autrainer
A Modular and Extensible Deep Learning Toolkit for Computer Audition Tasks. (GitHub) 
Posts by Collection
portfolio
publications
Dawn of the Transformer Era in Speech Emotion Recognition: Closing the Valence Gap
Published in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
Our top-cited work on speech emotion recognition.
Recommended citation: Wagner, J., Triantafyllopoulos, A., et al. (2023). "Dawn of the Transformer Era in Speech Emotion Recognition: Closing the Valence Gap" IEEE Transactions on Pattern Analysis and Machine Intelligence. vol. 45, no. 9, pp. 10745-10759.
Download Paper
An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era
Published in Proceedings of the IEEE, 2023
A narrative review of affective speech synthesis.
Recommended citation: Triantafyllopoulos, A., et al. (2023). "An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era" Proceedings of the IEEE. vol. 111, no. 10, pp. 1355-1381.
Download Paper
Computer audition: From task-specific machine learning to foundation models
Published in Proceedings of the IEEE (forthcoming), 2025
A narrative review of audio foundation models.
Recommended citation: Triantafyllopoulos, A. et al. (2025). "Computer audition: From task-specific machine learning to foundation models." Proceedings of the IEEE. (forthcoming).
Download Paper
talks
Digital health ‘in-the-wild’
Published:
Overview of digital health in noisy, industrial settings (https://www.tapas-etn-eu.org/events/te6)
N-HANS: Adaptive speech denoising
Published:
Quick overview of the principles underlying adaptive denoising
Affective computing for psychologists
Published:
Simple overview of affective computing and its connection to psychology research and praxis
Overview on AI for Hearing Aids and AI to Detect Extracochlear Electrode Placement
Published:
Overview of our efforts on low-footprint speech denoising and detection of extracochlear electrode placement
teaching
Advanced Practical Course Deep Learning for Audio, Speech, and Language
Graduate course (10 ECTS), Technical University of Munich, Chair of Health Informatics, 2025
Our quarterly practical course on audio, speech, and language.
theses
Deep reinforcement learning for audio
Learning to listen by reward.
Ecoacoustics
Using audio to monitor the environment.
Speech & language for mental health
Using speech for the diagnosis and treatment of mental disorders.
Speech for respiratory health
Using speech for the diagnosis of respiratory diseases.
Speech emotion recognition
Using speech to recognize emotions.
Source separation
Decomposing an audio stream to its individual salient components.