Title :
Informative acoustic feature selection on microphone array wiener filtering for collecting target source on sports ground
Author :
Yuma Koizumi;Kenta Niwa;Yusuke Hioka;Kazunori Kobayashi;Hitoshi Ohmuro
Author_Institution :
NTT Media Intelligence Laboratories, Tokyo, Japan
Abstract :
We propose a Wiener filter design method for collecting target sources on a noisy sports field. Because the noise on a sports field, e.g., cheering from the audience, arrives from the same direction as that of the targeted source, it is difficult to accurately design a Wiener filter by simply using spatial cues. This study focused on a combination of spatial cues and acoustic feature modeling. The Wiener filter using our method was designed using a Gaussian-mixture-model-based mapping function with automatically selected informative acoustic features from pre-enhanced observation using spatial cues. Through experiments using two-directional microphones on a mock sports field, it was confirmed that the proposed method outperformed previous methods that used either spatial cues or acoustic feature modeling only.
Keywords :
"Acoustics","Microphones","Signal to noise ratio","Arrays","Noise measurement","Estimation"
Conference_Titel :
Applications of Signal Processing to Audio and Acoustics (WASPAA), 2015 IEEE Workshop on
DOI :
10.1109/WASPAA.2015.7336949