Supervisory Team: Indu Bodala; Stuart Middleton; Tim Norman
Robots have the potential of becoming companions that can assist and collaborate with people in everyday tasks. The embodied multimodal interaction capabilities based on gestures, speech, vision and affect/emotion exhibited by the robot companions can better engage users physically and socially compared to digital interfaces such as mobile phones and computers. In most of the cases, the interaction behaviours exhibited by the robots are coded manually or automated to limited extents e.g., using scripted dialogues or teleoperated gestures. Further, there is also a need to investigate techniques to synchronize the behaviours exhibited across multiple modalities to suit various interaction contexts, e.g., the gestures of the robot need to suit its speech and emotional context of the conversation.
The aim of the project is to develop unified computational frameworks to generate multimodal behaviours for interactions that are context-dependent and can be personalized to suit user preferences such as user personality, interaction styles, etc. You will explore the use of the existing state-of-the-art conversational dialogue systems, computer vision, text-to-speech and emotion recognition modules to design novel interaction frameworks. These frameworks will look at bidirectional modelling of human-robot interactions where the robot can understand the content and context of the users’ speech and gestures and can respond through appropriate speech and affective behaviours. You will have access to specialist equipment and laboratories within the school such as HPC clusters and anthropomorphic and zoomorphic robots with integrated vision, audio and text-to-speech modules for the development and testing of relevant methodologies. The project will encompass various exciting topics in Computer Science such as Deep Learning, Human-Robot Interaction, Natural Language Processing and Affective Computing. You will be supervised by leading researchers in their field and join an exceptional and vibrant team of postdoctoral researchers and other PhD students.
Successful candidates would have a strong background in Computer Science, Engineering, Maths or Physics and preference would be given to those with good understanding of Deep Learning models and Signal Processing. You will join the School of Electronics and Computer Science which is ranked 1st in the UK for Electrical and Electronic Engineering (Guardian University Guide 2022) within the University of Southampton which is ranked in the top 1% of universities worldwide. We will also support the development of your future career and give you opportunities including teaching assistantships, professional networking via leading organizations such as Alan Turing Institute and UKRI TAS Hub, access to Future Worlds to explore commercialization for your research.
A very good undergraduate degree (at least a UK 2:1 honours degree, or its international equivalent).
Closing date: applications should be received no later than 31st August 2022 for standard admissions, but later applications may be considered depending on the funds remaining in place.
Funding: Tuition Fees and a stipend (UK only) of £16,062 tax-free per annum for up to 3.5 years.
How To Apply
Apply online: https://www.southampton.ac.uk/courses/how-to-apply/postgraduate-applications.page. Select programme type (Research), 2022/23, Faculty of Physical Sciences and Engineering, next page select “PhD Computer Science (Full time)”. In Section 2 of the application form you should insert the name of the supervisor Indu Bodala.
Applications should include:
Two reference letters
Degree Transcripts to date
For further information please contact: [Email Address Removed]