EASY LISTENING: Optimizing the consequences of effortful listening in occupational settings

PhD position 2: Acoustical Scene Analysis and Speech Enhancement

This position has been filled.

Together with CeoTronics AG, Fraunhofer Institute for Digital Media Technology IDMT in Oldenburg offers one fully funded Marie Skłodowska-Curie PhD stipend position in the field of audio scene analysis and speech enhancement.

For over 30 years, CeoTronics has developed and produced innovative communication systems for demanding environments. They are the leading supplier of mobile digital radio networks and terminal equipment as well as high-quality communication headsets and systems for professional use.

CeoTronics communication systems, including effective hearing protection and other protective functions, are far superior to simple hearing protectors because users can still communicate with each other even under the most adverse conditions. Whether working, for example, in noisy or dangerous environments or wearing personal protective equipment (PPE), CeoTronics systems offer more protection in the workplace, increasing productivity and efficiency.

CeoTronics provides communication systems and services for a wide variety of professional groups. The company employs approximately 100 people and is headquartered in Rödermark, near Frankfurt.

The objective of the Oldenburg Branch for Hearing, Speech and Audio Technology HSA of the Fraunhofer Institute for Digital Media Technology IDMT is to translate scientific findings related to hearing perception and man-machine interaction into technological applications. Its research and development priorities are the enhancement of sound quality and speech intelligibility, personalized audio reproduction, automatic speech recognition and acoustic event detection with the help of artificial intelligence. A further focus is the use of mobile neurotechnology, which specifically facilitates the recording of brain activity and utilization of the resulting data outside the laboratory.

Application fields include consumer electronics, the automotive sector, industrial production, security, telecommunications and healthcare. Through scientific partnerships, Fraunhofer IDMT-HSA has close links with the Carl von Ossietzky University of Oldenburg, Jade University of Applied Sciences and other institutions engaged in hearing research in Oldenburg. Fraunhofer IDMT-HSA is a partner in the Cluster of Excellence »Hearing4all«.

The Oldenburg Branch for Hearing, Speech and Audio Technology HSA is funded in the program »Vorab« by the Lower Saxony Ministry of Science andCulture (MWK) and the Volkswagen Foundation for its further development.

The group »Audio Signal Enhancement (ASE)« of the Fraunhofer IDMT-HSA focuses on single and multichannel based enhancement of disturbed audio signals (e.g. speech), separation of targeted sounds, automatic speaker recognition and acoustic analysis of dangerous situations.

About the project »EASYLI«

Noise, hearing loss and listening difficulties at the workplace can require high levels of (listening) effort in order to maintain performance. This can lead to increased levels of stress and fatigue, which can result in productivity loss and increased sick leave. However, applying effort to listening leads to positive consequences as well (good work performance, pleasure, safety, societal participation). In the Horizon Europe Doctoral Network project »EASYLI« (Easy listening: optimizing the consequences of effortful listening in occupational settings), our stance is to optimize the ratio between the costs and benefits of effortful listening.

EASYLI will train 6 doctoral candidates to develop and apply a toolbox of ambulatory and laboratory measures to assess listening effort in occupational settings. They will apply real-time acoustic scene analysis, virtual acoustics, and physiological and subjective measures in laboratory and real-life conditions. The candidates will also evaluate individualized interventions (e.g., machine learning-based speech enhancement algorithms, hearing aids). EASYLI consists of 5 academic partners and 4 non-academic partners representing hearing-aid and communication systems industries, audiology, and occupational sectors with challenging acoustic environments.

The doctoral network EASYLI strongly values research integrity, actively supports open access and reproducible research, and strives for diversity and gender balance in its entire research and training program. EASYLI adheres to The European Charter for Researchers and The Code of Conduct for the Recruitment of Researchers.

What you will do

In this project, you will research and develop machine learning-based technologies for audio scene analysis and improvement of the acoustical signal in the context of occupational communication in safety-critical conditions. At the same time, you will enroll as doctoral student at the Carl von Ossietzky University of Oldenburg, Germany.

You will be fully embedded in the EASYLI research and training network and will carry out theoretical and applied research in the interdisciplinary fields of signal processing, audio processing, communication systems, machine learning, and psychoacoustics. The topics of the position are related to the following fields:

  • Speaker recognition
  • Sound source detection and separation
  • Development of machine/deep learning-based algorithms for acoustic signal processing
  • Real time implementation (low delay processing)
  • Human speech perception and psychoacoustics

Senior researchers involved in this project are Jan Rennies-Hochmuth and Xavier Domont