Applications are invited for a nine-month postdoctoral research fellow position, starting on Monday, June 29, 2020, or as soon as after. This post is an EPSRC Impact Acceleration Account-funded project “Audio Tagging for Meta Data Generation of Media for Programme Recommendation”. The project is led by Prof Wenwu Wang in the Machine Audition Lab of the Centre for Vision Speech and Signal Processing (CVSSP) at the University of Surrey.
The aim of the project is to apply the audio tagging methods developed as part of the EPSRC project “Making Sense of Sounds” to support programme recommendations for major BBC services, including iPlayer and Sounds. The project will focus on applying the audio tagging algorithms to broadcast content, and tuning the algorithms to extract metadata that is most relevant to the context of recommendation. We will leverage the deep learning algorithms for audio tagging recently developed at CVSSP, and BBC’s data (e.g. a digital archive of TV programs and radio broadcasts), and develop a proof of concept software to demonstrate the potential of using the audio tagging algorithms for metadata generation in programme recommendation.
The postholder will be responsible for investigating and developing advanced machine learning methods for tagging of sound data provided by BBC. The postholder will be based in CVSSP and work under the direction of PI Prof Wenwu Wang and Co-Investigator Prof Mark Plumbley. The postholder is expected to have expertise and experience in the area of advanced machine learning (such as deep learning) and audio signal processing. He should be familiar with the state of the art deep learning models and software tools, and is capable in Python, C/C++, and/or Matlab programming.
CVSSP is one of the largest groups of its type in the UK, with over 180 active researchers working in the areas of vision, image processing, medical imaging, and audio, and a grant portfolio of over £12M. The Centre has state-of-the-art acoustic capture and analysis facilities enabling research into audio signal processing, music transcription and spatial audio, and a Visual Media Lab with video and audio capture facilities supporting research in real-time video and audio processing and visualisation. It has an extensive computing infrastructure for audio-visual processing and storage, comprised over 1,000 processing cores and a recent university investment of 500TB of fast, object based storage.
For informal inquiries about the position, please contact Prof Wenwu Wang (email@example.com) or Prof Mark Plumbley (firstname.lastname@example.org).