activity
20222026
most citedAn efficient encoder-decoder architecture with top-down attention for speech separation

16 citations · 36 across the 14 of their papers we have counts for

collaborators
Showing 2023 · eess.ASShow all

1 paper · 2 filters

eess.AS2023

Audio-Visual Speech Separation in Noisy Environments with a Lightweight Iterative Model

Héctor Martel, Julius Richter, Kai Li +2

We propose Audio-Visual Lightweight ITerative model (AVLIT), an effective and lightweight neural network that uses Progressive Learning (PL) to perform audio-visual speech separati…