Iordanis Thoidis

I am a Researcher in Hearing Technology, studying how people with hearing loss perceive speech and sound, and developing innovative solutions to make life sound better.

Career

Jacoti Hearing Technologies

Jacoti’s mission is to make state-of-the-art hearing solutions accessible and affordable for people with hearing loss throughout the world.

2023 - Present
Senior Researcher

Deep Hearing Lab - University of Cambridge

Research on deep learning methods to enhance speech intelligibility for hearing aid and cochlear implant users in environments with multiple speakers and background noise.

2022
Visiting Research Scholar

Department of Music Studies - University of Ioannina

Lecturer of "Sound Recording and Mixing Techniques" course

2021 - 2022
Adjunct Lecturer

Laboratory of Electroacoustics and TV Systems - Aristotle University of Thessaloniki

Audio-Visual (AV) System Design for projects in the Directorate-General for Security of the European Parliament and the Joint Research Centre of the European Commission.

2021 - 2022
Audio-Visual System Design Engineer

Aristotle University of Thessaloniki

Audio signal processing and Machine Learning for the research project "Automated fault detection of industrial equipment via audio analysis" (5047780) funded by Greece and the European Union (European Social Fund- ESF).

2019 - 2021
Research Fellow

Education

2018 - 2024

PhD in Electrical and Computer Engineering

Aristotle University of Thessaloniki, Greece

Thesis: "Restoring speech intelligibility in complex acoustic environments for people with hearing loss using deep learning techniques"

2011 - 2018

Master of Engineering in Electrical and Computer Engineering

Aristotle University of Thessaloniki, Greece

Thesis: "Development and evaluation of a diagnostic audiometer application software for mobile devices"

Recent Publications

2024

  • Using deep learning to improve the intelligibility of a target speaker in noisy multi-talker environments for people with normal hearing and hearing loss.

    Thoidis, I., & Goehring, T.
    The Journal of the Acoustical Society of America, 156(1), 706-724. (2024)
  • Test-retest reliability of remote home-based audiometry in differing ambient noise conditions.

    Thoidis, I., Hazan, A., Snik, A., Rivilla, J., Budzyński, K., Mendez, N., & Kinsbergen, J.
    Frontiers in Audiology and Otology, 2, 1371037. (2024)
  • Improved tactile speech robustness to background noise with a dual-path recurrent neural network noise-reduction method.

    Fletcher, M. D., Perry, S. W., Thoidis, I., Verschuur, C. A., & Goehring, T.
    Scientific Reports, 14(1), 7357. (2024)

2023

  • Perceptual analysis of speaker embeddings for voice discrimination between machine and human listening.

    Thoidis, I., Gaultier, C., Goehring, T.
    IEEE ICASSP 2023, Rhodes, Greece. (June 2023)


For the full list of publications, visit Google Scholar.

Research Projects

Deep Learning for Speech Enhancement

Development of novel deep learning architectures for improving speech intelligibility in complex acoustic environments.

Mobile Audiometry Platform

Design and implementation of a mobile-based hearing assessment system for remote and accessible hearing testing.

Hearing Aid Algorithm Development

Research on advanced signal processing algorithms for hearing aid applications.

Clinical Trials and Evaluations

Designing and conducting clinical evaluations for hearing assessment and hearing loss compensation strategies.

Audio Semantic Analysis

Development of advanced techniques for audio semantic analysis and speaker recognition.

Audio-Driven Fault Detection

Development of audio signal processing and semi-supervisedmachine learning techniques for automated fault detection of industrial equipment.

Awards

2022
Young Scientist Award
Young Scientist Award at the 3rd Virtual Conference on Computational Audiology 2022 for the presentation of the study 'Towards differentiable auditory models as objective functions for listener-specific speech enhancement' Thoidis I., Pastiadis K., Papanikolaou G.