Find Academic Supervisors

• Audio Signal Processing
• Beamforming
• Speech Enhancement
• +4 more

Kouei Yamaoka is an Assistant Professor in the Department of Electrical Engineering and Computer Science at Tokyo Metropolitan University's College of Engineering, specializing in advanced audio signal processing techniques. With over 24 publications from 2017-2024, Yamaoka has established a strong research presence in the international signal processing community. Yamaoka's research focuses on innovative beamforming techniques, time delay estimation methods, and speech enhancement algorithms. Their work consistently addresses challenging problems in multichannel audio processing, particularly in underdetermined scenarios where the number of sources exceeds available microphones. Key contributions include causal distortionless response beamforming, minimum-spanning-tree-based time delay estimation robust to outliers, and sound field interpolation for rotation-invariant processing. Analysis of Yamaoka's publication trends reveals a consistent focus on practical audio processing solutions with applications in source separation, speech enhancement, and acoustic scene analysis. The research demonstrates strong theoretical foundations combined with practical implementation considerations, particularly for real-time and online processing scenarios. Recent work has expanded into deep learning applications for bioacoustic analysis, as evidenced by the 2023 publication on marmoset vocalization analysis. Yamaoka maintains a productive collaboration network, with frequent co-authorship with Nobutaka Ono (20 joint publications), Shoji Makino (9 joint publications), and other researchers in the Japanese signal processing community. Publications appear consistently in top venues including IEEE/ACM Transactions on Audio Speech and Language Processing, APSIPA, EUSIPCO, and ICASSP.

• Sound Synthesis
• Physical Modeling
• Virtual Reality Audio
• +6 more

Cumhur Erkut is an Associate Professor in the Sound and Music Computing group within the Department of Architecture, Design and Media Technology at Aalborg University, Copenhagen, Denmark. With a publication record spanning over two decades from 2000 to present, his research bridges computer science, audio engineering, and creative arts. His primary research interests include Sound Synthesis, Physical Modeling of musical instruments, Virtual Reality Audio, Sonic Interaction Design, and Embodied Interaction. His work demonstrates a consistent focus on the intersection of technology and human experience, particularly in how sound and movement interact in digital environments. His recent publications show a strong shift toward AI-driven audio processing, voice conversion, and differentiable digital signal processing techniques. Dr. Erkut's publication trends reveal an evolution from traditional physical modeling of musical instruments (particularly string instruments like tanbur, clavichord, and guitar) toward more contemporary applications in virtual reality, embodied interaction, and AI-powered audio processing. His work consistently emphasizes real-time performance considerations and human-centered design principles. He has served in significant academic roles, including organizing the 17th International Conference on New Interfaces for Musical Expression (NIME 2017) at Aalborg University, demonstrating his leadership within the international research community. His collaborative network is extensive, with frequent co-authorship with Stefania Serafin, Vesa Välimäki, Antti Jylhä, Rolf Nordahl, and other prominent researchers in the sound and music computing field. These collaborations span multiple institutions across Europe, reflecting the international nature of his research.

Mark ThompsonView profile

Professor

• Fluid Dynamics
• Computational Fluid Dynamics
• Flow Instabilities
• +12 more

Professor Mark Thompson is a distinguished academic in the Department of Mechanical & Aerospace Engineering at Monash University, Faculty of Engineering. He holds the rank of Professor and has been a key figure in fluid dynamics research and academic leadership since joining Monash in 1995. He previously worked at CSIRO for ten years and earned his PhD from Monash in 1985. He has served as Associate Dean of Research Training (2003–2007) and Head of Department (2008–2011). Research interests include theoretical, computational, and experimental fluid dynamics, with focus on flow stability, transition to turbulence, bluff body flows, wake dynamics, flow-induced vibration, aeroacoustics, and applications in bioengineering, turbomachinery, vehicle aerodynamics, and sports. His work contributes to sustainable engineering and aligns with UN Sustainable Development Goals. The recent publications highlight a consistent focus on complex fluid-structure interactions, bluff body aerodynamics, and computational/experimental modeling. Key themes include wake transitions, vortex instabilities, flow control via afterbody design, and environmental and industrial applications such as wind comfort and heat transfer. His research combines high-fidelity simulations with wind tunnel and water channel experiments. Scientific awards: Faculty Research Award (2015) Fellow of the Australasian Fluid Mechanics Society (2018) Advising and grants: Professor Thompson is currently accepting PhD students and has supervised numerous research projects. He has led multiple externally funded research initiatives, including ARC-funded projects on flapping aerodynamics and fluid-structure interactions. His consulting experience includes collaborations with AMIRA, CRA, and Ford Europe. He has also contributed to editorial boards of the International Journal of Fluid Dynamics and an Elsevier journal. Labs and teams: He is a core member of a multidisciplinary research group at Monash focusing on fluid dynamics, collaborating closely with Professors Hourigan, Sheridan, and Lo Jacono. The team operates advanced experimental facilities including wind tunnels and water channels, and develops custom CFD codes for simulating complex flows.

