Dr.-Ing. Tim Polzehl

Contact +49 30 23895 1863 (Berlin)

Address (Berlin) DFKI Labor Berlin - KesselhausSalzufer 15-1610587 Berlin

Publications

Two Views, One Truth: Spectral and Self-Supervised Features Fusion for Robust Speech Deepfake Detection
Yassine El Kheir; Arnab Das; Enes Erdem Erdogan; Fabian Ritter Guttierez; Tim Polzehl; Sebastian Möller
In: Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics. IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA-2025), October 12-15, Tahoe City, CA, USA, IEEE, 10/2025.
BiCrossMamba-ST: Speech Deepfake Detection with Bidirectional Mamba Spectro-Temporal Cross-Attention
Yassine El Kheir; Tim Polzehl; Sebastian Moller (Hrsg.)
Conference in the Annual Series of Interspeech Events (INTERSPEECH-2025), INTERSPEECH 2025, located at INTERSPEECH-2025, August 16-22, Netherlands, Netherlands, ISCA Arxiv, 9/2025.
Generalizable Audio Spoofing Detection using Non-Semantic Representations
Arnab Das; Yassine El Kheir; Carlos Franzreb; Tim Herzig; Tim Polzehl; Sebastian Moller (Hrsg.)
Conference in the Annual Series of Interspeech Events (INTERSPEECH-2025), August 17-21, Rotterdam, Netherlands, ISCA - Interspeech 2025, 8/2025.

Fake-O-Meter
Joint Project: Multimodal AI-based Disinformation Assistant for Awareness and Resilience in Dealing with Media Disinformation
Fake-O-Meter develops a multimodal, AI-based assistance system that helps people identify and understand disinformation. It combines deepfake detection across image, audio and video, explanations…
VERANDA
Trustworthy anonymization of sensitive patient data for remote consultations
The primary aim of VERANDA is to explore and promote informational self-determination in the context of personal and sensitive medical data, especially among stigmatized groups. This includes…
news-polygraph
Privacy, transparency, bias-free, trustworthy multimodal disinformation fighting
In the news-polygraph project, we are developing digital methods for the media industry, with the help of which multimedia content can be checked more easily and quickly for manipulation,…
Medinym
AI-based anonymization of personal patient data in clinical text and voice databases
In the Medinym project, we are pursuing the goal of completely anonymising the speaker identity of a speaker, both on voice and on statement/semantic level, without losing emotional or diagnostic…
PYSA
Care documentation with a hybrid speech assistant
Comprehensive and accurate documentation is essential for needs-based care. In many places, the systems and processes used today for care documentation are time-consuming and prone to errors.…