Key points are not available for this paper at this time.
Laser Doppler vibrometers (LDVs) as non-contact vibration sensors have an ability of remote voice acquisition. With the assistance of a visual sensor (camera), various targets in the environment, where an audio event takes place, can be selected as reflecting surfaces for collecting acoustic signals by an LDV. The performance of the LDV greatly depends on the vibration characteristics of the selected targets (surfaces) in the scene, on which a laser beam strikes and from which it returns. In this paper, the relations of a target's material and structural properties with its vibration characteristics are studied, and a vibration amplitude model is established. Then the vibration characteristics of several typical surfaces with different materials and structures are explored through both simulations and real-sensor experiments. Based on their responses to the frequencies in the range of human voice, the targets are classified into three categories by the number of fluctuations (zero, one, or two) in their vibration returns in the range of speech. Some short- and long-range experimental results are presented for the speech acquisition from surfaces of these three categories, and their feasibilities in speech acquisition are also evaluated.
Li et al. (Tue,) studied this question.