![]() |
M3-AUDIODEC: MULTI-CHANNEL MULTI-SPEAKER MULTI-SPATIAL AUDIO CODEC |
![]() |
Listen2Scene: Interactive material-aware binaural sound propagation for reconstructed 3D scenes |
![]() |
Towards Improved Room Impulse Response Estimation for Speech Recognition |
![]() |
MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes |
![]() |
FAST-RIR: FAST NEURAL DIFFUSE ROOM IMPULSE RESPONSE GENERATOR |
![]() |
IR-GAN: Room impulse response generator for far-field speech recognition |
![]() |
TS-RIR: Translated synthetic room impulse responses for speech augmentation |
![]() |
IMPROVING REVERBERANT SPEECH SEPARATION WITH MULTI-STAGE TRAINING AND CURRICULUM LEARNING |
![]() |
Moving Object Based Collision-Free Video Synopsis |
![]() |
University of Maryland - College Park, College Park, MD, USA |
![]() |
University of Moratuwa, Moratuwa, Sri Lanka |
![]() |
Research Intern |
![]() |
Research Scientist Intern |
![]() |
Research Intern |
![]() |
Engineer |
![]() |
Research Intern |
ENEE 245: Digital Circuits and Systems Laboratory |