Picture for Anton Ratnarajah

Anton Ratnarajah

AV-RIR: Audio-Visual Room Impulse Response Estimation

Add code
Nov 30, 2023
Viaarxiv icon

M3-AUDIODEC: Multi-channel multi-speaker multi-spatial audio codec

Add code
Sep 23, 2023
Viaarxiv icon

AdVerb: Visually Guided Audio Dereverberation

Add code
Aug 23, 2023
Viaarxiv icon

Towards Improved Room Impulse Response Estimation for Speech Recognition

Add code
Nov 08, 2022
Viaarxiv icon

MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes

Add code
May 18, 2022
Figure 1 for MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes
Figure 2 for MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes
Figure 3 for MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes
Figure 4 for MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes
Viaarxiv icon

GWA: A Large High-Quality Acoustic Dataset for Audio Processing

Add code
Apr 04, 2022
Figure 1 for GWA: A Large High-Quality Acoustic Dataset for Audio Processing
Figure 2 for GWA: A Large High-Quality Acoustic Dataset for Audio Processing
Figure 3 for GWA: A Large High-Quality Acoustic Dataset for Audio Processing
Figure 4 for GWA: A Large High-Quality Acoustic Dataset for Audio Processing
Viaarxiv icon

FAST-RIR: Fast neural diffuse room impulse response generator

Add code
Oct 07, 2021
Figure 1 for FAST-RIR: Fast neural diffuse room impulse response generator
Figure 2 for FAST-RIR: Fast neural diffuse room impulse response generator
Figure 3 for FAST-RIR: Fast neural diffuse room impulse response generator
Figure 4 for FAST-RIR: Fast neural diffuse room impulse response generator
Viaarxiv icon

Improving Reverberant Speech Separation with Multi-stage Training and Curriculum Learning

Add code
Jul 19, 2021
Figure 1 for Improving Reverberant Speech Separation with Multi-stage Training and Curriculum Learning
Figure 2 for Improving Reverberant Speech Separation with Multi-stage Training and Curriculum Learning
Figure 3 for Improving Reverberant Speech Separation with Multi-stage Training and Curriculum Learning
Figure 4 for Improving Reverberant Speech Separation with Multi-stage Training and Curriculum Learning
Viaarxiv icon

TS-RIR: Translated synthetic room impulse responses for speech augmentation

Add code
Apr 03, 2021
Figure 1 for TS-RIR: Translated synthetic room impulse responses for speech augmentation
Figure 2 for TS-RIR: Translated synthetic room impulse responses for speech augmentation
Figure 3 for TS-RIR: Translated synthetic room impulse responses for speech augmentation
Figure 4 for TS-RIR: Translated synthetic room impulse responses for speech augmentation
Viaarxiv icon