Embodied Audio Intelligence: Foundations, Capabilities, and Opportunities
Year: 2026
Type: preprint
Abstract: Embodied intelligence requires perception, reasoning, action, and interaction, yet existing systems predominantly rely on vision, text, and proprioception. Audio offers complementary evidence about environments and human intentions, but research remains fragmented. From a novel perspective linking auditory roles to behavioral functions, this survey establishes the first unified framework for embodied audio intelligence. It brings physical, semantic, and socio-affective capabilities into a common account of perception, reasoning, and interaction through continuous auditory feedback loops. By synthesizing foundations, methods, applications, and evaluation resources, the survey identifies challenges and establishes a systematic research agenda for advancing robust, adaptive, and interactive embodied audio intelligence.
Source: Preprints.org
Authors: Wentao Lei, Tianxin Xie, Kai Jiang, Hui Xiong, Li Liu
Language: English
Topic: Speech and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7225830707
Cites:
Cited by:
Related to: