Title | ||
---|---|---|
Time-scale wavelet scattering using hyperbolic tangent function for vessel sound classification. |
Abstract | ||
---|---|---|
We introduce a time-frequency scattering method using hyperbolic tangent function for vessel sound classification. The sound data is wavelet transformed using a two channel filter-bank and filter-bank outputs are scattered using tanh function. A feature vector similar to mel-scale cepstrum is obtained after a wavelet packed transform-like structure approximating the mel-frequency scale. Feature vectors of vessel sounds are classified using a support vector machine (SVM). Experimental results are presented and the new feature extraction method produces better classification results than the ordinary Mel-Frequency Cepstral Coefficients (MFCC) vectors. |
Year | Venue | Keywords |
---|---|---|
2017 | European Signal Processing Conference | Vessel Sound Classification,Time-frequency Representation,Scattering Filter-bank,Hyperbolic Tangent Function |
Field | DocType | ISSN |
Mel-frequency cepstrum,Feature vector,Pattern recognition,Cepstrum,Support vector machine,Feature extraction,Hyperbolic function,Artificial intelligence,Mathematics,Wavelet,Wavelet transform | Conference | 2076-1465 |
Citations | PageRank | References |
0 | 0.34 | 3 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gokmen Can | 1 | 0 | 0.34 |
Cem Emre Akbas | 2 | 0 | 1.69 |
A. Enis Çetin | 3 | 871 | 118.56 |