You cannot apply for this job anymore (deadline was 4 Oct 2023).
Browse the current job offers or choose an item in the top navigation above.
Passionate about transforming pronunciation learning with voice AI?
AI-based speech diagnostics are used to analyse spoken audio in e-health to diagnose and monitor diseases, and in education, to evaluate and guide learning. However, current AI-based speech diagnosis has two shortcomings. First, it faces a capability gap as it lacks broad applicability. Second, it faces a responsibility gap as it puts users at risk by failing to prioritise privacy. The goal of this project is to develop responsible AI for speech diagnostics that will bridge both of these gaps.
In particular, this project develops interactive AI that diagnoses pronunciation issues and guides learners to improve pronunciation. The project will start undertaking the requirements for automatic pronunciation assessment (APA), which establishes the need for diverse types of speech in less controlled contexts. Currently, systems store detailed recordings and information from learners. This project will cross the responsibility gap by establishing the minimum amount of information that must be stored to support student learning, while maximising the ability of the human teacher to understand students' progress and special needs. Currently, such trade-offs are studied in session-based recommendation; the project will apply them to interactive speech-based AI.
Within this setting, the Faculty of Arts is looking for a PhD candidate in interactive speech-based AI for learning pronunciation. You will work in a multidisciplinary group consisting of PhD candidates, postdoctoral researchers and professors in different domains such as linguistics, language and speech technology, ASR, NLP, data privacy and responsible AI.
You will be responsible for 1) developing new approaches to data minimisation in the pronunciation learning setting, 2) designing and validating novel explainability techniques, and 3) designing and validating session-based pronunciation learning systems. You will be expected to publish your results in leading conferences and journals. The position may also include other duties such as supervision of Bachelor's and Master's students.
Fixed-term contract: You will be employed for an initial period of 18 months, after which your performance will be evaluated. If the evaluation is positive, the contract will be extended by 2.5 years (4 year contract) or 3.5 years (5 year contract).
The Faculty of Arts is committed to knowledge production with a significant scientific and social impact. With over 500 academic and support staff, we teach and conduct research in the fields of history and art, languages and cultures, and linguistics and communication, using innovative methodologies and working in close collaboration with each other. Our research is embedded in two research institutes: the Centre for Language Studies (CLS) and the Radboud Institute for Culture & History (RICH). We currently have approximately 2,500 students, enrolled in three departments: the Department of History, Art History and Classics, the Department of Modern Languages and Cultures, and the Department of Language and Communication. We aim to contribute to a more sustainable and inclusive world, which is why we especially seek applications from candidates who bring diverse perspectives, backgrounds and skills that will be assets to our study programmes and research profiles.
Context at Radboud University: Working on the NWO-funded research project 'Responsible AI for Voice Diagnostics' led by Dr Cristian Tejedor-García, you will be part of a new and proactive group of six PhD candidates and several postdoctoral researchers and professors, based at the Centre for Language Studies. The project leverages Radboud AI, Radboud's campus-overarching, interdisciplinary AI initiative, connecting the Faculty of Arts, Faculty of Science, Faculty of Social Sciences, and the Radboud university medical center. The project has links with the Radboud Healthy Data programme, the National AI Education Lab (NOLAI), the AI Hub East Netherlands through SME Datalab-East, relevant health-related Innovation Centres for Artificial Intelligence (ICAI) labs, and the European Laboratory for Learning and Intelligent Systems (ELLIS). The project addresses the challenges related to machine learning, natural language processing, data dependencies, quality and enrichment, the ethical dimensions of AI, and regulatory requirements for AI.
We maken het je graag makkelijk, log in voor deze en andere handige functies: