An analysis of human acceptability of recreated voice samples from whispering

Reconstruction of whispering voice into a pseudo-real voice was previously covered by other researchers using statistical processes. We´ve been doing this conversion from a different perspective and using the raw signal data only. As a result we can avoid heavy computation load because our approach does not require the data to be transformed before being analyzed. After some good results obtained in laboratory we´ve questioned ourselves about the quality of the reconstructed samples to real people and the results are presented in this study.