TU Berlin

Quality and Usability LabJan-Niklas Voigt-Antons

Inhalt des Dokuments

zur Navigation

Dr.-Ing. Jan-Niklas Voigt-Antons


Jan-Niklas Voigt-Antons joined the Telekom Innovation Laboratories as a research scientist in January 2009 and is working there since 2014 as a senior research scientist. He received his diploma in psychology in 2008 from the Technische Universität Darmstadt, Germany, a Doctor-of-Engineering degree in 2014 from the Technische Universität Berlin, Germany and has been doing research at the Quality and Usability Lab at the Technische Universität (TU) Berlin, since. His research interests are in Quality-of-Experience evaluation and its physiological correlates with an emphasis on media transmissions and human-machine-interaction, including neural processing of multimodal interaction. During summer 2012 he was visiting researcher at MuSAE Lab (INRS-EMT), Canada where he examined neural correlates of quality perception for complex speech signals. In spring 2014 he was visiting researcher at the department of psychology of NTNU, Norway where he examined neural correlates of audiovisual asynchrony.

QULab research group: Quality, User Experience, Augmented and Virtual Reality

Research Topics: 

• Multimedia Experience (Usability evaluation methods, Quality-of-Experience evaluation physiological measures)

• Interaction Design (Adaptive software, data mining, sensor and behavioural data)

Current projects:


Measuring of immersive media experience

Exergaming in virtual reality

DemTab - Tabletgestützte ambulante Versorgung von Menschen mit Demenz

VoiceAdapt - Adaptives Sprachtraining für ältere Menschen mit Aphasie

OurPuppet - Pflegeunterstützung mit einer interaktiven Puppe für informell Pflegende

Past projects:

PflegeTab - Technik für mehr Lebensqualität trotz Pflegebedürftigkeit bei Demenz (GKV)

Quality of Mobile Gaming

Bernstein Focus Neurotechnology - Berlin (BFNT - B)


Affective Computing
Study Project Quality & Usability (6/9 CP)


Current thesis offers of our lab can be found here. Please contact me via email if you are interested in doing a thesis supervised by me.


Current job offers of our lab can be found here


+49 30 8353 58 377


Technische Univertistät Berlin
Quality and Usability Lab
Telekom Innovation Laboratories
Ernst-Reuter-Platz 7
10587 Berlin, Germany


Single-trial analysis of the neural correlates of speech quality perception
Zitatschlüssel porbadnigk2013a
Autor Porbadnigk, Anne K. and Treder, Matthias and Blankertz, Benjamin and Antons, Jan-Niklas and Schleicher, Robert and Möller, Sebastian and Curio, Gabriel and Müller, Klaus-Robert
Seiten 1–20
Jahr 2013
ISSN 1741-2552
DOI 10.1088/1741-2560/10/5/056003
Adresse Bristol, UK
Journal Journal of Neural Engineering
Jahrgang 10
Nummer 5
Monat jul
Notiz Electronic/online
Verlag IOP Publishing
Wie herausgegeben Full
Zusammenfassung Objective. Assessing speech quality perception is a challenge typically addressed in behavioral and opinion-seeking experiments. Only recently, neuroimaging methods were introduced, which were used to study the neural processing of quality at group level. However, our electroencephalography (EEG) studies show that the neural correlates of quality perception are highly individual. Therefore, it became necessary to establish dedicated machine learning methods for decoding subject-specific effects. Approach. The effectiveness of our methods is shown by the data of an EEG study that investigates how the quality of spoken vowels is processed neurally. Participants were asked to indicate whether they had perceived a degradation of quality (signal-correlated noise) in vowels, presented in an oddball paradigm. Main results. We find that the P3 amplitude is attenuated with increasing noise. Single-trial analysis allows one to show that this is partly due to an increasing jitter of the P3 component. A novel classification approach helps to detect trials with presumably non-conscious processing at the threshold of perception. We show that this approach uncovers a non-trivial confounder between neural hits and neural misses. Significance. The combined use of EEG signals and machine learning methods results in a significant 'neural' gain in sensitivity (in processing quality loss) when compared to standard behavioral evaluation; averaged over 11 subjects, this amounts to a relative improvement in sensitivity of 35%.
Link zur Originalpublikation Download Bibtex Eintrag



Schnellnavigation zur Seite über Nummerneingabe