Abstract
This paper presents an online real-time method that enhances human voices included in severely noisy audio signals captured by microphones of a hose-shaped rescue robot. To help a remote operator of such a robot pick up a weak voice of a human buried under rubble, it is crucial to suppress the loud ego-noise caused by the movements of the robot in real time. We tackle this task by using online robust principal component analysis (ORPCA) for decomposing the spectrogram of an observed noisy signal into the sum of low-rank and sparse spectrograms that are expected to correspond to periodic ego-noise and human voices. Using a microphone array distributed on the long body of a hose-shaped robot, ego-noise suppression can be further improved by combining the results of ORPCA applied to the observed signal captured by each microphone. Experiments using a 3-m hose-shaped rescue robot with eight microphones show that the proposed method improves the performance of conventional ego-noise suppression using only one microphone by 7.4 dB in SDR and 17.2 in SIR.
| Original language | English |
|---|---|
| Title of host publication | SSRR 2015 - 2015 IEEE International Symposium on Safety, Security, and Rescue Robotics |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (Print) | 9781509019595 |
| DOIs | |
| Publication status | Published - 2016 Mar 29 |
| Event | IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2015 - West Lafayette, United States Duration: 2015 Oct 18 → 2015 Oct 20 |
Other
| Other | IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2015 |
|---|---|
| Country/Territory | United States |
| City | West Lafayette |
| Period | 15/10/18 → 15/10/20 |
ASJC Scopus subject areas
- Artificial Intelligence
- Control and Systems Engineering
- Safety Research