Navigation auf


Department of Computational Linguistics

Articulatory Synthesis and Modeling

Supervisor: Dr. Daniel Friedrichs


This thesis project focuses on the intersection of articulatory synthesis and modeling, aiming to enhance speech production models using detailed articulatory data. The core objective is to examine how the integration of high-resolution spatial data from Ultrasound Tongue Imaging (UTI) and precise temporal data from Electromagnetic Articulography (EMA) can refine existing models of speech synthesis. The project will involve analyzing the complex interplay of tongue movements and their temporal dynamics to develop more accurate and naturalistic speech synthesis models.


  • For MA students: Involvement in data collection using UTI and EMA, requiring a foundational understanding of these technologies.
  • Strong analytical skills, particularly in data analysis and interpretation.
  • Familiarity with speech synthesis and articulatory modeling.
  • Proficiency in relevant software tools and programming languages (e.g., MATLAB or Python) for data processing and model development.