Speech Enhancement Method in Aircraft Cockpit Voice Background
LEI Ming1, 2;Cen Hong-bing2; Li Xue-ren3
(1.the 95340th unit of air force, Tianyang 533616, China;2. College of Engineering, Air Force Engineering University, Xian 710038, China;3. Scientific Research Department, Air Force Engineering University, Xian 710051, China)
Abstract:It is very important to flight accident investigation that speech information in aircraft cockpit voice background is efficiently extracted. A speech enhancement method suiting the aircraft cockpit voice background was proposed. We choose CHI PDF as prior distribution for the statistical model of clean speech magnitude, the minimum mean-square error short time spectral amplitude (MMSE-STSA) estimator was utilized to estimate clean speech spectral magnitude, the share function was used to give different emphasis on errors of small amplitudes in relation to large amplitude in the error estimation function. In order to achieve the balance between noise reduction and speech distortion, we choose the parameters of clean speech spectral estimation in the cockpit voice background by simulation experiments incorporating with the objective assessment of speech quality. Finally, in order to validate the effectiveness of proposed method, the comparison experiments between the classic methods and the proposed method were carried out.