جستجوی استاد راهنمای دانشگاهی

Mikko Kurimo is a Full Professor at Aalto University's Department of Information and Communications Engineering, School of Electrical Engineering. He earned his M.Sc., Lic.Tech., and D.Sc.(Tech.) from Helsinki University of Technology (1992, 1994, 1997) and pioneered neural networks for automatic speech recognition (ASR) in his PhD thesis. After research roles at IDIAP (Swiss AI center) and visiting positions at University of Colorado, Edinburgh, SRI, ICSI, and Nitech, he leads Aalto's ASR group since 2000. His work focuses on unsupervised subword modeling for morphologically complex languages (Finnish, Estonian, Turkish, Arabic) and large speech foundation models. PhD in Neural ASR (Helsinki University of Technology, 1997) Research Scientist at IDIAP (Switzerland) Visiting Fellow at University of Colorado, Edinburgh, SRI, ICSI, Nitech Head of Aalto ASR Group (2000-present) His research spans deep learning for ASR, spoken language modeling , and low-resource language solutions . Recent work explores continued pre-training of self-supervised models, multimodal emotion recognition, and pronunciation assessment using LLMs. He led the winning team in the 2017 Multi-Genre Broadcast challenge and secured competitive funding in Tekes Challenge Finland and EC's H2020-ICT-2017. Key article trends include: Advancements in children's speech recognition and dysarthric speech processing Integration of generative AI for language learning feedback Specialization in low-resource Uralic languages (Finnish, Northern Sámi) Development of robust ASR systems for complex phonetic environments Scientific Awards ACM Multimedia 2023 Computational Paralinguistics Challenge Prize First place in MGB3 2017 Arabic ASR Challenge ISCA Best Student Paper Award (2011) Professeur Invité at Université de Saint-Etienne (2005-2006) Royal Society International Short Visit Fellowship (2004) Professor Kurimo leads the Speech Recognition Group at Aalto, collaborating with COIN (Centre of Excellence in Computational Inference) and AIRC (Adaptive Informatics Research Centre). His projects like CaptainA mobile app demonstrate practical applications of ASR in language education. He has supervised numerous publications with co-authors in domains spanning bandwidth extension, stuttering detection, and speech sound disorder assessment.

• Deep Learning
• Automatic Speech Recognition (ASR)
• Spoken Language Modeling
• +۳ مورد دیگر

Prof. Vesa Välimäki is an Audio Signal Processing Professor at Aalto University's School of Electrical Engineering, leading the Audio Signal Processing Research Group within the Aalto Acoustics Lab. He also serves as Vice Dean for Research and Head of the Doctoral Programme at the university. His research focuses on digital signal processing, machine learning, and their applications in audio, acoustics, and music technology, particularly in artificial reverberation, audio filter design, and virtual analog modeling. He has pioneered techniques like velvet noise for reverberation synthesis and contributed to open-source tools like FLAMO. His academic accolades include IEEE, AES, and AAIA Fellowships, along with multiple best paper awards at venues like DAFx and ICASSP. He has advised numerous students, including recipients of prestigious awards like the Huawei Master's Thesis Award. Prof. Välimäki has held editorial roles at the Journal of the Audio Engineering Society and organized major conferences such as SMC-17. His work extends to applied projects like acoustic optimization for early childhood education facilities and immersive audio in virtual reality (e.g., the 'Space Walk' project). Key Projects: NordicSMC (Nordic University Hub for Sound and Music Computing), Aalto Acoustics Lab, FLAMO library Grants: NordForsk funding (2018–2023), Foundation for Aalto University Science and Technology His research spans both theoretical advancements (e.g., diffusion models for audio restoration) and practical implementations (e.g., real-time equalizers, headphone compensation systems). He collaborates internationally, contributing to acoustic measurement techniques and noise reduction strategies for diverse environments.

• Digital Signal Processing
• Machine Learning
• Audio Technology
• +۸ مورد دیگر

Paavo Alku is a Professor of Speech Communication Technology at Aalto University's Department of Information and Communications Engineering. With academic credentials from Helsinki University of Technology (M.Sc. 1986, Lic.Tech. 1988, Dr.Sc.Tech. 1992), he has held academic positions at Asian Institute of Technology (1993) and University of Turku (1994-1999). Current research focuses on speech production analysis, parametric speech synthesis, and speech-based biomarkers for health monitoring Actively develops machine learning models for voice disorder detection and Parkinson's disease classification Principal investigator for projects including SymptoSonic (2024-2025) and HEART (2020-2024) His recent publications emphasize: Wavelet scattering for neurological speech analysis Fisher vector representations in voice disorder classification Machine learning approaches to vocal intensity categorization Respiratory aerosol emission during speech production Formant tracking through hybrid neural network/LP methods Awarded: IEEE Fellow (2020) Academy Professor (2015-2019) Multiple best student paper awards at ICASSP and Interspeech

