Rate My Professor Wenwu Wang

Professor Wang's research focuses on signal processing, machine learning, artificial intelligence, perceptual modelling, machine audition, multimodal fusion and learning, and statistical anomaly detection, particularly in audio source separation, generation, captioning, and applications to IoT, UAV computing, and creative audio. He has authored or co-authored over 400 publications, including books *Machine Audition: Principles, Algorithms and Systems* (IGI Global, 2010) and *Blind Source Separation: Advances in Theory, Algorithms and Applications* (Springer, 2014), and key papers such as "PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition" (2020), "AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining" (2024), and "AudioSR: Versatile Audio Super-Resolution at Scale" (2024). He has led or co-led more than 40 projects with over £40 million in funding from UKRI, EPSRC, EU, Dstl, and partners like BBC, Meta, and Huawei. Awards include IEEE Fellow (2026) for contributions to audio classification, generation, and source separation; Meta Distinguished Faculty Award (2026); Audio Engineering Society Best Technical Paper Award (2025); IEEE Signal Processing Society Young Author Best Paper Award (2022); and multiple DCASE awards. He holds editorial roles such as Senior Area Editor for IEEE Open Journal of Signal Processing (2025–2027) and chairs IEEE Signal Processing Society committees.