Dr. Konstantinos Drossos was born in Thessaloniki, Greece. He holds a BEng on Sound Technology with first-class honours (Technological Educational Institute of Ionian Islands, now merge with Ionian University, Greece), a BSc on Informatics (Ionian University, Greece), an MSc on Sound & Vibration Research (I.S.V.R., University of Southampton, U.K.), and a PhD with first-class honours and thesis title “Emotional Information Retrieval from Sound Events” (Ionian University, Greece).
Currently he is a Principal Scientist, Machine Learning, at NOKIA Technologies.
He has been a senior data scientist at Wolt Oy, a senior researcher and a postdoc researcher at Audio Research Group, Tampere University (former Tampere University of Technology, Finland) and working under Prof. Tuomas Virtanen, a postdoc fellow at Montreal Institute for Learning Algorithms (Mila, Université de Montréal, Canada) and working under Prof. and Alan Turing prize recipient, Yoshua Bengio, and a postdoc fellow at Music Technology Group (Universitat Pompeu Fabra, Spain) and working under Prof. X. Serra.
He is the author or co-author of over 50 research papers in international journals and conferences, has pioneered the field of audio captioning, is one of the pioneers of the field of emotion recognition from general sounds, has co-organized the very first ever international challenge on audio captioning, serves as a reviewer for top journals and conferences in audio signal processing, has organised multiple special sessions and workshops in international conferences, and has served as the Chairman of the Finnish IEEE Joint Chapter of Signal Processing and Circuits and Systems societies (SP&CAS, from 2016 to 2019). His research interests include audio captioning, domain adaptation, multimodal translation, source separation, detection and classification of acoustic scenes and events, machine listening.