Vacancy: PhD position – Speech & Audio Processing


We are looking for a junior researcher that will work on robust methods for analyzing pathological speech. This work is funded by the TAPAS project (a Horizon 2020 Marie Skłodowska-Curie Actions Innovative Training Network). The automatic speech analysis is used within the ASISTO e-health tool to provide feedback to both the patient (give feedback on exercises, measure if the patient’s speech improves) and to the speech therapist (aid in analyzing what the main problems is, measure the effectiveness of exercises). Since speech pathologies are diverse in nature and since annotated data is scarce, the focus of the work is on robust techniques and transfer learning. The main properties of speech, expressed as phonological features or articulatory features, are learned on non-pathological speech and then applied to the pathological speech. Extra robustness can be achieved by training on multiple languages (regard pathological speech as another language) and with modern deep learning techniques such as dropout, mix-up, adversarial training, etc. Given the scarcity of the pathological speech data, cross-pathology, cross-exercise and cross-language training is also thought to be beneficial. The work is expected to advance the state-of-the-art in robust speech processing.

The TAPAS project

There are an increasing number of people across Europe with debilitating speech pathologies (e.g., due to stroke or due to Parkinson's). This group faces communication problems that can lead to social exclusion. They are now being further marginalised by a new wave of speech technology that is increasingly woven into everyday life, but which is not robust to atypical speech. TAPAS aims to transform the wellbeing of these people.

Since TAPAS is a Horizon 2020 Marie Skłodowska-Curie Actions Training Network (MSCA-ITN-ETN), the researchers are required you to collaborate with researchers and developers across Europe.  Moreover, at least 9 months of your work will be executed in another country.


Imec is the world-leading research and innovation hub in nanoelectronics and digital technologies.  By leveraging our world-class research infrastructure and local and global ecosystem of partners across a multitude of industries, we create ground-breaking innovation in application domains such as healthcare, smart cities and mobility, logistics and manufacturing, and energy.  As a trusted partner for companies, start-ups and universities we bring together close to 3500 brilliant minds from over 70 nationalities. Imec is headquartered in Belgium and has distributed R&D groups at several Flemish universities, in the Netherlands, Taiwan, USA, China, and offices in India and Japan.

IDLab is a core research group of imec with research activities embedded in Ghent University.  IDLab performs fundamental and applied research on data science and internet technology, and is, with over 300 researchers, one of the larger research groups at imec.  Major research areas are machine learning and data mining, and various internet technologies such as distributed intelligence for IoT, cloud and big data infrastructures, and networking circuits and systems.  Speech & audio processing has been one of our research fields for over 40 years, covering a wide range of topics including speech recognition, speaker diarization (speech segmentation & speaker recognition, language & dialect recognition), extraction of para-linguistic features (emotion and mental state of the speakers), automatic assessment of pathological speech, music analysis and classification, and generic audio processing.

Eligibility Criteria

  • You have a degree in Master of Science/Engineering, preferably in Computer Science, Electronics-ICT or (Mathematical) Informatics.     
    Note: to be admissible to the PhD-program, your degree must be equivalent to 5 years of engineering studies (bachelor + master) in the European Union, and you must have a solid academic track record (graduation cum laude or grades in the top 30% percentile).
    • You must not have resided or carried out her/his main activity (work, studies, etc.) in Belgium for more than 12 months in the 3 years immediately prior to the recruitment.                                                                
    • You are interested in and motivated by the research topic, as well as in obtaining a PhD degree.
    • You have a strong interest in the above-mentioned domains.
  • You have excellent analytical skills.
  • You speak and write English fluently (C1 CEFR level) and you have good communication skills.
  • You have an open mind and a multi-disciplinary attitude.
  • You are proficient in programming (Python and/or C).
  • Having prior experience with the above-mentioned domains is a plus.

Our offer

We offer a fully funded PhD position in a challenging, stimulating and pleasant research environment, where you can contribute to our research on speech and audio processing. The PhD research is innovative with clear practical applications and is done in close collaboration with national and international industry players. You will join a young and enthusiastic team of researchers, post-docs and professors. This PhD position is available immediately. The duration of the recruitment is 2 years on the TAPAS project and 2 years on a subsequent project.


Apply with motivation letter, scientific resume, academic results, English proficiency scores, relevant publications, and two reference contacts.

For any questions, contact .

After the first screening, suitable candidates will be invited for an interview (also possible via Skype).

Read more articles about: