Ahmad Aloradi

Ahmad Aloradi

Doctoral Researcher. Signal Processing Engineer · Deep Learning and Audio Processing

I'm a Ph.D. student in Signal Processing at Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) - Department of Data Science, focusing on Adversarial and Domain Shift Robustness for Speaker Recognition.

View Resume

Publications

Speaker Verification in Multi-Speaker Environments Using Temporal Feature Fusion

Ahmad Aloradi, Wolfgang Mack, Mohamed Elminshawi, Emanuël A. P. Habets

EUSIPCO, Belgrade, Aug. 2022

Paper

Target-Speaker Voice Activity Detection in Multi-Talker Scenarios: An Empirical Study

Ahmad Aloradi, Mohamed Elminshawi, Srikanth Raj Chetupalli, Emanuël A. P. Habets

ITG, Aachen, Sep. 2023

Paper

Projects

Fraunhofer IIS Project

Multi-lingual Text-to-Speech TTS

Development of an enterprise-grade TTS system with zero-shot inference capabilities

Audiolabs Project

Robust Speaker Recognition

Speaker detection in multi-talker environments using deep neural networks

FAU Project

Adversarial Robustness for Speaker Recognition

Government-funded research project for improving the robustness of speaker recognition against spoofing, adversarial attacks, and domain-shifts

GitHub

Contact

ahmad.aloradi@fau.de

Department of Data Science, Erlangen-Nürnberg FAU