Overall, how would you describe your mood? – Active and Passive Voice Monitoring in mHealth for Wellbeing
A decade since the launch of mHealth, and some two since the birth of Affective Computing, we are at the edge of seeing voice-based monitoring of wellbeing conquer the consumer market. This is largely owing to recent advances in machine learning - most notably deep neural networks - for voice pre-processing, and analysis, including the ability to entirely learn from the raw audio. The number of health and wellbeing related states that can likewise be pre-diagnosed or monitored is thereby continuously growing over the last years including passive audio-based remote monitoring reaching from simply tracking if you "laughed enough" throughout a day or suffer from a cold over monitoring depression, eating, sleep, and alcohol use disorders, to pre-diagnosis of more specific conditions such as Alzheimer's, Autism, Parkinson's, or Rett Syndrome. However, a number of challenges remain to be faced to maximize adherence and added value of usage - in particular energy-awareness and general efficiency, privacy, and usability. In this talk, latest insights of the presenter are shared on these different aspects reaching from intelligent signal processing and embedded sensing to deep cooperative learning keeping the user via passive monitoring in the loop, synergistic holistic user modelling, and privacy-enhancing encoding of information. This comes with a series of latest benchmarks from diverse European projects and research competitions co-run by the presenter. Watch out - your smart watch might soon watch over your wellbeing.
Björn W. Schuller received his diploma (1999), doctoral degree (2006), habilitation (2012), and Adjunct Teaching Professor title (2013) all in electrical engineering and information technology from TUM in Munich/Germany where he lead the Machine Intelligence and Signal Processing group until 2014, and co-launched audEERING (2012), remaining its CEO. Since 2013, he is with the Imperial College London – currently as a Reader in Machine Learning (Associate Professor), and a Full Professor and head of the Chair of Complex and Intelligent Systems at the University of Passau/Germany. He is further a permanent Visiting Professor at the Harbin Institute of Technology/P.R. China among other Associateships. Previous major stations include Joanneum Research in Graz/Austria (2012) remaining a consultant until 2016, and the CNRS-LIMSI in Orsay/France (2009-10). Dr. Schuller is an elected member of the IEEE Speech and Language Processing Technical Committee, Senior Member of the IEEE, and was President of the Association for the Advancement of Affective Computing (2013-15). He (co-)authored 5 books and more than 600 publications (>13000 citations, h-index = 55). He is the current Editor in Chief of the IEEE Transactions on Affective Computing, and an Associate Editor for Computer Speech and Language, the IEEE Signal Processing Letters, the IEEE Transactions on Cybernetics, and the IEEE Transactions on Neural Networks and Learning Systems, and a General Chair of ACII 2019 and ACM ICMI 2014, a Program Chair of Interspeech 2019, ACII 2015 and 2011, ACM ICMI 2013, and IEEE SocialCom 2012. He won a range of awards including being honoured as one of 40 extraordinary scientists under the age of 40 by the World Economic Forum in 2015 and 2016. He served as Coordinator or PI in more than 10 European Projects, and is consultant of companies such as Huawei or Samsung.