جست‌وجوی استاد و پژوهشگر

Minje Kimمشاهده پروفایل

دانشیار

• AI for Audio
• Model Compression
• Personalized AI
• +۳ مورد دیگر

Minje Kim is an Associate Professor at the University of Illinois at Urbana-Champaign (UIUC), affiliated with the Siebel School of Computing and Data Science and Department of Computer Science. He also serves as an Amazon Visiting Academic at Amazon Lab126. Previously, he held positions at Indiana University and the Electronics and Telecommunications Research Institute (ETRI) in Korea. His research focuses on efficient machine learning models for audio applications, including model compression, personalized AI, and neural speech/audio coding. He has over 60 patents and has received honors such as the NSF CAREER Award (2021) and IEEE Best Paper Award (2020). Education: Ph.D. in Computer Science, UIUC (2016) M.S. in Computer Science and Engineering, POSTECH (2006) B.E. in Information and Computer Engineering, Ajou University (2004) Research Interests: AI for Audio Model Compression Personalized AI Signal Separation Speech Enhancement Neural Speech and Audio Coding Professional Activities: Editorial roles: ACM/IEEE Transactions in Audio, Speech and Language Processing; EURASIP Journal on Audio, Speech, and Music Processing Conference organization: Co-chair of HSCMA 2024 and General Co-chair of WASPAA 2023 Awards: NSF CAREER Award (2021) IEEE Signal Processing Society Best Paper Award (2020) Indiana University Trustees Teaching Award (2021) Grants & Consulting: NSF CAREER Grant (2021) Amazon Visiting Academic role (2020–present) Labs & Teams: Active collaborations with Amazon Lab126 and contributions to open-source frameworks like the Time-Frequency Domain RF Classification Toolkit.

Jorge Perianez-Pascualمشاهده پروفایل

پژوهشگر

• Software Engineering
• Artificial Intelligence
• Machine Learning
• +۷ مورد دیگر

Jorge Perianez-Pascual is a researcher at i3lab and co-founder of MetrikaMedia, currently pursuing doctoral studies at Universidad de Extremadura (UEx). His educational background includes: Bachelor in Software Engineering (2017) from Universidad de Extremadura Master in Software Engineering (2019) from Universidad de Extremadura His research spans Software Engineering and Artificial Intelligence with specific focus on: Machine Learning & Predictive Analytics Multimedia processing applications Industry 4.0 implementations Business Intelligence systems Data Visualization techniques Advanced audio classification methods His recent publications demonstrate innovation in audio classification using deep learning, particularly exploring EnCodec's latent space as an alternative to traditional spectrogram-based approaches. His work shows significant improvements in computational efficiency while maintaining classification accuracy across music genres, speech-music discrimination, and ambient sound recognition tasks. As co-founder of MetrikaMedia, he actively bridges academic research with practical applications, participating in events like the Winter School of AI and SE in Doha and Foro Conecta Empresas 2022.

• Deep Learning
• Audio-Visual Learning
• Multi-Modal Video Understanding
• +۳ مورد دیگر

Vladimir Iashin is a Postdoctoral Research Fellow at the Visual Geometry Group (VGG), University of Oxford . He earned a PhD with distinction in EECS from Tampere University and holds MSc in Applied Mathematics and Computer Science and BSc in Economics from HSE University . PhD (with distinction), Tampere University MSc (with distinction), HSE University BSc, HSE University His research focuses on deep learning for multi-modal video understanding , particularly audio-visual synchronization and visually guided sound generation . He develops transformer-based architectures for cross-modal sequence modeling and neural audio codecs for efficient spectrogram generation. His recent publications analyze techniques like codebook-based audio generation and sparse synchronization , with applications in open-domain sound synthesis and automatic evaluation metrics (e.g., Melception, MKL). Key trends include transformer scalability on large datasets (VGGSound) and visual-conditioned sampling trade-offs between fidelity and speed. Scientific awards include his PhD with distinction . He contributed to open-source tools like Video Features for GPU-accelerated video processing and co-authored benchmarks for container property estimation in robotics.