• Audio Processing
• Machine Learning
• Sound Event Detection
• +3 more

Paul Primus is a researcher at the Institute of Computational Perception, Johannes Kepler University Linz, specializing in audio processing and machine learning. His work focuses on sound event detection, acoustic scene classification, and language-based audio retrieval, with significant contributions to the DCASE (Detection and Classification of Acoustic Scenes and Events) challenges. Education: Dr. (PhD) MSc BSc Research Interests: Primus's research bridges audio signal processing and deep learning, addressing real-world challenges in machine listening. His work emphasizes device invariance, data efficiency, and transformer architectures for audio analysis. Key contributions include knowledge distillation for audio retrieval, multi-stage transformer training, and novel approaches to language-audio interaction. He actively explores low-complexity solutions suitable for embedded systems and edge deployment. Publication Trends: Primus's recent work (2023-2025) shows a clear trajectory toward multimodal audio-language systems, leveraging transformers and pretraining techniques. His publications increasingly focus on data efficiency, device generalization, and practical deployment constraints, as evidenced by his DCASE challenge submissions. The integration of metadata and cross-modal alignment represents a growing research emphasis. Activities: Adversarial Robustness in Data Augmentation (2020) Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification (2019) Labs and Teams: Primus is a core member of the Institute of Computational Perception at JKU, which leads research in computational audio analysis. The institute maintains strong participation in international challenges like DCASE and collaborates extensively on audio transformer development and language-audio interaction systems.

Ke SunView profile

Assistant Professor

• Mobile Computing
• Internet of Things
• Cybersecurity
• +4 more

Ke Sun is an Assistant Professor in the EECS Department at the University of Michigan, Ann Arbor. His research develops intelligent, deployable sensing systems for mobile, wearable, and IoT ecosystems, with applications in HCI, cybersecurity, health monitoring, and robotics. His work has been implemented in commercial devices like Amazon Echo and Google Home. Research spans: HCI for Mobile/IoT : Touch/gesture sensing (VSkin, RFCanvas) Cybersecurity : Privacy protection against eavesdropping (EveGuard, StealthyIMU) Health/Environmental Sensing : Vital sign monitoring (LoEar), activity logging (EgoADL) Wireless/Robotics : mmWave radar navigation (milliEgo), acoustic temperature sensing (VECTOR) Publication trends show consistent focus on acoustic/wireless sensing (13/15 papers), cybersecurity (5/15), and cross-modal AI fusion. Recent work explores adversarial ML attacks and LLM vulnerabilities. Awards include: Google Ph.D. Fellowship (2023) UbiComp Distinguished Paper Award (2023) ACM SenSys Best Poster Runner-up (2020) ACM-ICPC Asia Gold Medal (2015) Industry collaboration includes three internships at Amazon Lab126 where his research influenced Echo device development. He serves on program committees for ACM MobiSys/SenSys and organized the ICLR ML for IoT Workshop.

