£6,000 PhD Scholarship | APPLY NOW £6,000 PhD Scholarship | APPLY NOW

Neuro-symbolic modelling of music

   Department of Computer Science

  Dr Robert Lieck, Dr Eamonn Bell  Applications accepted all year round  Funded PhD Project (Students Worldwide)

About the Project

About the Project

This funded PhD position is about developing novel algorithmic tools for music analysis using deep learning and structured/symbolic methods. It will combine approaches from computational musicology, image analysis, and natural language processing to advance the state of the art in the field.

Music analysis is a highly challenging task for which artificial intelligence (AI) and machine learning (ML) is lagging far behind the capabilities of human experts. Solving it requires a combination of two different model types: (1) neural networks and deep learning techniques to extract features from the input data and (2) structured graphical models and artificial grammars to represent the complex dependencies in a musical piece. The central goal of the project is to leverage the synergies from combining these techniques to build models that achieve human-expert level performance in analysing the structure of a musical piece.

You will get:

-      the chance to do your PhD at a world-class university and conduct groundbreaking research in machine learning and artificial intelligence

-      the opportunity to work on an interdisciplinary project with real-world applications in the field of music

-      committed supervision and comprehensive training (regular one-on-one meetings, ample time for discussion, detailed feedback, support in your scientific development, e.g., presentation skills, research methodology, scientific writing etc.)

-      a stimulating, diverse, and supportive research environment (as member of the interdisciplinary AIHS group)

-      the opportunity to publish in top journals, attend international conferences, and build a network of collaborations

You should bring:

-      enthusiasm for interdisciplinary research in artificial intelligence and music

-      an open mind-set and creative problem-solving skills

-      a solution-oriented can-do mentality

-      a desire to understand the structure of music and its inner workings

-      a good command of a modern programming language (preferably Python) and familiarity with a modern deep learning framework (e.g. PyTorch)

-      a strong master degree (or equivalent) with a significant mathematical or computational component

Related Research

The project will build on latest results on combining symbolic and continuous models

●    Lieck, R. & Rohrmeier, M. Recursive Bayesian Networks: Generalising and Unifying Probabilistic Context-Free Grammars and Dynamic Bayesian Networks. in Advances in Neural Information Processing Systems 34 (NeurIPS) (2021).

Deep learning techniques for computational musicology

●    Hawthorne, C., Simon, I., Swavely, R., Manilow, E. & Engel, J. H. Sequence-to-Sequence Piano Transcription with Transformers. in Proceedings of the 22nd International Society for Music Information Retrieval Conference, ISMIR 2021, Online, November 7-12, 2021 (eds. Lee, J. H. et al.) 246–253 (2021).

●    McLeod, A. P. & Rohrmeier, M. A. A modular system for the harmonic analysis of musical scores using a large vocabulary. in International Society for Music Information Retrieval Conference, ISMIR, 435–442 (2021).

Neuro-symbolic approaches from natural language processing

●    Kim, Y., Dyer, C. & Rush, A. Compound Probabilistic Context-Free Grammars for Grammar Induction. in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics 2369–2385 (Association for Computational Linguistics, 2019). doi:10.18653/v1/P19-1228.

●    Zhang, Y., Zhou, H. & Li, Z. Fast and accurate neural CRF constituency parsing. in Proceedings of IJCAI 4046–4053 (2020). doi:10.24963/ijcai.2020/560.

Natural scene analysis

●    Wang, G., Wang, G., Wang, K., Liang, X. & Lin, L. Grammatically Recognizing Images with Tree Convolution. in Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 903–912 (2020). doi:10.1145/3394486.3403133.

Research Environment


The candidate will be jointly supervised by Dr Robert Lieck and Dr Eamonn Bell, both Assistant Professors in Computer Science at Durham University. Robert Lieck is an expert in machine learning and probabilistic modelling with a research focus on computational musicology and modelling musical structure. Eamonn Bell is a music theorist and an expert in mathematical and computational techniques applied to musicology and music theory.

The candidate will receive comprehensive training in all relevant areas through regular one-to-one meetings. Moreover, they will be part of the interdisciplinary AIHS group with a stimulating, diverse, and supportive research environment. They will benefit from a generous research and travel allowance and are encouraged to develop internationally significant research published in leading conferences and journals. Beyond the Department of Computer Science, there will be opportunities for interdisciplinary collaborations with the UK’s top-ranked Department of Music and international partners.

Durham University

The position is based at Durham University, which is ranked 5th in the UK (Guardian University Guide 2022) and among the top 100 universities in the world (QS World University Rankings 2022). As a member of the elite Russell Group, Durham University focuses on research excellence delivered by world-class academics. It is located in the beautiful city of Durham in North East England with a vibrant student community and an affordable living cost. Durham benefits from high-speed rail connections to Edinburgh and London, as well as convenient air links from Newcastle and Tees Valley Airport. The Department of Computer Science is one of the fastest-growing departments in the University, supported by major investments in staff recruitment and a brand new £40m academic building. 90% of its research outputs are considered “world-leading” or “internationally excellent” by the UK Research Excellence Framework (REF 2021).


This PhD position is funded for 3.5 years under the EPSRC Doctoral Training Partnership scheme, hosted at Durham University. This includes a stipend and covers home tuition fees.

How to apply

Please send an email with your CV and a short informal motivation to Dr Robert Lieck for initial discussions. We are looking to fill this position as soon as possible (the position is still open as long as it is advertised). The preferred start date is October 2022 (new academic year).

Funding Notes

This PhD position is funded for 3.5 years under the EPSRC Doctoral Training Partnership scheme, hosted at Durham University. This includes a stipend and covers home tuition fees.
Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs