4 papers
Discriminative Flow Matching: Beyond Time-Conditioning in Generative Restoration via Flow-State Representations
Shrishti Saha Shetu, Emanuël A. P. Habets, Andreas Brendel
Existing Conditional Flow Matching (CFM) formulations describe transport progress using an explicit interpolation coordinate, commonly interpreted as time, assuming that a single g…
A Comparison of Generative and Discriminative Methods for Speech Enhancement: Robustness, Complexity, and Hallucination
Shrishti Saha Shetu, Emanuël A. P. Habets, Andreas Brendel
In this study, we conduct a comprehensive comparative analysis of generative and discriminative deep learning-based speech enhancement methods, specifically in noise reduction task…
Room Impulse Response Completion Using Signal-Prediction Diffusion Models Conditioned on Simulated Early Reflections
Zeyu Xu, Andreas Brendel, Albert G. Prinn +1
Room impulse responses (RIRs) are fundamental to audio data augmentation, acoustic signal processing, and immersive audio rendering. While geometric simulators such as the image so…
GAN-Based Multi-Microphone Spatial Target Speaker Extraction
Shrishti Saha Shetu, Emanuël A. P. Habets, Andreas Brendel
Spatial target speaker extraction isolates a desired speaker's voice in multi-speaker environments using spatial information, such as the direction of arrival (DoA). Although recen…