-pharmacological interventions to improve cognitive and social functioning. Recent publications (2023-2025) demonstrate interdisciplinary focus combining neuroscience, psychiatry, and computational linguistics, with recurring themes in schizophrenia, social cognition, neuroimaging, and cognitive remediation. Her team applies sparse-sampling fMRI to study real-time verbal communication and develops ecological measures for social cognition assessment. Scientific award: FRQSC grant renewal for CAP-Rétablissement group (2024) Collaborative projects: Cross-linguistic NLP markers for psychosis, international social cognition initiatives Dr. Achim's lab (CERVO Brain Research Centre) investigates theory of mind impairments in schizophrenia and their impact on social interactions, with ongoing work on computer-based cognitive therapies and their long-term effectiveness.

• Social cognition
• Schizophrenia
• Neuroimaging
• +5 more

Durga Prasad Bavirisetti is an Associate Professor (Universitetslektor) at the University of Gävle, Sweden, specializing in computer vision and machine learning. His research spans geospatial information science, image fusion, and autonomous driving systems, with a strong focus on applying deep learning to real-world problems in energy, healthcare, and transportation. His educational background includes: PhD in Signal and Image Processing from VIT University, India (2016) Postdoctoral research at Shanghai Jiao Tong University Bavirisetti's research interests center on advancing computer vision through deep learning, particularly in multi-sensor image fusion (infrared-visible, MRI-CT), autonomous vehicle perception in challenging conditions (e.g., Nordic winters), and applications in renewable energy forecasting and medical diagnostics. His work bridges theoretical innovation with practical deployment, as evidenced by industry collaborations with Alibaba and SINTEF. Analysis of his recent publications reveals a strong trend toward multi-modal deep learning architectures, with increasing focus on autonomous systems and healthcare applications. His 2023-2025 output shows expansion into dysarthria detection, cyberbullying monitoring, and photovoltaic forecasting, demonstrating interdisciplinary reach while maintaining core expertise in image processing. No scientific awards were mentioned in the provided sources. While specific grant details are not provided, Bavirisetti's research demonstrates significant industry and international collaboration, including positions at Alibaba Group Innovation Center, SINTEF Industries, and visiting roles at UBC Okanagan and the University of Warsaw. His advising activities are not explicitly detailed, but his extensive publication record suggests active mentorship of students and junior researchers. He is part of collaborative research teams including the mobility department at SINTEF Industries (focusing on machine vision for autonomous driving) and works with researchers like Gabriel Kiss at NTNU on projects involving surgical environments and autonomous vehicle perception. His work often integrates expertise from computer science, electrical engineering, and medical fields.

• Machine Learning
• Deep Learning
• Computer Vision
• +3 more

Prof. Jonathan Harrington is a Professor of Phonetics and Digital Speech Processing and Director of the Institute of Phonetics and Speech Processing (IPS) at the University of Munich. He joined LMU in 2006 and specializes in experimental phonetics, laboratory phonology, and sound change. His work integrates real-time MRI studies, computational modeling, and large-scale speech databases. Current projects include SoundAct (ERC Advanced Grant, 2023–2028) exploring the actuation of sound change and InterAccent (ERC Advanced Grant, 2017–2023) investigating accent evolution in interaction. Notable past projects include studies on nasal coarticulation, speech impairment diagnostics via web-based tools, and the phonetics of Albanian, Mandarin, and German dialects. Research interests span articulatory phonetics, the phonetic basis of sound change, and computational models of linguistic dynamics. He develops tools like the EMU-SDMS R package for speech database management and soundChangeR for agent-based modeling. His work bridges laboratory and field studies, addressing questions of speech production, perception, and historical change. Recent studies examine velum movement in Mandarin, vowel nasalization in German, and compensatory lengthening in Albanian dialects. Grants include multiple ERC awards and German Research Council funding. His publications (over 100 articles) focus on articulatory MRI analysis, sociophonetic methods, and the interplay between phonetic detail and linguistic structure. He collaborates internationally, mentoring researchers in speech technology and dialectology.