Alexander LerchView profile

Associate Professor

• Music Information Retrieval (MIR)
• Signal Processing
• Machine Learning
• +3 more

Alexander Lerch is an Associate Dean of Research and Creative Practice and Associate Professor at the School of Music, Georgia Institute of Technology. He joined Georgia Tech in 2013 and teaches courses in music signal processing, computational music analysis, audio technology, and software engineering. Previously, he was Head of Research at zplane.development, a music technology licensing company. His research focuses on Music Information Retrieval (MIR), blending signal processing, machine learning, music psychology, and systematic musicology. He leads the Music Informatics Group, developing AI-driven tools for music generation, production, and consumption. Lerch authored over 40 peer-reviewed papers and the textbook An Introduction to Audio Content Analysis , accompanied by open-source libraries like libACA and pyACA. Recent work emphasizes generative models, source separation, and audio quality assessment. He actively contributes to conferences such as ISMIR and presents keynote lectures on AI in music and creative expression.

• Semantic Audio
• Music Information Retrieval
• Semantic Web
• +3 more

Dr. George Fazekas is a Senior Lecturer at Queen Mary University of London's School of Electronic Engineering and Computer Science. His research focuses on semantic audio, music information retrieval, and deep learning applications in music technology. He is affiliated with the Centre for Multimodal AI and contributes to advancing technologies like semantic web music, emotion recognition, and differentiable signal processing. His teaching includes modules on research methods, responsible innovation, and the Semantic Web. Research interests span semantic audio analysis, music ontology development, and AI-driven music production tools. He has collaborated on projects such as the Open Multitrack Testbed and the Audio Commons Ontology. Notable contributions include work on handwritten music synthesis, dynamic range compressor control, and adaptive music systems like Mood Conductor. Publications emphasize machine learning for music tasks, including few-shot learning for historical manuscripts and neural synthesis techniques. His work bridges theoretical research with practical applications in audio engineering and music technology.

Faezeh MarzbanradView profile

Senior Lecturer

• Biomedical Engineering
• Signal Processing
• Machine Learning
• +6 more

Dr. Faezeh Marzbanrad is a Senior Lecturer and Equity Diversity and Inclusion Director in the Department of Electrical and Computer Systems Engineering at Monash University. She holds a PhD from the University of Melbourne (2016) and has expertise in biomedical signal processing, machine learning, and statistical data analysis. Her research focuses on developing affordable medical technologies for maternal, fetal, and neonatal healthcare, with an emphasis on telehealth and AI-driven solutions. Dr. Marzbanrad has led and contributed to projects such as AI-driven low-cost ultrasound systems, neonatal respiratory monitoring, and wearable patches for fetal health. She has received prestigious awards including the Veski Victoria Fellowship and the Women in AI Asia Pacific Award. Her team includes multiple PhD students and postdoctoral fellows working on cutting-edge research in neonatal care and medical device innovation. Her academic background includes postdoctoral research at Monash and international collaborations, with a focus on global health equity. Key achievements include developing NeoSSNet for real-time neonatal chest sound separation and advancing fetal monitoring technologies. Awards highlight her contributions to education and research excellence, including the Dean’s Award for Honours Supervision and recognition in the IEEE conferences. Her work bridges engineering and healthcare, addressing critical challenges in neonatal and maternal health.

Gerard RomaView profile

Lecturer

• Audio Analysis and Synthesis
• Digital Musical Instruments
• Intelligent Audio Processing
• +6 more

Dr Gerard Roma is a Lecturer in Audio Software Engineering at the School of Computing and Engineering, University of West London. He contributes extensively to both research and teaching in the domain of sound and music computing, with a strong technical focus on audio technologies and intelligent systems. His research interests span several key areas in modern audio computing, including audio analysis and synthesis , digital musical instruments , intelligent audio processing , audio source separation , and environmental sound recognition . These interests reflect a deep engagement with both creative and computational aspects of sound. Gerard Roma teaches across a range of undergraduate and postgraduate programs such as the MSc Artificial Intelligence for Sound and Music, MSc Digital Audio Engineering, BSc (Hons) Sound Engineering, and MSc Applied Acoustics. His educational background includes a PhD in Engineering and a BSc (Hons) in Acoustics, grounding his work in rigorous scientific and engineering principles. Though no publications or awards are listed in the current profile, his expertise aligns with cutting-edge developments in audio AI and software engineering. He is also an active practitioner in electronic and computer music, bridging academic research with artistic application.

