Picture for Sebastian Braun

Sebastian Braun

Microsoft Research

Ultra-Low Latency Speech Enhancement - A Comprehensive Study

Add code
Sep 16, 2024
Viaarxiv icon

Multi-label audio classification with a noisy zero-shot teacher

Add code
Jul 20, 2024
Viaarxiv icon

Gaussian Flow Bridges for Audio Domain Transfer with Unpaired Data

Add code
May 29, 2024
Figure 1 for Gaussian Flow Bridges for Audio Domain Transfer with Unpaired Data
Figure 2 for Gaussian Flow Bridges for Audio Domain Transfer with Unpaired Data
Figure 3 for Gaussian Flow Bridges for Audio Domain Transfer with Unpaired Data
Figure 4 for Gaussian Flow Bridges for Audio Domain Transfer with Unpaired Data
Viaarxiv icon

ICASSP 2024 Speech Signal Improvement Challenge

Add code
Jan 25, 2024
Figure 1 for ICASSP 2024 Speech Signal Improvement Challenge
Viaarxiv icon

CMMD: Contrastive Multi-Modal Diffusion for Video-Audio Conditional Modeling

Add code
Dec 08, 2023
Viaarxiv icon

Adapting Frechet Audio Distance for Generative Music Evaluation

Add code
Nov 02, 2023
Viaarxiv icon

ICASSP 2023 Acoustic Echo Cancellation Challenge

Add code
Sep 22, 2023
Figure 1 for ICASSP 2023 Acoustic Echo Cancellation Challenge
Figure 2 for ICASSP 2023 Acoustic Echo Cancellation Challenge
Figure 3 for ICASSP 2023 Acoustic Echo Cancellation Challenge
Figure 4 for ICASSP 2023 Acoustic Echo Cancellation Challenge
Viaarxiv icon

ICASSP 2023 Speech Signal Improvement Challenge

Add code
Apr 02, 2023
Viaarxiv icon

ICASSP 2023 Deep Speech Enhancement Challenge

Add code
Mar 21, 2023
Figure 1 for ICASSP 2023 Deep Speech Enhancement Challenge
Viaarxiv icon

Towards Real-Time Single-Channel Speech Separation in Noisy and Reverberant Environments

Add code
Mar 14, 2023
Figure 1 for Towards Real-Time Single-Channel Speech Separation in Noisy and Reverberant Environments
Figure 2 for Towards Real-Time Single-Channel Speech Separation in Noisy and Reverberant Environments
Figure 3 for Towards Real-Time Single-Channel Speech Separation in Noisy and Reverberant Environments
Figure 4 for Towards Real-Time Single-Channel Speech Separation in Noisy and Reverberant Environments
Viaarxiv icon