• Experimental Phonetics
• Laboratory Phonology
• Speech Database Development
• +4 more

Prof. James Kirby is a Professor of Spoken Language Processing at Ludwig-Maximilians-Universität München, affiliated with the Lehrstuhl für Verarbeitung gesprochener Sprache. His research focuses on phonetics, linguistics, and tonal languages, particularly investigating speech production, prosody, sound change, and cross-linguistic phonetic patterns. He has contributed significantly to understanding laryngeal contrasts, tonogenesis, and the interplay between production and perception in languages like Khmu', Madurese, and Cantonese. Key research areas include the acoustic correlates of voicing, tonal text-setting in popular music, and the role of F0 and phonation cues in language perception. His work spans experimental phonetics, computational modeling, and corpus-based analysis, often employing real-time MRI and large-scale acoustic datasets. Kirby has collaborated on open data policies in phonetics and led studies on prosodic systems in Mainland Southeast Asia. His publications frequently address language universals, sound change dynamics, and the methodology of phonological argumentation. Though no specific awards are listed, his extensive contributions to phonetics and linguistics underscore his scholarly impact. He is associated with the Bavarian Archive for Speech Signals and has developed tools like the WebMAUS aligner for phonetic analysis.

• Phonetics
• Linguistics
• Tonal Languages
• +3 more

Stephen Tobin is a Research Fellow in the Department of Linguistics at the University of Michigan, joining in August 2018. He holds a BA in Modern Languages and Linguistics from the University of Cambridge, an MA from the University of Southern California, and a PhD from the University of Connecticut (2015). Prior to UMich, he was a Research Fellow at Universität Potsdam (Germany) from 2014 to 2018. His research focuses on phonetics, including speech production, perception, and their interrelation, particularly through studies of phonetic accommodation. He employs advanced methodologies such as Electromagnetic Articulography (EMA), real-time MRI, eye-tracking, and data analysis using MATLAB and R. Stephen contributes to the Linguistics department’s research initiatives and is affiliated with 440 Lorch Hall, Ann Arbor.

• Phonetics
• Speech Production
• Speech Perception
• +3 more

Ekaterina Torubarova is a doctoral student at KTH Royal Institute of Technology's Division of Speech, Music and Hearing. Under the supervision of André Pereira, her research focuses on conversational engagement in Human-Robot Interaction (HRI), combining neuroimaging and machine learning to study brain processes during human-robot interactions. She holds a joint master's degree in Cognitive Neuroscience from CIMeC (Trento, Italy) and SISSA (Trieste, Italy). Education: PhD Candidate in Speech, Music and Hearing (KTH Royal Institute of Technology, 2022–present) Joint Master's in Cognitive Neuroscience (CIMeC & SISSA, 2020–2022) Research Interests: Cognitive-inspired approaches to HRI, fMRI analysis of conversational dynamics, neural correlates of interaction, and multimodal datasets for understanding human-robot communication. Publications Overview: Her work explores brain activity patterns during conversation, HRI dynamics, and the application of neuroimaging techniques to study social interactions. Recent studies include the NeuroEngage dataset integrating multimodal fMRI for analyzing engagement metrics in human-robot interactions. Advising/Grants: Currently advised by Prof. André Pereira. No grant details provided in text. Labs/Teams: Active member of the Speech, Music and Hearing division at KTH, contributing to interdisciplinary research on cognitive science and robotics.

• Human-Robot Interaction (HRI)
• Cognitive Neuroscience
• Neuroimaging
• +3 more

Dr. Charlie Wiltshire is a Lecturer in Psychology at Bangor University's School of Psychology and Sports Science, where she leads the Integrative Speech Research Group . Her work combines advanced neuroimaging and brain stimulation techniques to investigate speech production systems, with particular focus on developmental stuttering and motor control mechanisms. University: Bangor University School: School of Psychology and Sports Science Academic Rank: Lecturer Research Interests center on neural control of speech, using: fMRI and multi-parameter brain imaging Transcranial magnetic/electrical stimulation Articulography with real-time MRI Current projects examine movement control in stuttering populations and bilingual speech patterns, funded by DFG, European Research Council, and Welsh Crucible. She collaborates with Swansea University, Cardiff Metropolitan University, and STAMMA charity. Scientific Recognition : American Speech-Language-Hearing Association Editor's Award (2022) The Travers Reid Award (2020) She employs co-production methods in research design and maintains an active lab website with research outputs.

