Speech Emotion Recognition Based on Modified ReliefF
As the key of human–computer natural interaction, the research of emotion recognition is of great significance to the development of computer intelligence. In view of the issue that the current emotional feature dimension is too high, which affects the classification performance, this paper proposes...
| الحاوية / القاعدة: | Sensors |
|---|---|
| المؤلفون الرئيسيون: | , , |
| التنسيق: | مقال |
| اللغة: | الإنجليزية |
| منشور في: |
MDPI AG
2022-10-01
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://www.mdpi.com/1424-8220/22/21/8152 |
| _version_ | 1850096304268509184 |
|---|---|
| author | Guo-Min Li Na Liu Jun-Ao Zhang |
| author_facet | Guo-Min Li Na Liu Jun-Ao Zhang |
| author_sort | Guo-Min Li |
| collection | DOAJ |
| container_title | Sensors |
| description | As the key of human–computer natural interaction, the research of emotion recognition is of great significance to the development of computer intelligence. In view of the issue that the current emotional feature dimension is too high, which affects the classification performance, this paper proposes a modified ReliefF feature selection algorithm to screen out feature subsets with smaller dimensions and better performance from high-dimensional features to further improve the efficiency and accuracy of emotion recognition. In the modified algorithm, the selection range of random samples is adjusted; the correlation between features is measured by the maximum information coefficient, and the distance measurement method between samples is established based on the correlation. The experimental results on the eNTERFACE’05 and SAVEE speech emotional datasets show that the features filtered based on the modified algorithm significantly reduce the data dimensions and effectively improve the accuracy of emotion recognition. |
| format | Article |
| id | doaj-art-e07e10bb1e8949eebef54e199fba01d1 |
| institution | Directory of Open Access Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| spelling | doaj-art-e07e10bb1e8949eebef54e199fba01d12025-08-20T00:06:44ZengMDPI AGSensors1424-82202022-10-012221815210.3390/s22218152Speech Emotion Recognition Based on Modified ReliefFGuo-Min Li0Na Liu1Jun-Ao Zhang2College of Communication and Information Engineering, Xi’an University of Science and Technology, Xi’an 710600, ChinaCollege of Communication and Information Engineering, Xi’an University of Science and Technology, Xi’an 710600, ChinaCollege of Communication and Information Engineering, Xi’an University of Science and Technology, Xi’an 710600, ChinaAs the key of human–computer natural interaction, the research of emotion recognition is of great significance to the development of computer intelligence. In view of the issue that the current emotional feature dimension is too high, which affects the classification performance, this paper proposes a modified ReliefF feature selection algorithm to screen out feature subsets with smaller dimensions and better performance from high-dimensional features to further improve the efficiency and accuracy of emotion recognition. In the modified algorithm, the selection range of random samples is adjusted; the correlation between features is measured by the maximum information coefficient, and the distance measurement method between samples is established based on the correlation. The experimental results on the eNTERFACE’05 and SAVEE speech emotional datasets show that the features filtered based on the modified algorithm significantly reduce the data dimensions and effectively improve the accuracy of emotion recognition.https://www.mdpi.com/1424-8220/22/21/8152emotion recognitionfeature selectionmodified ReliefFmaximum information coefficient |
| spellingShingle | Guo-Min Li Na Liu Jun-Ao Zhang Speech Emotion Recognition Based on Modified ReliefF emotion recognition feature selection modified ReliefF maximum information coefficient |
| title | Speech Emotion Recognition Based on Modified ReliefF |
| title_full | Speech Emotion Recognition Based on Modified ReliefF |
| title_fullStr | Speech Emotion Recognition Based on Modified ReliefF |
| title_full_unstemmed | Speech Emotion Recognition Based on Modified ReliefF |
| title_short | Speech Emotion Recognition Based on Modified ReliefF |
| title_sort | speech emotion recognition based on modified relieff |
| topic | emotion recognition feature selection modified ReliefF maximum information coefficient |
| url | https://www.mdpi.com/1424-8220/22/21/8152 |
| work_keys_str_mv | AT guominli speechemotionrecognitionbasedonmodifiedrelieff AT naliu speechemotionrecognitionbasedonmodifiedrelieff AT junaozhang speechemotionrecognitionbasedonmodifiedrelieff |