Stefan Lattner

We are usually unaware of the enormous computing power needed by our brain when listening to music. When trying to make sense of music, we constantly have to classify, sort, remember, structure, and connect a vast number of musical events. Moreover, these events do not only consist of notes, chords, and rhythms but are also characterized by "colors of sound." These ever-changing frequencies, resulting in complex soundscapes, are at the heart of our musical experiences. I use computer models to simulate the cognitive processes involved when listening to music, to create better tools for music production and music analysis. Creating compositions, musical arrangements, and unique sounds using machine learning and artificial intelligence will lead to a streamlined music production workflow and to entirely different ways to engage with music as a whole.

[Keywords]
Music Generation / Musical Structure / Computational Creativity / Neural Networks

Activities

More

Selected Publications

Lattner, S., Grachten, M., and Widmer, G. (2018b). Learning transposition- invariant interval features from symbolic music and audio. In Proceedings of the 19th International Society for Music Information Retrieval Conference, ISMIR 2018, Paris, France, September 23-27

Lattner, S., Grachten, M., and Widmer, G. (2018c). A predictive model for music based on learned relative pitch representations. In Proceedings of the 19th International Society for Music Information Retrieval Conference, ISMIR 2018, Paris, France, September 23-27

Lattner, S., Grachten, M., and Widmer, G. (2018a). Imposing higher-level structure in polyphonic music generation using convolutional restricted Boltzmann machines and constraints. Journal of Creative Music Systems, 3(1)

Lattner, S., Grachten, M., Agres, K., and Chacón, C. E. C. (2015b). Probabilistic segmentation of musical sequences using restricted Boltzmann machines. In Proceedings of the 5th International Conference on Mathematics and Computation in Music, MCM 2015, London, UK, June 22-25, 2015

Profile

In my study on media technology and design in Hagenberg, Austria, I learned a lot about sound engineering and audio mixing. I graduated from the Institute of Computational Perception at the Johannes Kepler University in Linz, Austria, where a strong focus was placed on machine learning. During my masters, I worked at a startup -- re-compose -- as a developer and project manager, where we developed Liquid Notes, an intelligent music software. At the Austrian Research Institute for Artificial Intelligence, Vienna, I worked in an EU project (lrn2cre8) where we studied computational creativity in music. My focus in that project was to mitigate the problem of structure learning in NNs. Since April 2018, I am applying my experience in music (generation), audio production and deep learning in Sony CSL, Paris.

Go to top