TY - GEN
T1 - Hybrid noise reduction for audio captured by drones
AU - Ahn, Hyohoon
AU - Le, Duc Tai
AU - Dang, Thien Binh
AU - Kim, Siwon
AU - Choo, Hyunseung
N1 - Publisher Copyright:
© 2018 ACM.
PY - 2018/1/5
Y1 - 2018/1/5
N2 - Recently, advances in technology have reduced the sizes, lowered prices, and increased commercial use of drones. In the market, drones have become an inexpensive and accessible way to accomplish many tasks such as filming, surveillance, agriculture, delivery, and broadcasting. Such applications typically require a video recording for their operations. However, due to the noise generated by propellers and rotors of a drone, the quality of sound in a video recorded by the drone is quite limited. In order to solve the noise problem of drones, this paper proposes a novel hybrid noise reduction technique combining Active Noise Control and Spectral subtraction methods. Experimental results show that the proposed technique produces a speech signal with up to 67.5% similarity to the original signal. It outperforms Active Noise Control and Spectral Subtraction with similarities of 53.1% and 39.6%, respectively.
AB - Recently, advances in technology have reduced the sizes, lowered prices, and increased commercial use of drones. In the market, drones have become an inexpensive and accessible way to accomplish many tasks such as filming, surveillance, agriculture, delivery, and broadcasting. Such applications typically require a video recording for their operations. However, due to the noise generated by propellers and rotors of a drone, the quality of sound in a video recorded by the drone is quite limited. In order to solve the noise problem of drones, this paper proposes a novel hybrid noise reduction technique combining Active Noise Control and Spectral subtraction methods. Experimental results show that the proposed technique produces a speech signal with up to 67.5% similarity to the original signal. It outperforms Active Noise Control and Spectral Subtraction with similarities of 53.1% and 39.6%, respectively.
KW - Active noise cancellation
KW - Drones
KW - Internet of things
KW - Noise reduction
KW - Spectral subtraction
UR - https://www.scopus.com/pages/publications/85048431625
U2 - 10.1145/3164541.3175682
DO - 10.1145/3164541.3175682
M3 - Conference contribution
AN - SCOPUS:85048431625
T3 - ACM International Conference Proceeding Series
BT - Proceedings of the 12th International Conference on Ubiquitous Information Management and Communication, IMCOM 2018
PB - Association for Computing Machinery
T2 - 12th International Conference on Ubiquitous Information Management and Communication, IMCOM 2018
Y2 - 5 January 2018 through 7 January 2018
ER -