Grigoris Bastas works at the Institute for Language and Speech Processing (ILSP) at the Athena Research Center (ATHENA RC). He received his M.Eng. degree in Electrical and Computer Engineering from the National Technical University of Athens (NTUA), Greece, in 2017. He is currently a Ph.D. candidate at NTUA preparing his thesis on Music Signal Processing and Recognition by Fusioning Visual Information. He has completed his Master’s Thesis on the field of Natural Language Processing as an intern and member of MELODI team of the Informatics Research Institute of Toulouse (IRIT) in France. His research interests are focused around audio and image processing, with emphasis on the study and application of machine learning methods. He is mainly engaged with problems relevant to music information retrieval in multi-modal environments, speech and singing voice analysis and processing, as well as optical character recognition. He has been working at ILSP since 2018 and has participated in the projects iMuSciCA, Drasi και Safety4ALL. Furthermore, he has participated in the organization of Esslli 2017 (29th European Summer School in Logic, Language and Information) in Toulouse and he has attended DeepLearn 2018 (2nd International Summer School on Deep Learning) in Genova.