Name
Abstract | ||
|---|---|---|
This study proposes two classes of speech emotional features extracted from electroglottography (EGG) and speech signal. The power-law distribution coefficients (PLDC) of voiced segments duration, pitch rise duration, and pitch down duration are obtained to reflect the information of vocal folds excitation. The real discrete cosine transform coefficients of the normalized spectrum of EGG and speech signal are calculated to reflect the information of vocal tract modulation. Two experiments are carried out. One is of proposed features and traditional features based on sequential forward floating search and sequential backward floating search. The other is the comparative emotion recognition based on support vector machine. The results show that proposed features are better than those commonly used in the case of speaker-independent and content-independent speech emotion recognition. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1162/NECO_a_00523 | Neural Computation |
Keywords | DocType | Volume |
pitch rise duration,content-independent speech emotion recognition,electroglottography egg,speech signal,comparative emotion recognition,speech emotional feature,segments duration,vocal folds excitation,speech emotional features extraction,floating search,proposed feature | Journal | 25 |
Issue | ISSN | Citations |
12 | 1530-888X | 3 |
PageRank | References | Authors |
0.41 | 30 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Lijiang Chen | 1 | 304 | 23.22 |
| Xia Mao | 2 | 188 | 21.89 |
| Pengfei Wei | 3 | 97 | 10.57 |
| Angelo Compare | 4 | 29 | 3.81 |