• Artificial Intelligence
• Machine Learning
• Deep Learning
• +۳ مورد دیگر

Albert Gu is an Assistant Professor in the Machine Learning Department. His research focuses on advancing artificial intelligence and machine learning, particularly in recurrent neural networks, sequence modeling, and efficient computational architectures. He has contributed to state space models, distillation techniques, and applications in fields like bioinformatics and speech recognition. His work emphasizes balancing model efficiency with performance in handling long-range dependencies and complex data types. Key research interests include: Recurrent and state space models for sequence data Efficient neural network architectures Applications in genomics and speech processing Model distillation and knowledge transfer His recent publications (2023-2025) demonstrate a focus on model optimization, such as subquadratic architectures for biological sequences (Lyra) and bidirectional state space models for DNA analysis (Caduceus). He has also explored hybrid approaches combining transformers with recurrent components (HybriDNA) and advanced distillation methods for PDE modeling. No formal awards or grants are listed, but his work is notable for bridging theoretical advancements with practical applications in diverse domains.

Park Woo-chanمشاهده پروفایل

استاد

• Real-time Ray Tracing
• GPU Architecture for Mobile Devices
• FPGA Implementation
• +۴ مورد دیگر

Professor Park Woo-chan is affiliated with the Department of Computer Engineering at Sejong University. His research focuses on real-time ray tracing, GPU architecture for mobile devices, and FPGA implementations. He has a strong publication record in 3D graphics and AI semiconductors. 1989-1993: Bachelor's in Computer Science, Yonsei University 1993-1995: Master's in Computer Science, Yonsei University 1995-2000: Doctorate in Computer Science, Yonsei University He leads the Processor Lab, which specializes in media processors including high-performance mobile GPUs and AI semiconductors. The lab has extensive experience with industry projects for Samsung and LG, national initiatives, and industry-academia collaborations. Research interests span real-time ray tracing algorithms, GPU memory systems, lossless data compression, computer arithmetic, and hardware acceleration for 3D graphics and sound rendering. Recent publications show a strong focus on real-time sound propagation, multi-threaded algorithms, depth level control, and FPGA implementations for ray tracing. Keywords from his work include: Computer Science , Neural Networks , GPU Architecture , 3D Rendering , Mobile Graphics , and FPGA Acceleration . Contact: pwchan@sejong.ac.kr

GE Mengمشاهده پروفایل

پژوهشگر ارشد

• Speech Signal Processing
• Social Network Analysis
• Healthcare with AI
• +۳ مورد دیگر

GE Meng is a Research Fellow at the National University of Singapore (NUS), affiliated with the Saw Swee Hock School of Public Health. Their research focuses on Speech Signal Processing, Social Network Analysis, and Healthcare with AI. They hold a Ph.D. in Applied Computer Technology (Tianjin University, 2022), M.E. in Software Engineering (Tianjin University, 2017), and B.E./B.S. degrees in Software Engineering and Public Management (Tianjin Polytechnic University, 2015). Key research interests include developing AI-driven solutions for speech enhancement, speaker extraction, and audio-visual processing, with applications in healthcare and social network analysis. Dr. Meng has received notable awards, including the Honda Kiyoshi’s Advanced Speech Science Award (2023) and a runner-up in the Intel N-DNS Challenge (2023). Prior to NUS, Meng was a Research Assistant at the Chinese University of Hong Kong, Shenzhen (2022–2023). Their work spans over 20 peer-reviewed publications, focusing on neural networks, graph-based learning, and real-world speech recognition challenges. Current projects emphasize scalable tools for speaker extraction and improving model robustness in noisy environments.

