A Deep Reinforcement Learning Approach for Audio-based Navigation and Audio Source Localization in Multi-speaker Environments

TL;DR

This paper presents a deep reinforcement learning approach using PPO to enable an autonomous agent to navigate and localize audio sources in 3D environments based solely on raw sound, demonstrating effective generalization and transfer.

Contribution

The work introduces a novel application of deep reinforcement learning for audio-based navigation and source localization in simulated 3D environments, with transfer learning capabilities.

Findings

Agent achieves adequate performance in navigation and localization tasks.

The approach generalizes well with limited training data.

Some knowledge transfer occurs between tasks.

Abstract

In this work we apply deep reinforcement learning to the problems of navigating a three-dimensional environment and inferring the locations of human speaker audio sources within, in the case where the only available information is the raw sound from the environment, as a simulated human listener placed in the environment would hear it. For this purpose we create two virtual environments using the Unity game engine, one presenting an audio-based navigation problem and one presenting an audio source localization problem. We also create an autonomous agent based on PPO online reinforcement learning algorithm and attempt to train it to solve these environments. Our experiments show that our agent achieves adequate performance and generalization ability in both environments, measured by quantitative metrics, even when a limited amount of training data are available or the environment parameters shift in ways not encountered during training. We also show that a degree of agent knowledge transfer is possible between the environments.