Postdoc fellow on music generation with emotion - opening

Our team at Singapore University of Technology and Design (SUTD) is looking for a postdoc fellow in automatic music generation. You will be joining our team in music/audio/vision AI supervised by Prof. Dorien Herremans, Prof. Gemma Roig and Prof. Kat Agres. More information on the music/audio team here.

You will be working on a 3 year project called ''aiMuVi: AI Music generated from Videos", which focuses on automatically generating music by specifying the emotion/tension throughout the musical piece so that it matches the emotion content extracted from videos.

Required skillset:
- experience in Music Information Retrieval
- knowledgeable in deep neural networks
- interest in machine learning for midi/audio and vision
- interest/experience in music generation systems
- savy programmer with experience in MIDI/web architectures/NN
- creative problem solver
- strong academic writing skills
- PhD in computer science, MIR, neural networks, or related

The ideal candidate has experience working with music generation or a strong background in machine learning, with familiarity in sound and music computing, and is willing to work with our PhD students in the lab to leverage individual efforts into a combined system.

This is a three year project sponsored by MOE. We offer a competitive salary, with an initial 1 year contract, extendable for up to 3 years. Singapore is a vibrant city with a warm climate year-round. It is a technological hub in South East Asia, and English is the first language.

Please email your application, including your cv, 2-3 first author publications, and a reference letter, to dorien_herremans [ad] sutd.edu.sg with subject [application MOE postdoc]. Ideal start date is July 1st.

We encourage traditionally underrepresented groups, such as minorities and women, to apply.