Timezone: »

Panel: Machine learning and audio signal processing: State of the art and future perspectives
Sepp Hochreiter · Bo Li · Karen Livescu · Arindam Mandal · Oriol Nieto · Malcolm Slaney · Hendrik Purwins

Fri Dec 08 05:45 PM -- 06:30 PM (PST) @
Event URL: http://www.bioinf.jku.at/people/hochreiter/,http://www.slaney.org/malcolm/pubs.html »

How can end-to-end audio processing be further optimized? How can an audio processing system be built that generalizes across domains, in particular different languages, music styles, or acoustic environments? How can complex musical hierarchical structure be learned? How can we use machine learning to build a music system that is able to react in the same way an improvisation partner would? Can we build a system that could put a composer in the role of a perceptual engineer?

Sepp Hochreiter (Johannes Kepler University Linz, http://www.bioinf.jku.at/people/hochreiter/) Bo Li (Google, https://research.google.com/pubs/BoLi.html) Karen Livescu (Toyota Technological Institute at Chicago, http://ttic.uchicago.edu/~klivescu/) Arindam Mandal (Amazon Alexa, https://scholar.google.com/citations?user=tV1hW0YAAAAJ&hl=en) Oriol Nieto (Pandora, http://urinieto.com/about/) Malcolm Slaney (Google, http://www.slaney.org/malcolm/pubs.html) Hendrik Purwins (Aalborg University Copenhagen, http://personprofil.aau.dk/130346?lang=en)

Author Information

Sepp Hochreiter (LIT AI Lab / University Linz)

Head of the LIT AI Lab and Professor of bioinformatics at the University of Linz. First to identify and analyze the vanishing gradient problem, the fundamental deep learning problem, in 1991. First author of the main paper on the now widely used LSTM RNNs. He implemented 'learning how to learn' (meta-learning) networks via LSTM RNNs and applied Deep Learning and RNNs to self-driving cars, sentiment analysis, reinforcement learning, bioinformatics, and medicine.

Bo Li (Google)
Karen Livescu (TTI-Chicago)
Arindam Mandal (Amazon.com)
Oriol Nieto (Pandora)
Malcolm Slaney (Google)
Hendrik Purwins (Aalborg University Copenhagen)

I am currently Associate Professor at the Audio Analysis Lab, at Aalborg University Copenhagen. Before that, I had been Assistant Professor at the same University. Previously, I had been researcher at the Neurotechnology and Machine Learning Groups at Berlin Institute of Technology/Berlin Brain Computer Interface. Previously I was lecturer at the Music Technology Group at the Universitat Pompeu Fabra in Barcelona. I have also been head of research and development at PMC Technologies. I have been visiting researcher at Perception and Sound Design Team, IRCAM; CCRMA, Stanford; Auditory Lab, McGill. I have obtained my PhD "Profiles of Pitch Classes" at the Neural Information Processing Group (CS/EE) at Berlin University of Technology, receiving a scholarship from the Studienstiftung des deutschen Volkes. Before that, I studied mathematics at Bonn and Muenster University, completing a diploma in pure mathematics. Starting with playing the violin at age of 7, and studying also musicology and acting on the side I also have experience as a performer in concerts and theatre. I have (co-)authored 70 scientific papers. My interests include deep learning and reinforcement learning for music and sound analysis, game strategies and robotics, statistical models for music/ sound representation/expectation/generation, neural correlates of music and 3D (tele)vision, didactic tools for music and dance, and predictive maintenance in manufacturing.

More from the Same Authors