Applications are invited for a Research Fellow in Source Separation for Musical Audio Repurposing to work full-time on an EPSRC funded project “Musical Audio Repurposing using Source Separation” from 1 February 2018 to 31 July 2018. This project is tackling the challenge of high quality musical audio repurposing, focussing on soloing, desoloing, remixing and upmixing. The project is investigating new methods for musical audio source separation, in parallel with investigating new perceptual evaluation measures for audio source separation.

The candidate will be responsible for investigating and developing new and enhanced methods for high quality musical audio source separation. These may include methods based on deep learning, score-informed musical source separation, non-negative matrix factorisation (NMF), and interactive methods employing user feedback. The candidate will be working as part of a team, with other researchers focussing on perceptual evaluation methods and software development of open-source research tools.

See further details at the link below.