Simon Welker

6 papers · 2022–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver

Venues

Interspeech (5) ICLR (1)

Top co-authors

Timo Gerkmann (6) Julius Richter (5) Bunlong Lay (2) Danilo de Oliveira (2) Alexander Richard (2) YI-CHIAO WU (2) Jean-Marie Lemercier (1) Shinji Watanabe (1) Ricky T. Q. Chen (1) Wei-Ning Hsu (1)

Research topics

Deep Learning (4) Machine Learning (4) Speech & Audio (4) Models (4) Optimization & Theory (3) Synthesis (3) Artificial Intelligence (1) Computer Vision (1) Mathematics & Optimization (1) Analysis (1) Application Areas (1) Bayesian & Probabilistic (1) Probability (1) Processing (1)

Keywords

speech enhancement (4) diffusion model (3) score-based generative model (2) stochastic differential equation (2) flow matching (1) metric optimization (1) likelihood estimation (1) score matching (1) perceptual quality (1) speech dataset (1) human evaluation (1) speech quality assessment (1) neural audio codec (1) anechoic speech (1) listening test (1) instrumental metric (1) perceptual evaluation (1) complex domain (1) brownian bridge (1) audio reconstruction (1)

Papers

FlowDec: A flow-based full-band general audio codec with high perceptual quality ICLR 2025 Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech Interspeech 2025 EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation Interspeech 2024 The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement Interspeech 2024 Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement Interspeech 2023 Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain Interspeech 2022