Audio-Visual Model Distillation Using Acoustic Images

04/16/2019
by   Andrés F. Pérez, et al.
6

In this paper, we investigate how to learn rich and robust feature representations for audio classification from visual data and a novel audio data modality, namely acoustic images. Former models learn audio representations from raw signals or spectral data acquired by a single microphone, with remarkable results in classification and retrieval. However, such representations are not so robust towards variable environmental sound conditions. We tackle this drawback by exploiting a new multimodal labeled action recognition dataset acquired by a hybrid audio-visual sensor that provides RGB video, raw audio signals, and spatialized acoustic data, also known as acoustic images, where the visual and acoustic images are aligned in space and synchronized in time. Using this richer information, we train audio deep learning models in a teacher-student fashion. In particular, we distill knowledge into audio networks from both visual and acoustic image teachers. Our experiments suggest that the learned representations are more powerful and have better generalization capabilities than the features learned from models trained using just visual or single-microphone audio data.

READ FULL TEXT

page 1

page 4

page 12

page 13

page 14

research
10/27/2016

SoundNet: Learning Sound Representations from Unlabeled Video

We learn rich natural sound representations by capitalizing on large amo...
research
08/14/2023

AudioFormer: Audio Transformer learns audio feature representations from discrete acoustic codes

We propose a method named AudioFormer,which learns audio feature represe...
research
11/15/2021

Metric-based multimodal meta-learning for human movement identification via footstep recognition

We describe a novel metric-based learning approach that introduces a mul...
research
11/15/2019

Cross-modal supervised learning for better acoustic representations

Obtaining large-scale human-labeled datasets to train acoustic represent...
research
11/09/2018

Identify, locate and separate: Audio-visual object extraction in large video collections using weak supervision

We tackle the problem of audiovisual scene analysis for weakly-labeled d...
research
08/20/2019

AI for Earth: Rainforest Conservation by Acoustic Surveillance

Saving rainforests is a key to halting adverse climate changes. In this ...

Please sign up or login with your details

Forgot password? Click here to reset