Author

Pejman Mowlaee

Graz University of technology

h-index 13 Homepage View on Semantic Scholar

We have 3 of 43 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

DiffVQE2: An Efficient Low-delay Diffusion Model for Acoustic Echo and Noise Control

Hands-free communication devices and speakerphones are inherently affected by acoustic echo and background noise. To mitigate these impairments, end-to-end discriminatively trained neural networks have emerged as the best-performing approach in research and deployment. While recent advancements in generative methods ha...

Haljan Lugo, Ernst Seidel, Pejman Mowlaee et al. · 0 citations

Preprint Aug 2026

Perceptually Better, Semantically Worse: Measuring Speech Enhancement Impact on LLM-Based Voice Systems

Output Divergence Rate (ODR) is introduced, which measures how often SE changes an LLM's intent classification relative to clean speech, and MetricGAN{+} and echo results replicate across ASR architectures, indicating that standard audio quality metrics are insufficient for LLM pipeline quality.

R. F. Fela, Pejman Mowlaee · 0 citations

Preprint Aug 2026

Knowledge Distillation for Efficient Acoustic Echo Control

These proposed CGGN16 student AEC models show significantly less near-end speech distortion at only 2% of its teacher's computational complexity, surpass the overall performance of a six times more complex model trained on ground-truth labels, and outperform other AEC-focused architectures from recent literature.

Ernst Seidel, Pejman Mowlaee, Tim Fingscheidt · 0 citations