• Neural control of speech production
• Developmental stuttering
• Speech motor control
• +3 more

Professor Povilas Treigys is a Senior Researcher and Group Leader at the Image and Signal Analysis Group within the Institute of Data Science and Digital Technologies at Vilnius University's Faculty of Mathematics and Informatics. With extensive experience in digital signal processing and machine learning applications, he leads research efforts in medical image analysis, speech processing, and maritime traffic modeling. Dr. Treigys earned his Doctor of Science in Computer Science Engineering in 2010 with a dissertation on "Development and application of graphical methods for analyzing ophthalmological and thermovision data." His academic journey has been marked by significant contributions to interdisciplinary research connecting computer science with medical applications. His research primarily focuses on digital signal processing across multiple domains including medical imaging (MRI, eye fundus), audio signals, and maritime traffic data. A key emphasis of his work is the development and application of deep learning methods to solve real-world problems in healthcare diagnostics, retail automation, and transportation safety. His recent work demonstrates a strong trend toward explainable AI in medical applications and sophisticated time series analysis for prediction tasks. Professor Treigys serves in numerous leadership roles including as a EuroHPC JU Board Member representing Lithuania, VU MIF representative on the Lithuanian Quantum Technology Association board, and as a delegate to multiple professional committees. He is an active reviewer for several prestigious journals including Computer Science, Nonlinear Analysis, Baltic Journal of Modern Computing, MDPI Sensors, and MDPI Electronics. His laboratory focuses on bridging theoretical machine learning advancements with practical applications, particularly in medical diagnostics where his team has made significant contributions to prostate cancer detection, arrhythmia classification, and ophthalmological image analysis. The group maintains strong international collaborations and regularly presents findings at major conferences in computer vision, medical imaging, and artificial intelligence.

• Digital Signal Processing
• Machine Learning
• Deep Learning
• +3 more

Hideaki Kikuchi is a Professor at Waseda University’s Faculty of Human Sciences, Japan, holding a Ph.D. in Information Science from the same university. He specializes in speech science, spoken dialogue systems, and human-agent interaction, with extensive work on prosody, infant-directed speech, and real-time MRI articulatory analysis. Education: Ph.D. (Information Science), Waseda University Research Interests: His research spans Speech Science , Spoken Dialogue Systems , Human-Agent Interaction , Kansei Informatics , Intelligent Informatics , and Language Acquisition . He investigates empathic dialogue generation, prosodic entrainment, infant speech development, and multimodal communication robots. Publications Trend: Recent articles focus on user empathy toward dialogue systems, linguistic alignment in chat-oriented robots, real-time MRI visualization of articulation, and developmental phonetic studies in Japanese children, indicating a strong emphasis on both technological innovation and cognitive speech science. Awards: Information Processing Society of Japan, 53rd National Convention Excellence Award (1996) Grants & Projects: JSPS KAKENHI "Real-time MRI database of articulatory movements of Japanese" (2020-2024) JSPS KAKENHI "Development of protocol of effective social work interview for older adults with dementia" (2019-2022) VR orality factors project (2017-2020) Labs & Teams: He leads the Speech & Interaction Research Group within Waseda’s Faculty of Human Sciences, collaborating with interdisciplinary members on spoken corpora, dialogue systems, and multimodal interaction experiments.

