<aside> 🚧

Last Update: 20:00 (GMT+8) Sun 15th Nov

</aside>

<aside> 🎖️

Two PhD studentships remain open. The application deadline is December 4, 2026 (AoE).

</aside>

Calling for PhD Students

Xi'an Jiaotong-Liverpool University (XJTLU), located in Suzhou, China, has two PhD studentships still open in machine listening and audio processing. The projects are Reverse Engineering for Generative Audio Signals (FOSLG251002) and Audio Repair and Recovery via Audio Recognition Techniques (PGRSLG251001). Detailed description of the projects can be found at the bottom of THIS PAGE.

Successful candidates will be supervised by Dr. Shengchen Li as principal supervisor. Dr. Jacopo de Berardinis (University of Liverpool) is the University of Liverpool co-supervisor for both projects. Prof. Qiufeng Wang (XJTLU) co-supervises Reverse Engineering for Generative Audio Signals. Prof. Eng Gee Lim (XJTLU) co-supervises Audio Repair and Recovery via Audio Recognition Techniques. Prof. Mark D. Plumbley (IEEE Fellow, King's College London) is the external supervisor for both projects. Upon graduation, the candidate will be awarded a degree of PhD via University of Liverpool.

FOSLG251002 is a fee-waiver studentship: it covers tuition fees, with potential living-cost support while in China. PGRSLG251001 is the other remaining studentship; the award is the studentship attached to that project code. Both projects are listed on the XJTLU postgraduate research scholarship page.

All applicants should have (or expect to obtain) a first-class/upper-second-class degree in a numerate discipline (mathematics, science or engineering) or MSc with Distinction/Merit (or GPA equivalent 3.0) and a strong interest in pursuing research in this field. Additional experience which is relevant to the area of research is also advantageous.Non-native English speakers who did not graduate from an English-speaking country in the past two years must achieve an IELTS score of 6.5 (with a minimum of 5.5 in each component).

Prospective students should prepare the following materials and complete the application form (at the end of this page). In the case of the form does not display as expected, you could click PhD Application Form.

The application deadline is December 4, 2026 (AoE). Interview arrangements will follow the deadline, subject to further notification. For inquiries about these positions, please contact Dr. Shengchen Li ([email protected]).

Projects

Audio Repair and Recovery via Audio Recognition Techniques

<aside> 1️⃣

PGRSLG251001. Supervised by Shengchen Li, Jacopo de Berardinis, Eng Gee Lim, Mark D. Plumbley

</aside>

This research project addresses the critical challenge of repairing and recovering degraded audio signals through advanced machine listening techniques. The proposed approach focuses on recognising semantic relationships between audio objects to intelligently reconstruct missing or corrupted audio segments. By leveraging deep learning models that understand the context and meaning of audio content, we aim to develop algorithms capable of identifying the semantic structure within audio recordings and using this understanding to guide the restoration process. This innovative method will significantly improve upon traditional signal processing approaches by incorporating semantic knowledge, enabling more natural and contextually appropriate audio repair for applications in archival preservation, telecommunications, and multimedia production.

Reverse Engineering for Generative Audio Signals