We are excited to announce that our paper “Co-attention-guided bilinear model for echo-based depth estimation” has been accepted to ICASSP2022.
Echoes reflect a geometric structure of a scene surrounding a sound source. In this paper, we address the problem of estimating depth maps of indoor scenes based on echoes. First, we experimentally show that fusing multiple acoustic features, especially spectrogram and angular spectrum, can improve estimation accuracy. We then propose a novel model that can obtain a compact fused feature while capturing the quadratic correlation both intra- and inter-features. Thorough evaluations on two datasets demonstrate the superiority of the proposed method over state-of-the-art echo-based depth estimation and feature fusion methods.
We will disclose the details of the proposed method later.