Conference paper Open Access

A ROS Framework for Audio-Based Activity Recognition

Theodoros Giannakopoulos; Georgios Siantikos

Research on robot perception mostly focuses on visual information analytics. Audio-based perception is mostly based
on speech-related information. However, non-verbal information of the audio channel can be equally important in the perception procedure, or at least play a complementary role. This paper presents a framework for audio signal analysis that utilizes the ROS architectural principles. Details on the design and implementation issues of this workflow are described, while classification results are also presented in the context of two use-cases motivated by the task of medical monitoring. The proposed audio analysis framework is provided as an open-source library at github (https://github.com/tyiannak/AUROS).

Files (431.9 kB)
Name Size
CONF43.pdf
md5:bc7fb57e5773ebafd7ee80f597c903bf
431.9 kB Download
39
38
views
downloads
Views 39
Downloads 38
Data volume 16.4 MB
Unique views 39
Unique downloads 35

Share

Cite as