The reviewed record of science sign in
Pith

arxiv: 2105.04488 · v1 · pith:6CP647KM · submitted 2021-05-10 · cs.SD · cs.LG· eess.AS

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

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:6CP647KMrecord.jsonopen to challenge →

classification cs.SD cs.LGeess.AS
keywords speakeragentenvironmentlearningreinforcementdeepnavigateroom
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.