- Speech Recognition and Synthesis
- Speech and Audio Processing
- Web Data Mining and Analysis
- Privacy, Security, and Data Protection
- Semantic Web and Ontologies
- Social Media in Health Education
- Data Visualization and Analytics
- Sentiment Analysis and Opinion Mining
- Privacy-Preserving Technologies in Data
- Scientific Computing and Data Management
- Advanced Text Analysis Techniques
- Music and Audio Processing
- Academic Publishing and Open Access
- Digital Mental Health Interventions
- Misinformation and Its Impacts
German Research Centre for Artificial Intelligence
2023-2025
Fraunhofer Institute for Open Communication Systems
2022
Many scientists share preprints on social media platforms to gain attention from academic peers, policy-makers, and journalists. In this study we shed light an unintended but highly consequential effect of sharing preprints: Their contribution conspiracy theories. Although the scientific community might quickly dismiss a preprint as insubstantial ‘clickbaity’, its uncertain epistemic status nevertheless allows theorists mobilize text support for their own narratives. To better understand...
Speaker anonymization consists of concealing the source speaker's identity, while keeping linguistic and paralinguistic content intact.It is usually evaluated as a trade-off between privacy utility.The current standard for evaluation automatic speaker verification system (ASV) from Voice Privacy Challenge (VPC); it involves computing embeddings comparing them with trained PLDA algorithm.We implement this ASV extend utility VPC, which previously consisted speech recognition performance,...
Due to the large number and heterogeneity of data sources, it becomes increasingly difficult follow research output scientific discourse. For example, a publication listed on DBLP may be discussed Twitter its underlying set used in different paper published arXiv. The discourse this is involved divided among not integrated systems, for researchers might very hard all discourses or in. Also, many these sources—DBLP, arXiv, Twitter, name few—are often updated real-time. These systems are...