Mark SandlerView profile

Professor

• Digital Signal Processing
• Machine Learning
• Deep Learning
• +6 more

Mark Sandler is a Professor of Signal Processing and Director of the Centre for Digital Music at Queen Mary University of London. He leads the School of Electronic Engineering and Computer Science and contributes to the Centre for Multimodal AI. His work spans Digital Signal Processing, Machine Learning, and their applications in Audio and Music Technology, including source separation, neural audio synthesis, and physics-informed models. He has pioneered research in music informatics, sound synthesis, and AI-driven creativity. Awards include Fellowships from the Royal Academy of Engineering (FREng), IEEE (FIEEE), IET (FIET), and Audio Engineering Society (FAES). Research interests include audio segmentation, harmonic analysis, and interdisciplinary projects with computer vision. He has authored numerous publications on topics like neural synthesizers, knowledge distillation, and spatial audio systems. His contributions extend to semantic web technologies for music production and interactive audio applications. Current projects focus on low-latency synthesis, machine learning for music tagging, and adaptive audio systems. Awards and grants highlight leadership in digital music innovation. His academic roles include supervising research groups and directing interdisciplinary initiatives. The labs under his leadership include the Centre for Digital Music and collaborations with industry partners on audio engineering and immersive technologies.

• Aerodynamic Unsteadiness
• Road and Racing Car Aerodynamics
• Advanced Wind Tunnel Instrumentation and Analyses

Professor David Sims-Williams is a faculty member at the Department of Engineering within the Faculty of Science at Durham University . His research focuses on Aerodynamic Unsteadiness , Road and Racing Car Aerodynamics , and the Development of Advanced Wind Tunnel Instrumentation and Analyses . He is actively involved in experimental and computational studies of fluid dynamics, vehicle aerodynamics, and aeroacoustic noise. Academic Rank: Professor Research Keywords: Aerodynamics, Fluid Mechanics, Automotive Engineering, Computational Fluid Dynamics, Noise Control His recent work includes studies on flow-induced vibration of polygonal cylinders , piezoelectric actuator integration in wind turbines , and beamforming techniques for noise source localisation . He frequently publishes in journals like SAE International Journal of Passenger Vehicle Systems , Journal of Fluids and Structures , and Physics of Fluids . His collaborations span fluid-structure interactions, transient flow analysis, and automotive noise reduction strategies. He has presented at major conferences including the International Vehicle Aerodynamics Conference , UK Fluids Conference , and SAE World Congress . His methodologies combine large eddy simulations , wind tunnel experiments , and machine learning for flow visualisation .

• Digital Signal Processing
• Audio Forensics
• Acoustics
• +3 more

Dr. Rob Maher is a Professor in the Department of Electrical & Computer Engineering at Montana State University (MSU), part of the Norm Asbjornson College of Engineering. He holds a BS from Washington University, an MS from the University of Wisconsin-Madison, and a Ph.D. from the University of Illinois at Urbana-Champaign, all in Electrical Engineering. His research focuses on digital audio signal processing, audio forensics, music synthesis, and acoustics. He served as ECE Department Head from 2007–2017 and is an Affiliate Professor of Music Technology in MSU's School of Music. Education: B.S. Washington University (1984), M.S. UW-Madison (1985), Ph.D. Illinois Urbana-Champaign (1989) Research Interests: Forensic audio analysis, gunshot acoustics, music synthesis, room acoustics Teaching: Courses on signal processing, audio engineering, and ethics in engineering He is a Fellow of the Audio Engineering Society (AES), Senior Member of IEEE, and has received awards including MSU's President's Excellence in Teaching Award (2022). His work includes over 50 publications on forensic audio analysis and acoustic modeling, as well as grants from the National Institute of Justice and National Park Service. Professional service includes editorial roles at the Journal of the AES and leadership in organizations like the IEEE Central Montana Section. He also engages in community activities as a runner and musician, including membership in the Second String Orchestra.