• Speech Communication Technology
• Speech Signal Processing
• Machine Learning Applications in Speech Analysis
• +۳ مورد دیگر

Mia Liljeström is a Staff Scientist at the Department of Neuroscience and Biomedical Engineering, Aalto University. She holds a Doctoral Degree in Engineering and Technology from Aalto University (2010) and a Master's Degree in Engineering and Technology from Helsinki University of Technology (2002). Doctoral Degree: Aalto University, 2010 Master's Degree: Helsinki University of Technology, 2002 Her research focuses on Magnetoencephalography (MEG) , Functional Connectivity , and Brain Networks . She explores Transcranial Magnetic Stimulation (TMS) , Functional MRI , and Neural Networks to map language-critical brain areas and study cortical dynamics. Recent work includes automated speech artefact removal from MEG data and test-retest reliability of brain connectivity metrics. Mia actively participates in conferences like MEG Nord and has presented invited talks on language processing and large-scale brain networks. Her publications emphasize MEG-informed TMS, cortical beta modulation, and brain stimulation precision. She contributes to the UN Sustainable Development Goal of Quality Education through neuroimaging research.

• Magnetoencephalography
• Functional Connectivity
• Brain Networks
• +۳ مورد دیگر

Eloi Moliner Juanpere is a Doctoral Researcher and Doctoral Student at Aalto University's School of Electrical Engineering, Department of Information and Communications Engineering. His research focuses on audio signal processing, leveraging diffusion-based generative models for tasks such as dereverberation, timbre transfer, and audio restoration. His work aligns with the UN Sustainable Development Goals through innovative contributions to audio technology. Proficient in deep learning and inverse problem solving, Moliner Juanpere has published extensively in top conferences like IEEE ICASSP and DAFx, emphasizing unsupervised methods for audio enhancement. Recent publications highlight advancements in diffusion models for room acoustics estimation blind bandwidth extension neural audio effects modeling timbre transfer in musical signals Scientific recognition includes Best Student Paper Award (1st place) at IWAENC 2024 Best Student Paper Award at ICASSP 2023 Third Best Paper Award at DAFx-22 He contributes to collaborative projects such as NordicSMC (2018–2023) and SA Profi 6 (2021–2027), focusing on neural networks and audio signal enhancement. His research also involves creating datasets like the Magnetic Tape Recorder Dataset (2023) for audio restoration applications.

• Audio Signal Processing
• Machine Learning
• Deep Learning
• +۶ مورد دیگر

Sami Äyrämö is an Associate Professor at the Faculty of Information Technology , University of Jyväskylä. His research bridges machine learning and health science , focusing on innovative applications in biomechanics , medical imaging , and exercise physiology . Specializes in automated scoring systems for medical diagnostics Pioneer in domain-specific transfer learning for healthcare data Develops synthetic data for wellbeing sector innovation His work spans colorectal cancer tissue analysis , ACL injury risk modeling , and dementia detection from speech , with recent studies applying cluster analysis and deep learning to sports biomechanics challenges. Current projects include the WellbeingDataLab initiative for synthetic exercise data, and collaborations with the Computational Data Science Research Group on spectral imaging and health analytics.

• Computer Science
• Machine Learning
• Health Science
• +۱۱ مورد دیگر

Archontis Politis is an Assistant Professor in the Department of Computing Sciences at Tampere University's Faculty of Information Technology and Communication Sciences. His research focuses on signal processing, machine learning, and their applications in audio engineering, particularly in spatial audio, sound source separation, and parametric audio coding. He explores topics such as Ambisonics, reverberation control, and neural network-based approaches for audio processing. His work emphasizes spatial audio reproduction, including six degrees of freedom (6DOF) rendering, microphone array processing, and efficient compression techniques for higher-order Ambisonics. He also investigates sound event localization and detection, leveraging machine learning for real-world acoustic scenarios. His contributions span theoretical advancements in spherical harmonics and practical implementations of spatial audio systems. Recent research highlights include developing datasets for music source separation, improving synthetic-to-real generalization in classical music, and creating neural encoding models for irregular microphone arrays. His methodologies often integrate deep learning with traditional signal processing to address challenges in multi-speaker environments and dynamic acoustic scenes.

