Sensors & Transducers (Sep 2014)
Compressed Sensing Adaptive Speech Characteristics Research
Abstract
The sparsity of the speech signals is utilized in the DCT domain. According to the characteristics of the voice which may be separated into voiceless and voiced one, an adaptive measurement speech recovery method is proposed in this paper based on compressed sensing. First, the observed points are distributed based on the voicing energy ratio which the entire speech segment occupies. Then the speech segment is enflamed, if the frame is an unvoiced speech, the numbers of measurement can be allocated according to its zeros and energy rate. If the frame is voiced speech, the numbers of measurement can be allocated according to its energy. The experiment results shows that the performance of speech signal based on the method above is superior to utilize compress sensing directly.