Dr Modrzejewski looks for answers to questions from the area of music information retrieval. He researches, among other things, whether AI algorithms could replace a conductor, what the chances are of instruments learning to play on their own, and what the differences would be between machine- and human-written music.

– In my research I combine my two greatest passions: music and issues relating to deep neural networks, which form the basis of machine learning and the use of artificial intelligence – explains Dr Mateusz Modrzejewski from the Division of Computer Graphics at the Faculty of Electronics and Information Technology. – As a jazz percussionist with vast performance experience, I know and understand the structure of music. As an engineer, I write it down not only as musical notes, but I also present it in a computer language. This is an excellent entry data collection for machine processing, analysis and composing music by AI algorithms.

A new outlook on music

Dr Modrzejewski’s research focuses around the use of deep neural networks, including GAN-type recurrent and generative networks, as well as state-of-the-art representations based on the transfer learning approach.

New methods are prepared with the use of large data sets in both audio and symbolic formats, such as MIDI (Musical Instrument Digital Interface). Once individual pieces are processed using AI algorithms, it is possible to generate original music that meets specific objectives and to accurately and precisely classify existing music according to given criteria, such as the identification of the singer, mood and instruments, or the recognition of a musical genre.

– Music is highly abstract communication, deeply rooted in human intelligence and sensitivity – Dr Modrzejewski points out. – In the case of generating music, we emphasise the compositional aspect – we code musical notes as expressive textural representations or in graphic form known as piano roll. Artificial intelligence becomes the ally of a human composer, providing new melodies, structures and solutions. We support human intelligence and creativity through AI techniques.

Things are slightly different when it comes to analysing music.

– Here, we use the techniques of digital signal processing and we investigate representations learned by deep neural networks – Modrzejewski explains. – These representations allow machines to organically understand the content contained in music – this also includes recommending new music to listeners, taking into account their personalised preferences.

Scientist and drummer

Dr Modrzejewski develops his original concepts under the wings of Prof. Przemysław Rokita in the Division of Computer Graphics at WUT’s Faculty of Electronics and Information Technology.

As a drummer, our scientist has played over 600 concerts with leading Polish artists. He has performed at many festivals and musical events in Poland, as well as in China, Vietnam, Germany, Scotland, England, Estonia, Ukraine and others. He has played for audiences as large as 150 thousand. In 2020 he was awarded the “Kultura w Sieci” grant by the Polish Minister of Culture and National Heritage. Last year, as a member of Majka Jeżowska’s band, he was nominated for the Fryderyk award for the “Live at Pol’and’ rock” album.

Would you like to hear Dr Modrzejweski play? Follow his Instagram profile.

You can find more information, as well as some of our scientist’s performances, on the Faculty of Electronics and Information Technology website.