Due to the uniqueness of the sound mechanism of birds, they have typical non-stationary and nonlinear characteristics. This paper proposed a new acousic feature, HHT-MFCC, combined the HHT transformation and MFCC method, aiming at the dynamic instantaneousness of bird sounds. This method, firstly, uses the ensemble empirical mode decomposition EEMD to decompose the bird sounds into a number of intrinsic modal functions IMFs, and then adopts the Hilbert transform to obtain the Hilbert marginal spectrum of each IMF, at last applies the mel-scale filter to complete the feature extraction of HHT-MFCC. The experiment extracts HHT-MFCC from 9 kinds of cranes in China to cluster. Three indexes of cluster evaluation are used to evaluate the feautre HHT-MFCC and MFCC. The results show that the HHT-MFCC feature is 10% higher in RI index than MFCC, 9% higher in JC index, and 4% higher in FMI index.

In view of the characteristics of ethnic original ecological music and the limitation of human ear’s understanding of hearing. This paper presents a MFCC feature extraction method based on HHT transformation. In this method, the ethnic original ecological music signals were decomposed into several inherent mode functions (IMFs) by EEMD and Hilbert transform, in which the Hilbert marginal spectrum of each IMF was used to complete the feature extraction of HHTMFCC through the MEL scale filter. The experiment collected 13 kinds of original ecological music of ethnic minorities in Yunnan. Based on the feature extraction results of HHTMFCC, Kmeans clustering analysis method was adopted to compare and analyze the clustering effect of HHTMFCC. The experimental results showed that the HHTMFCC feature was 0.49 higher than that of MFCC in the Purity index, 1.2 lower than that of Entropy index, and 3% higher than that of F index. The experimental results show that the HHTMFCC features extracted from ethnic original music are better than the traditional MFCC features.

No abstract