Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  Human emotion analysis and recognition for improving trusted human-robot interaction. Main project focus: AI and Robotics


   School of Science, Engineering and Environment

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
  Prof Mary He, Prof Trevor Cox, Dr Salem Ameen, Prof Wei Yao  Applications accepted all year round  Self-Funded PhD Students Only

About the Project

Information on this PhD research area can be found further down this page under the details about the Widening Participation Scholarship given immediately below.

Applications for this PhD research are welcomed from anyone worldwide but there is an opportunity for UK candidates (or eligible for UK fees) to apply for a widening participation scholarship.

Widening Participation Scholarship: Any UK candidates (or eligible for UK fees) is invited to apply. Our scholarships seek to increase participation from groups currently under-represented within research. A priority will be given to students that meet the widening participation criteria and to graduates of the University of Salford. For more information about widening participation, follow this link: https://www.salford.ac.uk/postgraduate-research/fees. [Scroll down the page until you reach the heading “PhD widening participation scholarships”.] Please note: All candidates who wish to apply for the MPhil or PhD widening participation scholarship will first need to apply for and be accepted onto a research degree programme. As long as you have submitted your completed application for September/October 2024 intake by 28 February 2024 and you qualify for UK fees, you will be sent a very short scholarship application. This form must be returned by 28 March 2024. Applications received after this date must either wait until the next round or opt for the self-funded PhD route.

-----------------

Project description: Applications are accepted until appropriate candidates are recruited.                                           

Trusted human-robot interaction (HRI) is a challenge for human-centric artificial intelligence. HRI requires harmonious collaboration between interdisciplinary domains. It involves modelling human behaviour and reasoning to improve robot recognition, knowledge acquisition, representation, and manipulation at the human level of reasoning and decision making, and ultimately to enable physical actions that are legible to and coordinated with humans [1] To enable intuitive, genuine, and natural interaction with humans, emotional intelligence is important in robots [2] Emotion recognition has been widely researched in the fields of human-machine interaction and affective computing. Emotional intelligence is especially crucial for service robots; much research has been done in the field of emotion recognition.

Emotion intelligence in robots refers to their ability to perceive, understand, and respond to human emotions. Several disciplines are involved in the study of emotion intelligence in robots, such as advances in AI, computer vision, natural language processing, cognitive science, psychology, human-robot interaction (HRI). These enable robots to recognise facial expressions, body language, tone of voice, and other cues of human emotion. Emotionally intelligent robots can adapt their behaviour and communication to better interact with humans, improving their overall usability and user experience. Although progress has been made in this area, achieving true emotional intelligence in robots that is similar to humans remains a significant challenge. In particular, there is still a large space in the improvement of the recognition rate. Two key challenges in robotic emotional intelligence are: (1) Accuracy of emotion recognition: developing AI algorithms that accurately perceive and interpret human emotions based on various cues such as facial expressions, body language, and tone of voice. Variability in individual expression, cultural differences, and context-dependent emotions make this task complex. (2) Contextual understanding: robots must understand the context in which emotions are expressed in order to respond appropriately. Interpreting emotions within specific situations, social norms, and cultural nuances is still a challenge for robotic systems.

To improve emotional intelligence of robots, this PhD programme will address the two challenges above on improving the robot's cognitive abilities to analyse and recognise human emotions under different scenarios, so that it can infer and interpret human emotions. In various emotion reflections, the expression and mimic of the face and the tone and pitch of the voice are much more obvious and externally accessible than others [3]. Recently, there is an increasing attention on the research of the emotional content of speech signals [4]. Therefore, the aim of the PhD programme is to train PhD candidates to have capacity for developing advanced technologies for automatic emotion recognition based on various data sources using state-of-the-art AI technologies, focusing on two tasks:

(1) Human-facial emotion analysis and recognition, addressing the challenges due to individual differences, cultural variations, occlusions, lighting conditions, and subjectivity in interpreting expressions.

(2) Human-voice emotion analysis and recognition, addressing the challenges due to the variability in individual voice characteristics, language-specific nuances, the influence of background noise, and the subjectivity in interpreting emotions from voice alone.

For this programme, TWO PhD students will be recruited. One PhD student will focus on human-facial emotion analysis and recognition and the other on human-voice emotion analysis and recognition.

Applications from domestic/international students are welcome. We are looking for highly motivated candidates who are passionate about human-robot interaction and artificial intelligence and are able to develop advanced technologies to address the challenges in the field of robotic emotional intelligence to develop their future research profile in the relevant areas. Applicants should have a Bachelor's degree (2:1 and above) and/or a Master's degree in Computer Science, Robotics, AI, Data Science or a related STEM discipline and interested in psychological emotion analysis. Applicants with equivalent industry experience may also apply. The study offers candidates the opportunity to participate in various trainings to enhance their research skills and requires candidates to disseminate their research findings at conferences and/or in peer-reviewed journals. Applicants must have good interpersonal and communication skills in oral and written English. If English is not your native language, you must have an IELTS average of 6.5 or higher with a minimum of 6.0 in each component or equivalent. The programme is a three-year PhD research programme.

Applicants must submit a proposal to specify one of the two research tasks. Successful applicants will work with the supervisors to define the objectives, deliverables, and timeline.

The supervisory team consists of experts from the Centre for Autonomous Systems and Robotics and the Acoustics Research Centre in the School of Science, Engineering and  Environment (SSEE), you will join the Doctoral School at the University of Salford.

After receiving your application with two reference letters, you could be offered an interview for further selection.

Computer Science (8) Engineering (12) Mathematics (25)

References

[1] H. He, et al. The Challenges and Opportunities of Human-Centred Artificial Intelligence for Trustworthy Robots and Autonomous Systems, IEEE Transactions on Cognitive and Developmental Systems, 14(4), Dec. 2022, pp. 1398 - 141202. DOI: 10.1109/TCDS.2021.3132282.
[2] Emotion Recognition for Human-Robot Interaction: Recent Advances and Future Perspectives, Front. Robot. AI, 21 December 2020 Sec. Smart Sensor Networks and Autonomy. 7, 2020, https://doi.org/10.3389/frobt.2020.532279.
[3] A. B. Gumelar et al., "Human Voice Emotion Identification Using Prosodic and Spectral Feature
Extraction Based on Deep Neural Networks," 2019 IEEE 7th International Conference on Serious Games and Applications for Health (SeGAH), Kyoto, Japan, 2019, pp. 1-8, doi: 10.1109/SeGAH.2019.8882461.
[4] M. E. Ayadi, M. S. Kamel, F. Karray, Survey on speech emotion recognition: Features, classification schemes, and databases, Pattern Recognition, 44(3), 2011, pp. 572-587, https://doi.org/10.1016/j.patcog.2010.09.020.
Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

 About the Project