Renzheng Shiمشاهده پروفایل

پژوهشگر

• Speech Coding
• Machine Learning
• Audio Signal Processing
• +۳ مورد دیگر

Renzheng Shi is a Researcher at the Institute of Communications Engineering within the Faculty of Electrical Engineering, Information Technology, Physics at Braunschweig University of Technology, specializing in signal processing and machine learning applications for speech and audio systems. His academic background includes: Master of Science in Signal and Information Processing from Xidian University, China (2016-2019) Bachelor of Science in Internet of Things from Jiangnan University, China (2012-2016) Shi's research centers on neural network-based speech coding, with emphasis on high-fidelity audio reconstruction using generative models. His work bridges traditional signal processing with deep learning techniques, particularly exploring generative adversarial networks (GANs) and latent space representations for speech enhancement. Current projects focus on developing efficient neural codecs that improve transmission quality while reducing computational complexity, directly addressing limitations in modern communication technologies like video conferencing and streaming services. As part of the Signal Processing and Machine Learning department, Shi collaborates on cutting-edge research that integrates machine learning methodologies into audio coding frameworks. His supervisory role in master's theses demonstrates active contribution to academic training, with recent work targeting publishable advancements in neural audio codec architectures.

• Speech Communication Technology
• Voice Pathology Detection
• Machine Learning in Audio Analysis
• +۳ مورد دیگر

Saska Valtteri Tirronen is a Doctoral Researcher at the Department of Information and Communications Engineering at Aalto University , specializing in Speech Communication Technology . Their research focuses on applying advanced machine learning techniques to address complex challenges in voice pathology and health diagnostics. Key Research Areas: Speech signal processing for medical applications Transformer-based and WAV2VEC models in disorder detection Glottal feature analysis and acoustic modeling Robust detection in telephony environments Severity classification of speech disorders Publication Trends: Recent work emphasizes database-independent voice disorder detection, leveraging self-supervised models to improve generalizability. Collaborations span interdisciplinary fields including biomedical engineering, acoustics, and clinical diagnostics. Research Groups: Speech Communication Technology

• Speech Processing
• Signal Enhancement
• Bandwidth Extension
• +۳ مورد دیگر

Esteban Andrés Gómez Mellado is a Visiting Doctoral Researcher at the Department of Information and Communications Engineering at Aalto University. His work focuses on advanced signal processing techniques for speech enhancement and bandwidth extension. Academic affiliation: Aalto University, Department of Information and Communications Engineering Research focus: Speech processing, neural networks, and real-time audio systems Recent publications analyze noise suppression in reverberant environments and low-complexity neural network implementations. He also contributes to interdisciplinary studies in Turkish music theory. Collaborators include Tom Bäckström and Benedikt Wimmer. Current research trends involve deep learning applications for audio signal enhancement and cultural evolution of musical systems.

Nilesh Madhuمشاهده پروفایل

استاد

• Machine Learning
• Audio & Speech Enhancement
• Automated Audio Scene Analysis
• +۴ مورد دیگر

Nilesh Madhu is a Professor for Audio and Speech Processing at Ghent University and imec, Belgium, where he leads research in the Internet Technology and Data Science Lab (IDLab). His academic journey began with a Dr.-Ing. degree (summa cum laude) from Ruhr-Universität Bochum, Germany in 2009, followed by a Marie-Curie postdoctoral fellowship at KU Leuven. Prior to his academic appointment, he served as Principal Scientist and team lead at NXP Semiconductors from 2011-2017, developing advanced audio algorithms for mobile devices. His research spans multiple domains within signal processing, with a particular focus on machine learning applications for audio and speech enhancement, automated audio scene analysis, and hearing prostheses. Professor Madhu's work bridges theoretical signal processing with practical implementations in communications, healthcare, and assistive technologies. Analysis of his recent publication record reveals a strong emphasis on deep learning approaches for speech enhancement, with particular attention to phase reconstruction, multichannel processing, and efficient model architectures. His research increasingly incorporates biomedical applications, particularly in cardiovascular monitoring using advanced sensing techniques like laser Doppler vibrometry. His laboratory work centers around the Internet Technology and Data Science Lab (IDLab) at Ghent University, where his team develops innovative signal processing algorithms with applications spanning mobile communications, hearing aids, and biomedical monitoring systems. The group maintains strong industry connections, evidenced by their focus on practical implementation constraints and real-world performance metrics.

