Rate My Professor Philip Jackson

His research centers on machine audition, exploring how machines process acoustical signals from speech, music, and everyday sounds to discern identity, events, locations, timing, and narrative meaning. Core interests include sound localisation, audio-visual talker tracking, object-based media production, and responsible AI. He has led contributions to prominent projects such as Nephthys, Columbo, BALTHASAR, DANSA, SAVEE (Surrey audio-visual expressed emotion database, 2014), DynamicFaces, QESTRAL, POSZ, UDRC2, S3A, EyesFree, Polymersive, and AI4ME, advancing fields like active noise control for aircraft, speech aero-acoustics, source separation, articulatory models for speech recognition, audio-visual emotion classification, visual speech synthesis, and spatial audio reproduction. With over 200 publications across journals, conferences, patents, and books, and a Google Scholar h-index of 30, his scholarship demonstrates substantial influence in audio signal processing and AI. Key publications include 'Surrey audio-visual expressed emotion (SAVEe) database' (2014), 'ForecasterFlexOBM: A Multi-View Audio-Visual Dataset for Flexible Object-Based Media Production' (2024), 'Fusion of Audio and Visual Embeddings for Sound Event Localization and Detection' (ICASSP 2024), 'Acoustic Room Modelling using a Spherical Camera for Reverberant Spatial Audio Objects' (2017), and 'Personalising sound over loudspeakers' (2019). He holds the position of Associate Editor for Computer Speech and Language (Elsevier) and reviews for journals including Journal of the Acoustical Society of America, IEEE/ACM Transactions on Audio, Speech and Language Processing, and conferences such as InterSpeech and ICASSP.