Depth Infused Binaural Audio Generation using Hierarchical Cross-Modal Attention

TL;DR

This paper introduces a hierarchical cross-modal attention model that leverages image and depth features to enhance binaural audio generation from mono recordings, improving immersion in AR/VR applications.

Contribution

The work proposes a novel encoder-decoder architecture that incorporates depth information with image features using hierarchical attention for better binaural audio synthesis.

Findings

Adding depth features improves audio quality both qualitatively and quantitatively.

The hierarchical attention mechanism effectively fuses visual and depth cues with audio features.

The approach outperforms previous mono-to-binaural conversion methods.

Abstract

Binaural audio gives the listener the feeling of being in the recording place and enhances the immersive experience if coupled with AR/VR. But the problem with binaural audio recording is that it requires a specialized setup which is not possible to fabricate within handheld devices as compared to traditional mono audio that can be recorded with a single microphone. In order to overcome this drawback, prior works have tried to uplift the mono recorded audio to binaural audio as a post processing step conditioning on the visual input. But all the prior approaches missed other most important information required for the task, i.e. distance of different sound producing objects from the recording setup. In this work, we argue that the depth map of the scene can act as a proxy for encoding distance information of objects in the scene and show that adding depth features along with image features improves the performance both qualitatively and quantitatively. We propose a novel encoder-decoder architecture, where we use a hierarchical attention mechanism to encode the image and depth feature extracted from individual transformer backbone, with audio features at each layer of the decoder.