workshop01
Audio Source Separation and NNabla

In a first part, we will introduce Sony's audio source separation technology and show that many different use cases can be solved with the same tool, which makes it very powerful. In a second part, we will discuss Open-Unmix - an open-source implementation of audio separation - and reveal upcoming features of it. Finally, we will talk about NNabla, Sony's deep learning framework and highlight features which makes NNabla attractive not only for research and development but also for production use cases.

• 

  Stefan Uhlich

  Sony R&D Center Stuttgart Lab.１

  Stefan Uhlich received the Dipl.-Ing. and PhD degree in electrical engineering from the University of Stuttgart, Germany, in 2006 and 2012, respectively. From 2007 to 2011 he was a research assistant at the Chair of System Theory and Signal Processing, University of Stuttgart. In this time he worked in the area of statistical signal processing, focusing especially on parameter estimation theory and methods. Since 2011, he is with the Sony Stuttgart Technology Center where he works as a Principal Engineer on problems in music source separation, speech enhancement and deep neural network compactization.

＞　Audio source separation

workshop02
The Sound of AI - How Machine Learning Impacts Music Production

New technologies always have the potential to transform the way music is created. AI is a powerful new paradigm and, as such, establishes its place also in the creative workflows of music production. In this talk, we present current solutions of AI-assisted music production and discuss the potentials and challenges, as well as unanswered questions in this paradigm. We also present our research activities at Sony CSL, including some brief details about the underlying machine learning models. For creating relevant tools, we rely on close collaboration with music producers, which can be a challenge on its own. We talk about the gap between the scientific approach and that of artists and the music industry, and we address our efforts to bridge that gap.

• 

  Stefan Lattner

  Sony CSL Paris

  Stefan Lattner is a research associate at Sony CSL Paris, where he works on transformation and invariance learning with artificial neural networks. Using this paradigm, he targets rhythm generation (i.e., DrumNet) and is also involved in music information retrieval, audio generation, and recommendation. He obtained his doctorate in the area of music structure modeling from the Johannes Kepler University in Linz, Austria.

• 

  Cyran Aouameur

  Sony CSL Paris

  Cyran Aouameur is an assistant researcher at Sony CSL. Graduated from Ircam-organized ATIAM Master's degree, he entered CSL two years ago. Passionate about urban music since he was a child, he has been focusing on developing AI-based solutions for artists to quickly design unique drum sounds and rhythms, which he considers being top-importance elements. He is now partly responsible for the communication with the artists, seeking to get the research and the music industry worlds to understand each other.