The Complexity Analysis of Voiced and Unvoiced Speech Signal Based on Sample Entropy
Guiqi Sun, Zhenyan Fan, Nikos E. Mastorakis, Stavros D. Kaminaris, Xiaodong Zhuang · 2017
The difference of signal complexity for voiced/unvoiced speech is studied. The sample entropy is estimated for a group of single phoneme pronunciations. The experimental data indicates that voiced and unvoiced pronunciations are different in signal complexity, which proves the effectiveness of the sample entropy feature for voiced/unvoiced classification.