Music: The shorthand of Emotion – Readable to Computers?

Speaker: Prof. Björn W. Schuller
Date: 2016-03-16 (Wed) 14:00 - 16:00
Location: Auditorium 122 at CITI Building
Host: Yi-Hsuan Yang

Abstract:

Music is the shorthand of emotion – according to Tolstoy, and it seems hard to disagree. But is it also readable by computers? In this talk, development aiming at automatic recognition of emotion or mood in music is introduced that repeatedly lead to best results in recent MediaEval Benchmarks on Emotion in Music. These include brute-force feature approaches and deep learning. Further, the analysis of emotion in singing is highlighted. To add, also singer traits such as age or height are considered. To this end, the singing voice is extracted from polyphonic music. The talk also includes a broader perspective on avenues to best provide higher level features for future improvements.  Finally, a broader view on emotion in audio is shared with exemplifying results from transfer learning of emotion across music, speech, and general audio.

Bio:

Björn W. Schuller is Full Professor and Chair of Complex and Intelligent Systems at the University of Passau/Germany, Reader (Associate Professor)  in Machine Learning at Imperial College London/UK, and the co-founding CEO of audEERING. Further affiliations include HIT/China as Visiting Professor and the University of Geneva/Switzerland and Joanneum Research in Graz/Austria as an Associate. Previously, he was with the CNRS-LIMSI in Orsay/France and headed the Machine Intelligence and Signal Processing Group at TUM in Munich/Germany. There, he received his diploma in 1999, doctoral degree in 2006, his habilitation in 2012, and was entitled Adjunct Teaching Professor – all in electrical engineering and information technology.  Best known are his works advancing Intelligent Audio Analysis and Affective Computing. Dr Schuller is President Emeritus of the AAAC, elected member of the IEEE SLTC, and Senior Member of the IEEE. He (co-)authored 5 books and >500 peer reviewed technical contributions (>10,000 citations, h-index = 49). Selected activities include his role as Editor in Chief of the IEEE Transactions on Affective Computing, Associate Editor of Computer Speech and Language, IEEE Signal Processing Letters, IEEE Transactions on Cybernetics, and IEEE Transactions on Neural Networks and Learning Systems. Professor Schuller was General Chair of ACM ICMI 2014, Program Chair of ACM ICMI 2013, IEEE SocialCom 2012, and ACII 2015 and 2011, as well as organiser of the INTERSPEECH 2009-2016 annual Computational Paralinguistics Challenges and the 2011-2016 annual Audio/Visual Emotion Challenges. He won several awards including best results in research challenges such as MediaEval, MIREX, or of ACM Multimedia. In 2015 and 2016 he has been honoured as one of 40 extraordinary scientists under the age of 40 by the World Economic Forum.