Towards a Vowel Formant Based Quality Metric for Text-to-Speech Systems: Measuring Monophthong Naturalness
Sven Albrecht, Rewa Tamboli, Stefan Taubert, Maximilian Eibl, Günter Daniel Rey, Josef Schmied

This contribution proposes an objective, vowel formant based quality metric for assessing the naturalness of monophthongs synthesized by Text-to-Speech (TTS) systems.

Untying the Gordian Knot: Legally Compliant Sound Data Collection and Processing for TTS Systems in China
Stefanie Meyer, Sven Albrecht, Maximilian Eibl, Günter Daniel Rey, Josef Schmied, Rewa Tamboli, Stefan Taubert, Dagmar Gesmann-Nuissl

If data is to be collected and partially processed in China as part of an international and interdisciplinary research project, all applicable European and Chinese regulations have to be observed. This contribution compares the regulations and draws conclusions about similarities and differences in legislation across countries in order to ensure data collection and processing in conformity with data protection.


Automated Lifelog Moment Retrieval based on Image Segmentation and Similarity Scores (PDF)
Stefan Taubert, Stefan Kahl, Danny Kowerko and Maximilian Eibl

In 2019 I participated in the annual international ImageCLEF competition and developed a method for automated Lifelog Moment Retrieval based on image segmentation and similarity measures as part of my master thesis.


Species Prediction based on Environmental Variables using Machine Learning Techniques (PDF)
Stefan Taubert, Max Mauermann, Stefan Kahl, Danny Kowerko and Maximilian Eibl

In 2018 I took part in the annual international LifeCLEF competition and as part of my research seminar I developed a method for specifying plant species using images and environmental variables.