• Signal Processing
• Machine Learning
• Audio Engineering
• +۷ مورد دیگر

Dr. Krister Linden is a Research Director at the University of Helsinki ’s Department of Digital Humanities under the Faculty of Arts. He is the National Coordinator for FIN-CLARIN and supervises doctoral research, including Rosa Suviranta’s PhD thesis. Research Interests include language technology applications, digital humanities focused on Ancient Near Eastern Empires, science policy, and development of language resources infrastructure. He leads the Language Bank of Finland and participates in EU projects like FIN-CLARIAH and LAREINA. Active in computational linguistics and NLP Contributes to research infrastructures Works on Akkadian text analysis Organizes international conferences Recent Projects include coordination of the Business Finland-funded BF LAREINA (2023–2025) for Finnish speech corpus analysis and leadership in the Digital Europe Programme’s Open European Family of Large Language Models (2025–2028).

• Language Technology
• Digital Humanities
• Ancient Near Eastern Empires
• +۲ مورد دیگر

Stefan Albert Wirler serves as a Researcher in the Department of Information and Communications Engineering at Aalto University, actively contributing to the Communication Acoustics research group specializing in Spatial Sound and Psychoacoustics. His work bridges theoretical audio signal processing with practical applications in spatial audio systems. Primary research areas include Spatial Audio, Psychoacoustics, and Speech Enhancement, with specific focus on microphone array processing, spatial post-filtering techniques, and machine learning applications for auralization. His investigations address critical challenges in virtual reality audio reproduction and headphone acoustics through innovative signal processing approaches. Analysis of his 2020-2024 publications reveals consistent advancements in spatial post-filter design, particularly through non-linear combinations and coherence-based methods for speech enhancement. His work demonstrates growing integration of machine learning with traditional signal processing, notably in rigid sphere scattering modeling and DIY headphone modifications for improved acoustic transparency. Wirler operates within Aalto University's Communication Acoustics research ecosystem, collaborating extensively with senior researchers like Ville Pulkki on projects spanning spatial audio rendering, psychoacoustic validation, and real-time audio processing systems.

• Spatial Audio
• Psychoacoustics
• Speech Enhancement
• +۳ مورد دیگر

Jarmo Malinen is a Lecturer at the Department of Mathematics and Systems Analysis, Aalto University , School of Science. He leads the speech modeling group and participates in the Comspeech consortium, collaborating with institutions like the University of Helsinki and Turku University Hospital. His research spans mathematical systems theory, numerical analysis, and computational speech science, focusing on MRI-based vocal tract modeling, glottal flow dynamics, and speech acoustics. He develops physical models for speech production and contributes to educational technologies like the STACK system. Key publication trends include applications of finite element methods to vowel formants, inverse filtering for glottal flow estimation, and eigenvalue problem solutions for coupled systems. His work intersects applied mathematics, biomedical imaging, and speech physiology. Malinen advises master's and PhD students in mathematical modeling and speech research, though specific student names are not listed in the provided texts. He has developed tools for MRI data post-processing and vocal tract resonance optimization.

• Applied Mathematics
• Numerical Analysis
• Mathematical Systems Theory
• +۳ مورد دیگر

Mikaela Bonsdorff von is a Professor at the Faculty of Sport and Health Sciences , University of Jyväskylä, and leads the Social Gerontology Programme at Folkhälsan Research Center in Helsinki. Her research group investigates healthy and active aging from a life course perspective, integrating doctoral students, postdocs, and project researchers across multiple institutions including University of Helsinki, Tampere University, Karolinska Institutet, VU Amsterdam, and Lund University. Current affiliations: University of Jyväskylä, Folkhälsan Research Center Collaboration networks: Nordic and European aging research institutions Research focus: Multidisciplinary gerontology and public health Research interests center on healthy and active aging from a life course perspective, examining physical, psychological, and social functioning. Key areas include work ability, health trajectories, frailty development, adaptation to adversity, and lifestyle determinants of aging. The group employs diverse methodologies including longitudinal cohort studies and environmental gerontology approaches. Recent publications focus on social vulnerability in aging, early-life determinants of resilience, multimorbidity patterns , and digital health tools for frailty prediction. These studies demonstrate interdisciplinary integration of epidemiology, genomics, and social sciences to understand aging processes. The Paving the Way for Healthy Aging (FINeFI) project develops electronic frailty indices for early risk identification, while the Active University project explores community-building interventions for health promotion. Research outputs emphasize translational applications for preventive geriatrics and public health policy.

