An embedded multichannel sound acquisition system for drone audition



Recordings


Array Setup1: The human is talking toward the backside of the hovering drone.

setup1
Original Enhanced


Array Setup2: The human is talking toward the frontside of the hovering drone.

setup2
Original Enhanced


.

Speech recognition results

We pass the noisy and processed audio to a simple speech recognition engine (Google Translate with voice input), the recognition result is given in the table below.


recognition