DeepAI AI Chat
Log In Sign Up

Audio-Visual Model Distillation Using Acoustic Images

by   Andrés F. Pérez, et al.

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.


page 1

page 4

page 12

page 13

page 14


SoundNet: Learning Sound Representations from Unlabeled Video

We learn rich natural sound representations by capitalizing on large amo...

Self-supervised Learning of Audio Representations from Audio-Visual Data using Spatial Alignment

Learning from audio-visual data offers many possibilities to express cor...

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

We describe a novel metric-based learning approach that introduces a mul...

Cross-modal supervised learning for better acoustic representations

Obtaining large-scale human-labeled datasets to train acoustic represent...

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...

Deep Learning-Based Acoustic Mosquito Detection in Noisy Conditions Using Trainable Kernels and Augmentations

In this paper, we demonstrate a unique recipe to enhance the effectivene...

Code Repositories


Code for the paper: Audio-Visual Model Distillation Using Acoustic Images

view repo