• Speech Science
• Spoken Dialogue Systems
• Human-Agent / Human-Robot Interaction
• +7 more

Dr. Krishna S. Nayak serves as Dean's Professor of Electrical and Computer Engineering at the University of Southern California's Viterbi School of Engineering. He directs the Signal and Image Processing Institute, Dynamic Imaging Science Center, and Magnetic Resonance Engineering Laboratory (MREL), leading interdisciplinary collaborations with radiologists, cardiologists, pulmonologists, and obesity researchers. His educational background includes a PhD (2001) and MS (1996) in Electrical Engineering from Stanford University, and BS degrees in Electrical Engineering, Computer Science, and Applied Mathematics from Florida State University (1995). Nayak's research pioneers MRI technology development with core expertise in pulse sequence design, real-time imaging, and quantitative reconstruction. His lab focuses on translating innovations to clinical applications for cardiovascular disease, obesity, and speech production through low-field systems, compressed sensing, and machine learning techniques. Current projects target high-performance imaging for coronary disease, cancer biomarkers, and vocal tract dynamics. His publication portfolio shows consistent advancement in MRI methodology, with recent work emphasizing low-field systems (0.55T), real-time speech imaging, and artifact correction. Key trends include clinical translation of quantitative biomarkers and hardware-software co-design for specialized applications. Jan 2022, Fellow, IEEE Apr 2020, USC Viterbi Use-Inspired Research Award May 2019, ISMRM Board of Trustees Apr 2018, Fellow, SCMR Apr 2017, Fellow, AIMBE Apr 2009, GE Healthcare Thought Leader Award His research program receives sustained funding from NIH, NSF, American Heart Association, and Coulter Foundation, supporting mentorship of graduate students and postdocs. As evidenced by his USC-Mellon Mentoring Award, he maintains strong commitment to training next-generation engineers through the MREL's collaborative environment. The Magnetic Resonance Engineering Laboratory operates as a multidisciplinary hub developing state-of-the-art imaging solutions, with active projects spanning hardware configurations, real-time cardiac imaging, and quantitative pulmonary assessment through close clinical partnerships.

• Magnetic Resonance Imaging
• MRI Pulse Sequence Design
• Image Reconstruction
• +5 more

Adam Tierney is a Professor in the Department of Psychological Sciences at Birkbeck, University of London. His research focuses on auditory neuroscience, exploring how auditory processing underpins speech, music, and rhythm perception. He investigates links between neural mechanisms of sound processing and cognitive abilities such as reading, language learning, and rhythmic skills. His work spans developmental, clinical, and cross-cultural contexts, emphasizing the interplay between perception, attention, and neural plasticity. Key research themes include: Neural entrainment to rhythmic structures Effects of musical training on auditory processing Speech-in-noise perception and its developmental basis Cross-modal perception of music and speech Second language acquisition and domain-general auditory aptitude Recent work examines how perceptual strategies dynamically adapt across contexts, leveraging large-scale datasets and global music recordings to uncover universal auditory principles. He has pioneered methods to quantify pitch discreteness in music and speech, linking acoustic properties to perceptual outcomes. His findings underscore the role of rhythmic skills in neurodevelopmental outcomes like literacy. Notable contributions include demonstrating how auditory brainstem responses predict reading readiness in children, and how musical training alters adolescent auditory maturation. Collaborative projects explore the social neuroscience of singing and its effects on group cohesion.

• Auditory Neuroscience
• Music Cognition
• Speech Perception
• +3 more

Sungbok Lee is a Research Assistant Professor in the Department of Electrical Engineering at the University of Southern California. He holds dual affiliations at the Speech Analysis and Interpretation Laboratory (SAIL) and the Phonetics and Phonology Group in the Department of Linguistics. His expertise spans Speech Production Modeling of Emotional Speech, Speech and Language Processing, and Human Behavior Analysis in Interactive Environments. Lee’s work integrates advanced signal processing techniques with clinical and developmental studies, particularly focusing on neurodevelopmental disorders and child language acquisition. Education: B.S. in Chemistry (Seoul National University, 1978) M.S. in Physics (Seoul National University, 1985) Ph.D. in Biomedical Engineering (University of Alabama at Birmingham, 1991) His research emphasizes articulatory kinematics, prosody analysis, and multimodal speech databases. Notable contributions include the USC-EMO-MRI corpus and IEMOCAP dataset. Lee’s recent work explores acoustic-prosodic features in child-psychologist interactions and the application of real-time MRI for speech production studies. His methodologies often combine machine learning with physiological measurements to decode emotional and developmental speech patterns.

