Research Fellow in Generative Audio AI at the University of Surrey
Are you passionate about the potential of generative AI in the audio space? Do you want to contribute to cutting-edge research that could shape the future of AI for audio generation? If so, the University of Surrey has an exciting opportunity for you!
Position: Research Fellow in Generative Audio AI
The University of Surrey, UK, is inviting applications for a Research Fellow (RF) position within the Centre for Vision Speech and Signal Processing (CVSSP) and the Surrey Institute for People-Centred AI. This research role focuses on advancing generative AI methods for audio generation, including the creation of audio-related multimodal content, with particular emphasis on environmental sound generation.
This position is funded by the AI Hub in Generative Models (Gen AI Hub), which connects experts from academia and industry to make generative AI models more customisable, reliable, and trustworthy. This collaboration aims to bring generative AI technologies to new heights, benefiting society, science, and the economy.
Key Responsibilities
As a Research Fellow, you will lead research into generative AI and machine learning techniques for audio generation. Your work will include exploring the use of approaches such as diffusion models and flow matching for environmental sound generation, and integrating audio with other forms of media like text and video.
About You
The ideal candidate will hold a PhD (or equivalent) in a relevant field such as electronic engineering, computer science, applied mathematics, artificial intelligence, audio engineering, or a similar subject. You should have prior research experience in areas like:
- Audio signal processing
- Audio-related multimodal processing (such as audio with text or video)
- Audio deep learning
Experience in developing research algorithms and methods, with proficiency in languages like Python, C++, and MATLAB, will be essential. Familiarity with relevant signal processing, machine learning, or deep learning tools will be crucial for success in this role.
The Research Environment
CVSSP is an internationally recognized centre for excellence in audio-visual machine perception and AI research. With over 180 researchers, it provides access to cutting-edge facilities for audio and video capture, real-time processing, and visualization. Additionally, the centre is equipped with a compute facility featuring 200 GPUs and over 2PB of high-speed secure storage.
The Surrey Institute for People-Centred AI takes a multidisciplinary approach, combining expertise across audio-visual and signal processing, computer science, mathematics, engineering, physical sciences, and more. At the heart of the institute is the commitment to placing people at the core of AI research.
How to Apply
The application deadline for this position is 13 May 2025. For further details and application instructions, visit the official job posting: University of Surrey Job Listing.
For informal inquiries, you can contact Prof. Mark Plumbley at m.plumbley@surrey.ac.uk.
Don’t miss this opportunity to be part of groundbreaking research in generative audio AI!
