A Deep Reinforcement Learning Approach to Audio-Based Navigation in a Multi-Speaker Environment

Abstract

In this work we use deep reinforcement learning to create an autonomous agent that can navigate in a two-dimensional space using only raw auditory sensory information from the environment, a problem that has received very little attention in the reinforcement learning literature. Our experiments show that the agent can successfully identify a particular target speaker among a set of $N$ predefined speakers in a room and move itself towards that speaker, while avoiding collision with other speakers or going outside the room boundaries. The agent is shown to be robust to speaker pitch shifting and it can learn to navigate the environment, even when a limited number of training utterances are available for each speaker.

To be published in ICASSP 2021

References in corpus (6)

• Unity: A General Platform for Intelligent Agents
• Deep Neural Networks for Multiple Speaker Detection and Localization
• Towards End-to-End Acoustic Localization using Deep Learning: from Audio Signal to Source Position Coordinates
• Multi-Speaker Localization Using Convolutional Neural Network Trained with Noise
• Deep learning methods in speaker recognition: a review
• Do Autonomous Agents Benefit from Hearing?

Cited by in corpus (4)

• Improving Post-Processing of Audio Event Detectors Using Reinforcement Learning
• Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning
• Audio-Driven Reinforcement Learning for Head-Orientation in Naturalistic Environments
• A Deep Reinforcement Learning Approach for Audio-based Navigation and Audio Source Localization in Multi-speaker Environments