Research focuses on the development of machine learning methods, with particular emphasis on neural networks, generative models, and multimodal representation learning. These methods are developed within the signal processing framework to analyze, model, and generate structured signals and data across a broad range of application domains, including audio, images, sensor signals, time series, and complex systems.
Danilo Comminiello actively contributes to the international machine learning and signal processing research community through scientific leadership, editorial services, and conference organization. He serves as Chair of the IEEE Machine Learning for Signal Processing Technical Committee and of the IEEE Task Force on Computational Audio Processing, and he is a member of the Board of Governors of the International Neural Network Society. He is Area Editor of IEEE Signal Processing Magazine and Associate Editor of several leading journals, including IEEE Transactions on Neural Networks and Learning Systems, Elsevier Neural Networks, and IEEE Computational Intelligence Magazine. He served as General Chair of IEEE MLSP 2023 and IJCNN 2025.