activity
20222026
most citedLook Once to Hear: Target Speech Hearing with Noisy Examples

25 citations · 54 across the 14 of their papers we have counts for

collaborators
Showing eess.ASShow all

1 paper · 1 filter

eess.AS2025

SoundSculpt: Direction and Semantics Driven Ambisonic Target Sound Extraction

Tuochao Chen, D Shin, Hakan Erdogan +1

This paper introduces SoundSculpt, a neural network designed to extract target sound fields from ambisonic recordings. SoundSculpt employs an ambisonic-in-ambisonic-out architectur…