PhD Studentship in machine learning applied to sound synthesis and media content creation

Queen Mary, University of London - School of Electronic Engineering and Computer Science

Applications are invited from all nationalities for a funded PhD Studentship starting January 2015 within the Centre for Digital Music (C4DM) at Queen Mary University of London, to perform cutting-edge research in machine learning applied to sound synthesis and media content creation.

In this PhD project, the concept of an Intelligent Assistant is investigated as a means of short form media content creation. A small high-tech company are in the process of creating a collaborative cloud platform for the creation of short form media, such as advertisements, promotional videos, local information etc. The Intelligent Assistant would identify and organise the content, add effects and synthesised sounds where necessary and present the produced content as a coherent story. It will be used as a tool by content creators to assist in quick and intuitive content creation. The goal of this project is to create and assess such tools, focusing on the challenges of varied, user-generated content with limited metadata, and the need for an enhanced user experience. 
Research questions to be investigated include;
- How best can sounds be synthesised in order to provide additional audio content to enhance the production?
- Can multimedia (especially audio) content be intelligently combined to effectively tell a story? 
- How can this be assessed and evaluated? What are the key factors, features and metrics for intelligent storyboard systems? 
This project is expected to generate high impact results, especially in the growing research fields of signal processing, sound synthesis, music informatics and semantic tools for content creation and production. 

There is scope to tailor the project to the interests and skills of the successful candidate.

Candidates should have a first class honours degree or equivalent and/or a strong MSc degree in computer science, mathematics, physics or engineering, or equivalent experience. Good programming skills are essential, as is a passion for sound and/or nature. Knowledge of machine learning, digital signal processing or audio production is desirable, but not essential if the candidate otherwise demonstrates good technical/mathematical skills.

The candidate will be supervised by Dr Josh Reiss, and will join a group of around 60 full-time PhD students, post-doctoral researchers and academics in the Centre for Digital Music (http://c4dm.eecs.qmul.ac.uk/). The candidate will also interact often with the company supporting the project, and with other researchers working on related projects.

Informal enquiries can be made by email to Dr. Josh Reiss: joshua.reiss<στο>qmul.ac.uk

This studentship is available to candidates of all nationalities. It is funded by the university for 3 years and will cover student fees and a tax-free stipend starting at £15,863 per annum.

To apply, please follow the online process (www.qmul.ac.uk/postgraduate/apply) by selecting 'Electronic Engineering' in the 'A-Z list of research opportunities' and following the instructions on the right-hand side of the web page. Make sure to state in your application that you are applying for the PhD with Dr Josh Reiss.

Please note that instead of the 'Research Proposal' we request a 'Statement of Research Interests'. Your statement should answer two questions: (i) Why are you interested in the topic? (ii) What relevant experience do you have? Your statement should be brief: no more than 500 words or one side of A4 paper. In addition we would also like you to send a sample of your written work. This might be a chapter of your final year dissertation, or a published conference or journal paper.

More details can be found at: www.eecs.qmul.ac.uk/phd/apply.php

Interviews are expected to take place during the week of 5th January 2015.

Apply