← Authors

Timo Gerkmann

18 papers · 2017–2025 · 3 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (6) πŸ—ΊοΈ Taxonomy Completionist (32) πŸŒ‰ Interdisciplinary Bridge 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (3) πŸƒ Academic Marathon (8) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (6) 🧬 Topic Evolution πŸ”₯ Unstoppable (7) πŸ’Ž Century Club (18) ⚑ Prolific Year (5) πŸ—ƒοΈ Keyword Collector (77)

Conferences

INTERSPEECH (16) ICLR (1) NIPS (1)

Top co-authors

Julius Richter (6) Simon Welker (5) Bunlong Lay (3) Jean-Marie Lemercier (3) Danilo de Oliveira (3) Xiaolin Hu (2) Kai Li (2) Kristina Tesch (2) Alexander Richard (2) Guillaume Carbajal (2)

Keywords

speech enhancement (12) diffusion model (3) stochastic differential equation (3) convolutional neural network (2) arousal recognition (2) speech separation (2) score-based generative model (2) deep neural network (2) speech emotion recognition (2) neural network (2) spatial filtering (2) progressive learning (1) metric optimization (1) fundamental frequency (1) uncertainty modeling (1) transformer architecture (1) deep learning (1) signal-to-noise ratio (1) multimodal learning (1) variational inference (1)

Papers

FlowDec: A flow-based full-band general audio codec with high perceptual quality ICLR 2025
An Analysis of the Variance of Diffusion-based Speech Enhancement INTERSPEECH 2024
The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement INTERSPEECH 2024
EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation INTERSPEECH 2024
Leveraging Semantic Information for Efficient Self-Supervised Emotion Recognition with Audio-Textual Distilled Models INTERSPEECH 2023
Extending DNN-based Multiplicative Masking to Deep Subband Filtering for Improved Dereverberation INTERSPEECH 2023
Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement INTERSPEECH 2023
Audio-Visual Speech Separation in Noisy Environments with a Lightweight Iterative Model INTERSPEECH 2023
Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain INTERSPEECH 2022
End-To-End Label Uncertainty Modeling for Speech-based Arousal Recognition Using Bayesian Neural Networks INTERSPEECH 2022
Neural Network-augmented Kalman Filtering for Robust Online Speech Dereverberation in Noisy Reverberant Environments INTERSPEECH 2022
On the Role of Spatial, Spectral, and Temporal Processing for DNN-based Non-linear Multi-channel Speech Enhancement INTERSPEECH 2022
Efficient Transformer-based Speech Enhancement Using Long Frames and STFT Magnitudes INTERSPEECH 2022
Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network NIPS 2021
Speech Enhancement with Stochastic Temporal Convolutional Networks INTERSPEECH 2020
Influence of Speaker-Specific Parameters on Speech Separation Systems INTERSPEECH 2019
On Nonlinear Spatial Filtering in Multichannel Speech Enhancement INTERSPEECH 2019
MixMax Approximation as a Super-Gaussian Log-Spectral Amplitude Estimator for Speech Enhancement INTERSPEECH 2017