• Speech Production Modeling
• Emotional Speech Analysis
• Speech and Language Processing
• +3 more

Dr. Md Khan is an Adjunct Associate Professor at The University of Western Australia's Institute of Agriculture. He holds a Ph.D. from Aligarh Muslim University, India, with postdoctoral research at the International Rice Research Institute (Philippines) and the National Institute of Plant Genome Research (India). His research focuses on environmental stress mitigation in staple crops like wheat and rice, emphasizing plant stress physiology and sustainable development goals (SDGs). He explores oxidative stress markers, plant hormones, and multi-omics strategies to enhance agronomic productivity under climate pressures. Dr. Khan advocates for education reforms aligned with SDGs, emphasizing teacher training and student mentorship. He organizes initiatives like 'Plant Drive Programs' and delivers invited talks on climate change and food security. His expertise spans crop physiology, nutrient security, and sustainable agriculture, with collaborations across global institutions. Education: Ph.D., Aligarh Muslim University; Postdoctoral Fellowships at IRRI and NIPGR. Research Interests: Environmental stress responses in crops, plant growth regulators, and SDG-aligned agricultural practices. Awards: INSA Young Associates Fellowship (2024), R. H. Dastur Gold Medal (2023), Highly Cited Researcher (2022). His recent publications address topics like fake news detection, breast cancer classification, and automated exam script checking, reflecting his interdisciplinary approach to solving global challenges through AI and plant science.

• Crop Physiology
• Environmental Stresses
• Nutrient and Food Security
• +3 more

Dr. Michel Belyk is a Senior Lecturer in Psychology at Edge Hill University, affiliated with the Psychology Health Research Institute. He holds a PhD in Psychology, Neuroscience & Behaviour from McMaster University (2015) and completed postdoctoral fellowships at the University of Maastricht, University of Toronto, and University College London. His research focuses on the neurobiology of voice production, integrating brain imaging, neurostimulation, and audio analysis to explore speech, singing, and emotional expression. Key areas include stammering neurobiology, vocal imitation, and applications of real-time MRI. As Local Network Lead for the UK Reproducibility Network, he promotes open research practices. His work bridges neuroscience with clinical advocacy, emphasizing collaborations with stammering communities. Education: PhD Psychology, Neuroscience & Behaviour, McMaster University (2015) Postdoctoral Fellowships: University of Maastricht (Netherlands), University of Toronto (Canada), University College London (UK) Research Interests: Neural control of voice production Stuttering neurobiology and community advocacy Real-time MRI for vocal tract analysis Applications of brain imaging in vocal disorders Psychology of deception detection via speech Professional Engagement: Local Network Lead, UK Reproducibility Network (UKRN) Speaker for The British Voice Association and Voice Study Centre Advocate for open research methodologies

• Speech and Language Processing
• Neuroscience of Communication
• Brain Imaging Techniques
• +5 more

Ahmet Enis Cetin is a Professor in the Department of Electrical and Computer Engineering at the University of Illinois at Chicago. His work spans computer vision, biomedical imaging, and energy-efficient signal processing for cyber-physical systems. Department of Electrical and Computer Engineering (University of Illinois at Chicago) Member, Turkish Academy of Sciences (2015–present) Fellow, IEEE Research Interests include: Computer vision for wildfire and VOC detection Biomedical image processing and microscopy analysis Energy-efficient deep learning and multiplication-free operators Speech and sound analysis for industrial and medical applications Cyber-physical systems for environmental monitoring Scientific Awards : Fellow of IEEE (2009) 2012 Best Paper Award at UNESCO-organized conference Member, Turkish Academy of Sciences (2015–present) Advising and Grants : Mentored students on wildfire detection, VOC monitoring, and biomedical imaging. Secured NSF and Intel grants for energy-efficient neural networks and cyber-physical systems.

• Computer Vision
• Artificial Intelligence
• Signal Processing
• +7 more