Thesis supervisor: Géza Németh
Location of studies (in Hungarian): Department of Telecommunications and Media Informatics Abbreviation of location of studies: TMIT
Description of the research topic:
Artificial intelligence has already reached several applications. There has been significant progress in various component fields (e.g. image and object recognition, natural language processing, speech processing, etc.).There are also remaining challenges at these levels (e.g noisy conditions, limited training data, explainability, etc.). But there are even higher levels of challenges at the system level: how the components influence each other’s performance and the overall acceptance of the whole system,
The task of the PhD candidate is to review the literature of the objective and subjective, low and high level parameters that determine to characteristics of human computer interaction systems. Based on these studies the candidate shall define, implement and evaluate algorithms applicable in new human computer interaction systems.
Research tasks:
- Review of the literature related to artifical intelligence based human computer interaction systems
- Analysis of performance evaluation methodologies at component and system levels
- Design and implement baseline and state-of-the-art algorithms for benchmarking
- Definition, implementation and evaluation of improved algorithms
- Contribution in the creation and evaluation of application scenarios.
Related cooperations:
- AI4EU H2020 project
- APH-ALARM AAL project
Required language skills: English Number of students who can be accepted: 2