<aside> 🚧
Last Update: 20:27 (GMT+8) Wed 24th Dec
</aside>
Xi'an Jiaotong-Liverpool University (XJTLU), located in Suzhou, China, is offering four fully-funded PhD studentships in the exciting and rapidly growing field of machine listening and audio processing. Each project explores cutting-edge research areas including large audio models, audio enhancement, and trustworthy audio processing—providing students with the opportunity to work at the forefront of AI and audio technology. Detailed description of the projects can be found at the bottom of THIS PAGE.
Successful candidates will be supervised by an exceptional international team led by Dr. Shengchen Li as primary supervisor, while Prof. Eng Gee Lim (Dean of Artificial Intelligence) and Prof. Qiufeng Wang (Head of Department of Intelligent Science) at XJTLU provide additional senior mentorship. Dr. Jacopo de Berardinis and Dr. Guangliang Cheng from University of Liverpool serve as co-supervisors, alongside Prof. Mark D. Plumbley (IEEE Fellow) from King's College London as external supervisor. This world-class supervision panel ensures you'll benefit from diverse expertise and numerous opportunities for international exchange throughout your PhD journey. Upon graduation, the candidate will be awarded a degree of PhD via University of Liverpool.
We offer two types of studentships to provide different support with different flexibilities: two fee-waiver studentships that cover full tuition fees with potential living cost support while in China, and two full studentships that cover both tuition fees and a monthly maintenance allowance of 5,000 RMB in exchange for 200 hours of teaching assistance annually. Both options provide excellent financial support while you pursue groundbreaking research in a vibrant academic environment.
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 February 15th (AoE time). Interviews are scheduled for Thursday, February 26th subject to further notifications of interview. For inquiries about these positions, please contact Dr. Shengchen Li ([email protected]).
<aside> 1️⃣
Fee waiver; Supervised by Shengchen Li, Guangliang Cheng, Qiufeng Wang, Mark D. Plumbley
</aside>
This research focuses on developing robust techniques for identifying non-genuine audio content by analysing semantic inconsistencies in AI-generated, partially synthesised, or artificially combined audio. With the rapid advancement of generative audio technologies, distinguishing authentic from fabricated content has become increasingly challenging. The proposed methodology emphasises detecting linguistic anomalies, contextual misalignments, and semantic patterns that deviate from natural speech patterns. By focusing on content meaning and contextual coherence rather than purely acoustic characteristics, we aim to create detection frameworks that remain resilient against sophisticated generation techniques. This research will contribute critical verification tools for maintaining information integrity in the digital media landscape.
<aside> 2️⃣
Fee waiver; Supervised by Shengchen Li, Jacopo de Berardinis, Qiufeng Wang, Mark D. Plumbley
</aside>