wind noise
Recently Published Documents


TOTAL DOCUMENTS

446
(FIVE YEARS 65)

H-INDEX

18
(FIVE YEARS 3)

Author(s):  
Wei-Hung Liu ◽  
Yen-Ting Lai ◽  
Kai-Wen Liang ◽  
Jia-Ching Wang ◽  
Pao-Chi Chang

2021 ◽  
Author(s):  
Keisuke Imoto

Sounds recorded with smartphones or IoT devices often have partially unreliable observations caused by clipping, wind noise, and completely missing parts due to microphone failure and packet loss in data transmission over the network. In this paper, we investigate the impact of the partially missing channels on the performance of acoustic scene classification using multichannel audio recordings, especially for a distributed microphone array. Missing observations cause not only losses of time-frequency and spatial information on sound sources but also a mismatch between a trained model and evaluation data. We thus investigate how a missing channel affects the performance of acoustic scene classification in detail. We also propose simple data augmentation methods for scene classification using multichannel observations with partially missing channels and evaluate the scene classification performance using the data augmentation methods.


2021 ◽  
Vol 150 (4) ◽  
pp. A103-A103
Author(s):  
Richard Raspet ◽  
Craig J. Hickey ◽  
Md A. Samad

2021 ◽  
Vol 150 (4) ◽  
pp. A104-A105
Author(s):  
Mylan R. Cook ◽  
Kent L. Gee ◽  
Mark K. Transtrum ◽  
Shane V. Lympany ◽  
Matt Calton

2021 ◽  
Author(s):  
Kai Aizawa ◽  
Masashi Komada ◽  
Hidenori Morita ◽  
Richard DeJong ◽  
Steve Sorenson

Sign in / Sign up

Export Citation Format

Share Document