Haupt-Navigation

Inhalt des Dokuments

Gabriel Mittag

: © Robert Greinacher

Biography

Gabriel Mittag received his B.Sc. and M.Sc. degree in electrical and electronic engineering at the Technische Universität Berlin. During his master's degree he spent two semesters at the RMIT University in Melbourne, Australia and focused primarily on biomedical and speech signal processing. Since 2016 he is employed as research assistant at the Quality and Usability Lab at the TU Berlin, where he works towards a PhD in the field of Quality of Experience (QoE) of speech communication services. His main interests are in psychoacoustics, quality evaluation, signal processing, and machine learning.

Research Fields

Perceived Quality of Speech
Speech and Signal Processing

Research Topic

Diagnostic Quality of Transmitted Speech

Projects

Prizes

DAGA-Posterpreis: G. Mittag, F. Köster, S. Möller, "Non-intrusive Estimation of the Perceptual Dimension Coloration", DAGA 2016.
Best Paper Award: F. Köster, G. Mittag, T. Polzehl, S. Möller, "Non-intrusive Estimation of Noisiness as a Perceptual Quality Dimension of Transmitted Speech", PQS 2016.

Teaching

Speech Communication (Exercise)

Open Bachelor/Master theses:

Contact

Email: gabriel.mittag@tu-berlin.de

Publications

Detecting Packet-Loss Concealment Using Formant Features and Decision Tree Learning
Zitatschlüssel	mittag2018a
Autor	Mittag, Gabriel and Möller, Sebastian
Buchtitel	Proceedings of Interspeech 2018
Seiten	1883–1887
Jahr	2018
ISSN	2472-7814
DOI	10.21437/Interspeech.2018
Adresse	Baixas, France
Monat	sep
Notiz	electronic
Verlag	ISCA
Serie	Interspeech
Wie herausgegeben	Fullpaper
Zusammenfassung	One of the main quality impairments in today's packet-based voice services are interruptions caused by transmission errors. Therefore, most codecs comprise concealment algorithms that attempt to reduce the perceived quality degradation of missing speech packets. In case the algorithm fails to properly synthesize the lost speech, interruptions or unnatural sounds are usually perceivable by the user. When measuring the quality of a voice network, there are excellent tools available, which can predict the perceived speech quality. However, they offer only little insight into the technical cause of a quality degradation. A packet-loss detection model could explain the influence of transmission errors on the speech quality and state a packet-loss rate. Thus, making it easier to identify technical problems in the network. In this paper, we examine a new approach for detecting (perceived) packet-loss of transmitted speech by audio analysis. After finding a lost packet, the model classifies in a second stage if the loss was perceivable as a quality degradation. In the model, we use meaningful features that are easy to interpret, and obtained promising results in a simulated environment. Therefore, this detector could also be used to evaluate new packet-loss concealment algorithms and help in optimizing the same.