Call for PhD applications at the Machine Listening Lab – 2027 entry

The Machine Listening Lab of Queen Mary University of London is inviting applications for PhD study for Autumn 2027 start across various funding schemes. Below is a suggested PhD topic offered; interested applicants can apply for a PhD under this topic, or can propose their own topic. In all cases, prospective applicants are strongly encouraged to contact lab academics to informally discuss prospective research topics.

Opportunities include internally and externally funded positions for PhD projects to start in Autumn 2027. It is also possible to apply as a self-funded student or with funding from another source. Applicants can apply for a 3-year PhD degree in Computer Science or Electronic Engineering. Studentship opportunities include:

• CSC PhD Studentships in Electronic Engineering and Computer Science (Autumn 2027 start, Chinese applicants)
• International PhD Funding Schemes (Autumn 2027 start, numerous international funding agencies)

Multimodal AI for music understanding

Supervisor: Emmanouil Benetos

The field of music information retrieval (MIR) has historically focused on audio and machine-readable scores as its core representations and modalities under investigation. However, music as an art form is inherently multimodal: ways to capture music performances and music compositions include but are not limited to video, images (from music scores to album art), lyrics and text descriptions in addition to audio. This PhD project will investigate and propose new methods from the field of Multimodal AI towards creating and evaluating multimodal foundation models for music understanding. Part of the project will involve data collection towards a multimodal MIR corpus, as well as benchmarking existing models and methods against multimodal MIR tasks. The successful candidate will investigate, propose and develop novel machine learning methods for MIR across multiple modalities, resulting in models that can accelerate and broaden MIR research but also advance the broader field of Multimodal AI.