Stuart Cunninghamمشاهده پروفایل

مدرس ارشد

• Affective Technologies
• User Experience (UX)
• Human-Computer Interaction
• +۶ مورد دیگر

Dr. Stuart Cunningham is a Senior Lecturer in Computer Science at the University of Chester, where he also serves as Programme Leader for the MSc Advanced Computer Science, REF Unit of Assessment 11 co-ordinator, and Senior Postgraduate Research Tutor. Previously, he held roles at Manchester Metropolitan University (Visiting Research Fellow and Senior Lecturer) and Glyndwr University (Reader in Audio and Affective Computing, Head of Department, and Lecturer/Senior Lecturer). With 20+ years in higher education, his expertise spans academic leadership, teaching, and research in computing and creative technology hybrids. He holds a PhD in Computer Science from the University of Wales (2009), an MSc in Multimedia Communications from the University of Paisley (2003), and a BSc in Computer Networks (2001). Cunningham’s research focuses on affective technologies, audio compression (e.g., ACER codec), and interdisciplinary applications of sound design in fields like healthcare, gaming, and film. He chairs the Audio Mostly steering committee and contributed to the MPEG-SMR working group developing ISO/IEC 14496-23:2008. His work bridges technical and creative domains, exploring biofeedback sensors for emotional state analysis, Foley artistry in 3D animation, and auditory alerts in safety systems. He advocates for practice-led research methodologies that combine creative outputs with empirical validation. Cunningham has authored numerous publications, including research articles, book chapters, and creative works, and actively participates in peer reviewing for journals like IEEE Transactions and Personal and Ubiquitous Computing . In teaching, he emphasizes interactive/collaborative learning and portfolio-based assessment across undergraduate and postgraduate courses. He has designed and delivered degree apprenticeship programs, particularly during the pandemic, and teaches courses like Web Systems, Software Development, and User Experience Design. His research also extends to UX education, esports analytics, and assistive technologies for dementia care.

Olivier Fercoqمشاهده پروفایل

استاد

• Optimization Algorithms
• Primal-Dual Methods
• Coordinate Descent Methods
• +۴ مورد دیگر

Olivier Fercoq is a Professor at Télécom Paris, affiliated with the Laboratoire Traitement et Communication de l’Information (LTCI). He holds a PhD in Applied Mathematics from École Polytechnique (2012) and has held academic roles including Assistant Professor (2015–2021) and Postdoctoral positions at Télécom ParisTech and the University of Edinburgh. Education: PhD in Applied Mathematics, École Polytechnique (2009–2012) Master of Research in Optimization, Paris 6 University (2008–2009) Engineer's Degree in Mathematical Engineering, ENSTA-ParisTech (2006–2009) Research Interests: First-order optimization algorithms, primal-dual methods, and coordinate descent Applications in machine learning, web ranking, and chemotherapy optimization Key Achievements: Second Prize of the IMA Leslie Fox Prize (2015) PhD Thesis Award from the Gaspard Monge Programme (2013) Developed software tools like APPROX and contributions to Scikit-learn Teaching: Advanced courses on optimization, machine learning, and signal processing at Télécom Paris and IPP Master’s programs

• Video Quality Assessment
• Telecommunications
• Quality of Service (QoS)
• +۵ مورد دیگر

Professor Tadeus Uhl is a faculty member at the University of Applied Sciences Flensburg in the School of Information and Communication. His research focuses on telecommunications, video quality assessment, and Quality of Service (QoS) technologies. He maintains an active research profile with numerous publications spanning from 2017 to 2024. Professor Uhl's research interests center around video quality evaluation, telecommunications technologies, and network performance analysis. His work examines cutting-edge topics including 8-bit and 10-bit MP4 coding, machine learning applications for video quality assessment, and user experience with different video resolutions (1K, 2K, and 4K). He has also conducted significant research on 5G technology, VoIP systems, and Quality of Service in IoT environments. His recent publications show a clear trend toward video quality assessment using modern machine learning techniques, with a focus on real-world streaming services like Netflix. His work bridges theoretical network performance concepts with practical applications in video streaming, cellular networks, and offshore communication systems. Professor Uhl has made substantial contributions to understanding Quality of Service parameters across various communication technologies, from traditional VoIP systems to modern IoT networks and offshore wind farm communications infrastructure. His research has been published in notable venues including IEEE conferences, the Journal of Telecommunications and Information Technology, and various scientific journals focused on telecommunications and multimedia technology.