Technically enabled explanation of speaker traits (Project C06)

A voice might be described as hoarse, or it may be clear, deep, or breathy. Researchers in Project C06 are looking at issues of how different vocal traits sound, and how a voice can be represented in all of its many facets. Here, linguists and computer scientists are working to develop an intelligent system that professionals can use to explain the phenomenon of voice to general audiences. To do this, the artificial intelligence (AI) system generates speech samples in which the same content is spoken by different voices. This may also be helpful for clinical linguists working in diagnostics, for example, to help identify the vocal characteristics of Parkinson's disease. By demonstrating how the system measures differences between voices, vocal modelling becomes more transparent and comprehensible. The goal of the research team is to find out whether people can better imitate and describe a voice with the help of the AI system.

Publications

Rautenberg F., Kuhlmann M., Ebbers J., et al. (2023). Speech Disentanglement for Analysis and Modification of Acoustic and Perceptual Speaker Characteristics. In: Fortschritte der Akustik - DAGA 2023. ; 2023:1409-1412. https://ris.uni-paderborn.de/record/44849

 

In this video the project leaders present their view of co-construction.
Research areas

computer science, linguistics

Project leaders

Prof. Dr. Reinhold Häb-Umbach, Paderborn University

Prof. Dr. Petra Wagner, Bielefeld University

Staff

Frederik Rautenberg, Paderborn University

Jana Wiechmann, Bielefeld University

Support Staff

Marc Deegen, Paderborn University

Lisa Kalinitschenko, Bielefeld University

Alexandra Schmidt, Bielefeld University