• Healthy ageing
• Active ageing
• Gerontology
• +۷ مورد دیگر

Johanna Virkki is an Associate Professor at the Department of Computing Sciences, Faculty of Information Technology and Communication Sciences, Tampere University. Her research focuses on smart textiles, wearable technologies, RFID systems, and their applications in healthcare, assistive communication, and human-computer interaction. She has pioneered projects integrating RFID into clothing and environments for control interfaces, physiological monitoring, and gamified therapies. Key research areas include: Development of e-textiles for AAC (Augmentative and Alternative Communication) RFID-based wearable and furniture interfaces for accessibility Sensor systems for healthcare monitoring and rehabilitation Smart spaces and IoT-enabled environments Her work emphasizes interdisciplinary collaboration, with notable contributions in: Passive RFID sensor platforms for moisture, strain, and physiological signals Co-design approaches involving speech therapists, engineers, and end-users Prototyping wearable devices for children with disabilities and elderly care Recent publications highlight advancements in: Smart furniture and textile-based AAC solutions AI-driven smart spaces and edge-cloud computing Bio-inspired sensors using animal hair and conductive yarns Johanna's research bridges technology and human needs, addressing challenges in healthcare, education, and accessibility through innovative textile and RFID systems.

• Smart Textiles
• RFID Technology
• Wearable Devices
• +۵ مورد دیگر

Joni Kämäräinen is a Professor of Signal Processing at Tampere University’s Computing Sciences department under the Faculty of Information Technology and Communication Sciences. He leads the Vision Group and has a tenure-track career at Tampere University since 2012, achieving full professorship in 2020. Prior, he conducted postdoctoral research at the University of Surrey’s Center of Vision, Speech and Signal Processing and held a faculty position at LUT University. His research spans robot vision and robot learning , focusing on computer vision and machine learning applications. Key applied projects address industrial collaboration with Huawei, Nokia Technologies, and others, emphasizing robust visual perception, autonomous systems, and depth sensor integration. Notable work includes long-term visual place recognition, RGB-D tracking, and color constancy solutions. Recent publications (2023–2025) reflect expertise in digital twins for industrial manipulators, probabilistic subgoal modeling, depth-aware video deblurring, and LiDAR-place recognition datasets. His team’s outputs bridge robotics, AI, and signal processing, with interdisciplinary impacts in healthcare and autonomous navigation. Teaching responsibilities include graduate and doctoral colloquia, and the textbook Koneoppimisen perusteet (2023) . Funding sources include the Academy of Finland, EU Horizon 2020, Business Finland, Huawei, and Nokia Technologies.

• Robot Vision
• Robot Learning
• Computer Vision
• +۵ مورد دیگر

Liisa Mustanoja is a Senior University Lecturer at Tampere University's Faculty of Information Technology and Communication Sciences, within the Department of Language Studies. She leads the Languages Unit and directs the Doctoral Programme in Language Studies (DPLA). Her research focuses on sociolinguistics, sociophonetics, Finnish dialects, and historical language change, particularly analyzing wartime letters and affective speech. She heads the Plural research center and collaborates on projects like Tunteiden Tampere (Kone Foundation grant 2024–2027) and the Sulka corpus initiative. Her academic career includes a PhD in Language Studies and a Docent title. She has held leadership roles in ethics committees and networks like Langnet. She has received teaching awards (2021) and contributed over 38 publications since 2003, focusing on Finnish language variation, speech corpus development, and sociolinguistic methodology. Key grants: Kone Foundation grants for Sulka (2023–2026), Kippo (2017–2022), and Tunteiden Tampere (2024–2027) Research groups: Sumu (Sulka), Plural (Languages and Cultures) Her work bridges human-machine interaction in language, emphasizing ethical communication and inclusivity. Recent projects explore affective speech processing and language policy innovations like the 'Data Protection Passport' concept.

• Sociolinguistics
• Sociophonetics
• Finnish Dialects
• +۵ مورد دیگر

Alexandre Nikolaev is a University Lecturer in General Linguistics at the School of Humanities, University of Eastern Finland. His research focuses on morphological complexity, paradigmatic defectivity in inflectional systems, and cognitive approaches to language structure. Key methodologies include corpus analysis, behavioral experiments, and computational modeling. Affiliation: University of Eastern Finland Research Areas: Morphology, Corpus Linguistics, Psycholinguistics, Neurolinguistics Prominent Research Themes: Paradigmatic defectivity as dynamic systems rather than static gaps Cognitive load in inflectional choice production Interaction of corpus frequency and subjective acceptability ratings Comparative analysis of Finnish, Czech, and Russian inflectional patterns Methodological Expertise: Network analysis, mixed-effects modeling, optimal string alignment techniques, cross-linguistic corpus studies, multi-lab collaboration frameworks. No scientific awards or student advising details were explicitly mentioned in the provided text.

• Corpus Linguistics
• Morphology
• Neurolinguistics
• +۶ مورد دیگر