Timo Gerkmann

Universität Hamburg — Germany

Computer Science · Physical Sciences

29h-index4.1kcitations243works4.22yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech and Audio Processing(195), Advanced Adaptive Filtering Techniques(100), Speech Recognition and Synthesis(76), Music and Audio Processing(53), Hearing Loss and Rehabilitation(40)

Publications243 total

Real-Time Streamable Generative Speech Restoration with Flow Matching
ArXiv.org·2025Open Access
Real-Time Streamable Generative Speech Restoration with Flow Matching
arXiv (Cornell University)·2025Open Access
A Novel Artificial-Intelligence-Based Reverberation-Reduction Algorithm for Cochlear Implants Enhances Speech Intelligibility and User Experience
Ear and Hearing·2025· 1 citedOpen Access
Are These Even Words? Quantifying the Gibberishness of Generative Speech Models
arXiv (Cornell University)·2025Open Access
Diffusion Buffer for Online Generative Speech Enhancement
arXiv (Cornell University)·2025Open Access
Self-Steering Deep Non-Linear Spatially Selective Filters for Efficient Extraction of Moving Speakers under Weak Guidance
2025
Real-Time Streaming Mel Vocoding with Generative Flow Matching
arXiv (Cornell University)·2025Open Access
Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech
2025
Diffusion Buffer: Online Diffusion-based Speech Enhancement with Sub-Second Latency
2025
Steering Deep Non-Linear Spatially Selective Filters for Weakly Guided Extraction of Moving Speakers in Dynamic Scenarios
2025· 1 cited
Diffusion Buffer: Online Diffusion-based Speech Enhancement with Sub-Second Latency
arXiv (Cornell University)·2025Open Access
Steering Deep Non-Linear Spatially Selective Filters for Weakly Guided Extraction of Moving Speakers in Dynamic Scenarios
arXiv (Cornell University)·2025Open Access
LipDiffuser: Lip-to-Speech Generation with Conditional Diffusion Models
arXiv (Cornell University)·2025Open Access
Do We Need EMA for Diffusion-Based Speech Enhancement? Toward a Magnitude-Preserving Network Architecture
ArXiv.org·2025Open Access
Mask-Weighted Spatial Likelihood Coding for Speaker-Independent Joint Localization and Mask Estimation
2025
HRTF Estimation using a Score-based Prior
2025· 2 citedOpen Access
Investigating Training Objectives for Generative Speech Enhancement
2025· 6 cited
FlowDec: A flow-based full-band general audio codec with high perceptual quality
arXiv (Cornell University)·2025Open Access
Unsupervised Blind Joint Dereverberation and Room Acoustics Estimation With Diffusion Models
IEEE Transactions on Audio Speech and Language Processing·2025· 4 citedOpen Access
Diffusion Models for Audio Restoration: A review
IEEE Signal Processing Magazine·2024· 27 citedOpen Access
page 1 of 13Next →

Frequent Co-authors

Simon Doclo(11), Julius Richter(8), Simon Welker(8), Martin Krawczyk-Becker(6), Richard C. Hendriks(5), Jean-Marie Lemercier(5), Rainer Martin(5), Stefan Goetze(5), Birger Kollmeier(5), Martin Krawczyk(4), Bunlong Lay(4), Kristina Tesch(4), Ina Kodrasi(4), Alfred Mertins(4), Colin Breithaupt(3), Robert Rehr(3), Kamil Adiloğlu(3), Jesper Rindom Jensen(2), Ante Jukić(2), Guillaume Carbajal(2)