Gaël RichardView profile

Professor

• Audio Signal Processing
• Speech Synthesis
• Source Separation
• +5 more

Gaël Richard is a Professor at Télécom Paris, part of the Institut polytechnique de Paris. He leads the Signal, Statistics and Learning (S²A) research group within the LTCI laboratory and is the Executive Director of Hi! Paris, a hub for AI and data science. His primary research focuses on audio signal processing, including speech synthesis, source separation, and non-negative matrix factorization techniques. He has contributed significantly to applications in automotive and music industries, and his work has been recognized with the 2020 IMT-Académie des Sciences Grand Prix and a 2022 ERC Advanced Grant for the HI-Audio project. Education and Career: Gaël Richard transitioned from classical music to applied mathematics, earning a PhD in speech synthesis. His academic journey blends technical expertise with creative problem-solving, leading to impactful contributions in machine learning and audio technologies. Research Interests: His work spans machine learning for audio signals, including speech synthesis, sound separation, and music information retrieval. He emphasizes reproducibility, publishing tools like YAAFE and databases widely used in the field. Key Projects: The HI-Audio project explores AI-driven audio processing, while his ERC grant supports advancements in hybrid deep learning for audio. He co-supervises PhD students in areas like intelligibility in noisy environments and EEG-based source separation. Awards and Recognition: In addition to major grants and the IMT-Académie des Sciences prize, his work on source separation and audio indexing has earned international acclaim. He actively contributes to academic conferences and serves on editorial boards. Labs and Teams: He leads the S²A team at LTCI, fostering collaborations between academia and industry partners like Thales and Deezer. His research bridges theoretical advancements with practical applications in audio technology.

Li WanView profile

Lecturer

• Acoustics
• Speech Processing
• Machine Learning
• +4 more

Li Wan serves as a Lecturer at the Language Centre within Queen Mary University of London's School of Languages, Linguistics and Film. Despite her institutional affiliation with language education, her research output demonstrates deep expertise in acoustics, machine learning, and sensor networks, reflecting an unusual interdisciplinary profile spanning engineering and biomedical applications. Her research interests center on acoustics and speech processing, with significant contributions to machine learning applications in sensor networks, signal processing, and natural language processing. Recent work focuses on binaural audio rendering, emotion recognition systems, and biomedical diagnostics using electrocardiogram data, often addressing real-world challenges like missing sensor data and class imbalance in classification tasks. This research bridges engineering disciplines despite her Language Centre appointment. Analysis of her 15 most recent publications reveals a strong trend toward physics-informed neural networks for audio applications and sensor-based human activity recognition. Her work frequently appears in specialized challenges like the SHL and Odyssey competitions, emphasizing practical implementations for locomotion recognition, drone audition, and text segmentation. Key methodological themes include multimodal fusion, data augmentation, and cross-domain adaptation. Scientific Awards: No formal awards or fellowships documented in provided sources While her Language Centre role suggests teaching responsibilities in Chinese language, her publication record indicates active research mentorship in engineering domains. No grants or student advisement details are publicly available, though her challenge competition participation implies collaboration with technical research teams. The absence of lab affiliations in current documentation contrasts with her hardware-oriented work on drone audition and sensor systems.

• Music Processing
• Music Information Retrieval
• Audio Signal Processing
• +1 more

Prof. Dr. Meinard Müller is a Professor at Friedrich-Alexander Universität Erlangen-Nürnberg (FAU), leading the Chair of Semantic Audio Signal Processing within the International Audio Laboratories Erlangen (a joint institute with Fraunhofer IIS). He specializes in Music Processing, Music Information Retrieval, Audio Signal Processing, and Motion Processing. His work bridges fundamental research and practical applications in music technology, including audio decomposition, source separation, and computational musicology. Research Interests: Focus on algorithmic methods for music analysis, audio feature extraction, and real-time audio processing. Teaching: Supervises a large group of doctoral and master’s students, offering courses on audio processing and music technology. Awards: Recognized as an IEEE Fellow (2020) and ACM Senior Member (2020). His research group develops open-source tools like the FMP Notebooks and libfmp, and maintains datasets such as the Wagner Ring Dataset and Dagstuhl ChoirSet. He actively contributes to conferences like ISMIR and ICASSP, with over 200 publications in top-tier journals and conferences.