Researcher on MediSpeech (junior)

1. Introduction

Are you passionate about data science, speech technology, and healthcare innovation? Radboud University's Faculty of Arts offers a junior researcher position with a focus on speech recognition and NLP in the health domain. Come and join the MediSpeech project!

2. Job description

The MediSpeech project emerges as a critical intervention, harnessing the potential of automatic speech recognition (ASR) and large language models (LLMs) to mitigate administrative burdens. By automating the transcription of clinical conversations and integrating sophisticated AI technologies to process and understand medical dialogue, MediSpeech aims to revolutionise healthcare interactions. This initiative not only promises to streamline administrative workflows but also to refocus healthcare professionals' efforts on patient care, thereby enhancing the quality and timeliness of healthcare delivery. In Medispeech academia, hospital and companies will join forces.

Your main task will be to use language and speech technology such as automatic speech recognition (ASR) and natural language processing (NLP) to transcribe and linguistically enhance audiovisual recordings and texts deemed relevant for MediSpeech. The audio recordings will typically contain Dutch patient-doctor interactions from the nephrology domain. Together with our team of language and speech technology experts you will build tooling and workflows to structure speech and language data for inclusion in electronic health records.

3. Profile

• You hold a Master's degree in data science or language and speech technology (completed before the starting date of this position) or in another relevant discipline (e.g. computer science).
• You have proven expertise in a discipline within data science or language and speech technology (ASR & NLP), preferably health-related and linked to linguistics.
• You have experience in applying modern ASR technologies such as Wav2vec2.0 and Whisper.
• You know how to use transformers to finetune speech and language models.
• You can successfully interact with and establish links with other communication science and/or data science subdisciplines.
• You have demonstrable affinity for academic research, as evidenced by publications and/or presentations.
• You are proficient in English and preferably also in Dutch.
• Ideally, you have experience with the FAIRification of data (preferably health-related), GDPR aspects of research on sensitive data, knowledge of the potential and risks of advanced methods of AI-based data processing and application development, preferably related to language and speech technology, as evidenced by research projects, publications and/or teaching experience. You have a clear vision on ethical and privacy aspects in this particular context.
• Your responsibilities include optimising ASR and NLP performance for the MediSpeech use case through building workflows for audio data processing, reporting on your progress, presenting your findings at project meetings, and supporting the integration of workflow into the MediSpeech infrastructure.
• You have strong communication skills and the ability to work effectively with both technical and non-technical teams.

4. We are

You will work in a team with colleagues from the Healthy Data project, which also has the objective to unlock and structure audio and text data from the health domain, and with the RAIVD project team working on  the state of the art in health with respect to speech-based diagnosing and managing neurodegenerative disease (Alzheimer’s and Parkinson’s) and in education with respect to reading and pronunciation skills. 

5. We offer

• We will give you a temporary employment contract of 1 year.
• Your salary within salary scale 10 depends on your previous education and number of years of (relevant) work experience. The amounts in the scale are based on a 38-hour working week.
• You will receive an 8% holiday allowance and an 8,3% end-of-year bonus. 
• You will receive extra days off. With full-time employment, you can choose between 30 or 41 days of annual leave instead of the statutory 20. 

6. Practical information and applying

You can apply only via the button below. Address your letter of application to Dr Henk van den Heuvel. In the application form, you will find which documents you need to include with your application.

The first interviews will take place on Monday 10 March. Any second interview will take place on Friday 14 March. You will preferably start your employment on 1 May 2025.

We can imagine you're curious about our application procedure. It describes what you can expect during the application procedure and how we handle your personal data and internal and external candidates. If you wish to apply for a non-scientific position with a non-EU nationality, please take notice of the following information.