PhD Student Position in Computing Science with a focus on digital signal processing for computer music - Befattningen är under tillsättning eller redan tillsatt, och det är inte längre möjligt att lämna in en ansökan

PhD Student Position in Computing Science with a Focus on Digital

Signal Processing for Computer Music

The Department of Computing Science at Umeå University is seeking a candidate for a fully funded position as Ph.D. student to work on the topic "digital signal processing for computer music" for a project aimed at the development of algorithms and code for a fully automated dj-mixing system. The application deadline is October 10th, 2019.

About the position

The doctoral student’s main task is to devote herself/himself to her/his postgraduate education, which includes participation in research projects and postgraduate courses for a total study time of 48 months. In addition, teaching and other work at the department (up to a maximum of 20% of full time) can be included in the duties. If so, the employment as a PhD student will be prolonged accordingly.

Project description

Continuous, "mixed", dance music has animated clubs since the end of the 1970s, when DJs began to overlap successive songs, creating an uninterrupted stream of music, also known as a "dj mix". Since then, continuous mixes conquered other public spaces such as private parties, shops & malls, gyms, radio broadcasts and even on-flight entertainment. Due to such a widespread appeal, the generation of high-quality dj mixes is very much on demand, and many companies, including Spotify and iTunes, offer the feature of playing uninterrupted sequences of songs.However, this is usually accomplished by overlapping the end of the current song with the beginning of the next one, with results that are not competitive with human-generated mixes.

The objective of this project is the generation of an uninterrupted sequence of songs with seamless transitions, automating all the steps that a Dj performs when mixing in a live setting. Specifically, we aim at real-time algorithms that use digital signal processing and high-performance techniques to 1) select the next song, 2) tempo adjust it, 3) beat align it, 4) segment it, 5) overlap it with the current one in agreement to its musical structure, and 6) perform a crossover. All of these tasks have to be completed while the current track is playing, that is, in real time.

The project consists in:

- definition of rules, based on music theory, for the creation of seamless transitions of songs

- generation of playlists through a recommender-like system

- analysis of individual tracks through Music Information Retrieval (MIR) tasks

- automation of the entire workflow

- blind testing

Requirements and qualifications

To be admitted for studies at the third-cycle level, the applicant is required to have completed a second-cycle level degree, or completed course requirements of at least 240 ECTS credits, of which at least 60 ECTS credits are at second-cycle level in Computing Science or of direct relevance for the project described above. The entry requirements can also be fulfilled by equivalent qualifications gained in another educational system or as a result of work experience. The applicant needs to have very good knowledge of digital signal processing, music information retrieval, and experience in data processing (recommender systems, deep learning, NoSQL or relationaldatabases). With respect to programming, the candidate is expected to have good knowledge of Python, Data Science frameworks (such as numpy, pandas, scikit-learn), as well as audio and music signal processing frameworks (madmom, essentia). The research will be carried out in collaboration with international researchers from different disciplines, so good collaborative skills are required, and the applicant must be able to speak and write English fluently.

The most important assessment criteria for the selection are scientific expertise and skills, suitability for the project, and documented ability to both work in groups and to independently carry out work tasks.

Application

The application must be written in English and must include the following:

• A cover letter that motivates your interest in the position and that describes how your qualifications and experience are relevant to the employment (maximum 2 A4 pages with 11pt font). Please include a discussion of your experience in the development of high-quality audio/music software.

• Curriculum vitae

• Certified copies of completed academic courses and grades and diploma

• Copies of master thesis and any other relevant scientific publications

• Contact information of at least two references(no reference letters!)

Please observe that all material needs to be in English. If any material is submitted in another language, a translation must be included.

As we strive for a more balanced gender distribution within the department, we specifically encourage female candidates to apply for the position.

The application must be submitted through the e-recruitment system no later than October 10th, 2019. Reference number AN 2.2.1-1263-19.

According to the Higher Education Ordinance (chapter 12, 2§) the hiring decision cannot be appealed.

For more information, contact Prof. Paolo Bientinesi: pauldj@cs.umu.se

Welcome with your application!

About the department and research environment

The Department of Computing Science at Umeå University is a dynamic environment with around 100 employees representing more than 20 countries worldwide. We conduct education and research on a broad range of topics in Computing Science. The department's research is internationally well-established and includes basic research, method development and program development, but also research and development in various application areas. Information about the department's postgraduate education can be found on our website http://www.cs.umu.se/forskning/