Supervision (As a supervisor & co-supervisor)
PhD Theses
- Eva Paraschou (2024-), Alignment for LLMs and AI in Mental Health (Official daily advisor + co-supervisor)
- Hewei Gao (2024-), Alignment for LLMs and AI in Education (Official daily advisor + co-supervisor)
- Martin Bertelsen (2024-), Intelligent Hydroacoustic Modeling of Fish Feeding (Co-supervisor; Industrial PhD)
- Aditya Parikh (2024-), Label bias and its effect on responsible AI (Co-supervisor)
- Harald Skat (2025-), Informatics catalysis (Co-supervisor)
Masters Theses
- Maria Christine Neiiendam (2025), Investigating Memorisation Risks: A Benchmarking Approach For Speech Processing Tasks
- Jakub Jedraszka (2025), Voice biomarkers for predicting cognitive impairment in hearing-and non-hearing-impaired subjects
- Ting-Hui Cheng (2025), Mitigating bias for non-native speakers in automatic speech recognition
- Mark Hageman Welin (2025), Automated Transcription Analysis: Comparing Speech-to-Text Models with Real-World Audio Data
- Anders Rolighed Larsen (2025), Synchronizing Audio and Textual Modalities: A Framework for Sentiment Detection through Temporal and Syntactic Alignment for AI Coaching
- Kirstine Cort Graae (2025), Exploration of synchrony in bio-signals
- Kathrine Sofie Rasmussen (2025), Foundational Models for predicting OCD events in children
- Ilias Tsikontouris (2025), Emotion Recognition using Machine Learning and Image resources Analysis
- Eleftherios Katiforis (2025), Logical Fallacy detection using LLMs
- Maria Katarachia (2024), On summarization for non-structured data with applications to teaching-learning and social surveys
- Kristoffer Nielsen (2024), Automated Behavioral Coding in Child and Adolescent Psychiatry using Artificial Intelligence
- Maja Jønck Hjuler (2024), Speech emotion recognition for low-resource languages
- Odelia Gefei Huang (2024), Exploring Voice Recognition With a lens on Bias and Fairness in Low-resource Settings
- Harald Vilhelm Skat-Rørdam, Simon Nørby Knudsen, Mia Hang Knudsen (2024), Harnessing Wearable Biosensors for Predicting Obsessive-Compulsive Disorder Episodes in Minors (publication)
- Asbjørn Hammershøi Petersen (2024), Speaker diarization of children and adults in LFE recordings using feature extraction and temporal segmentation
- Ambrus Török (2024), Limited Resource Chatbots – How well can they perform?
- Usama Ahmad Mir (2023), Facial recognition for kinship detection using deep neural networks
- Sebastian Nicolai Fabricius Grut (2023), Kinship detection of individuals with video data
- Zihao Fu (2023), Chinese family relationship recognition via video and audio modalities
- Laurits Fromberg (2023), Analysis of Children with Obsessive-Compulsive-Disorder using Machine Learning
- Carlos Ramos Gonzalez (2023), Biosignal synchrony analysis in collaboration activities
- Maria-Madalina Jarca & Vincent Parluhutan Ryan (2023), Intelligent computer vision systems applied in psychiatry
- Maria Garofalaki (2022), Speech and natural language processing for clinical in-the-wild data
- Angélica Stephania Zambrano Suárez (2022), Automating Crowdsourcing Experiments for Speech Quality to Provide Relevant Insights of Results and Optimize Algorithms for Human Perception (publication)
- Steinn Orri Erlendsson (2022), Deep Learning Methods in Speech Emotion Recognition for Danish language
- Nicklas Leander Lund (2021), Analysis of Obsessive Compulsive Disorder in Children using Deep Learning
- Farida Yeasmin (2020), Privacy Analysis of Voice User Interfaces (publication)
Bachelor Theses
- Jawhara Hamoua (2025), Predicting and detecting Obsessive Compulsive Disorder in Children Using a Foundation Models
- Lucia Han Lu, Ditte Bjerrum Gilsfeldt (2025), Federated learning for tackling data heterogeneity in healthcare applications
- Christian Houlberg Rand, Bertram Nicolai Hage (2025), Cross-Silo Federated Learning: Advancing Robustness and Scalability for Practical Applications
- Abrahim Deiaa El Din Abbas (2024), Implementing distributed information retrieval relevancy score service using machine learning and artificial intelligence
- Adrian Lopez Pirvu (2024), Computer Vision, Speech Technology, Biosensors, and NLP for Child and Adolescent Mental Health
- Akira-Miranda Adeyomi Adeniran-Lowe, Natalia Karina Kasinska, Glebs Vinarskis (2024), On Anti-deepfake Methods for Audio, Speech and Multimodal Technology
- Smilla Due (2024), Evaluation of Large Language Models (pre-print)
Course projects
- Andro Kranjcevic (2025), MSc project, A Survey on Sentiment Analysis using Natural Language Processing (NLP) Techniques: Methods, Applications, and Comparative Insights
- Ting-Hui Cheng (2025), MSc project, Benchmark for bias and fairness in atypical speech and voice
- Zhijin Lyu & Yutong Jin (2024), Research project, Robustness in deeplearning models
- Zhijin Lyu (2024), MSc project, Multimodal Deepfake Detection
- Angelos Michelis (2024), MSc project, AI tools and implementation
- Anna Leschanowsky (2020), MSc project, Perception of Privacy Measured in the Crowd–Paired Comparison on the Effect of Back-ground Noises (publication)
- Rosa Louise Elinor Marker (2021), BSc project, Wearable to assist children with OCD
