Graph Learning Based Speaker Independent Speech Emotion Recognition
In this paper, the algorithm based on graph learning and graph embedding framework, Speaker-Penalty Graph Learning (SPGL), is proposed in the research of speech emotion recognition to solve the problems caused by different speakers. Graph embedding framework theory is used to construct the dimensi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Stefan cel Mare University of Suceava
2014-05-01
|
| Series: | Advances in Electrical and Computer Engineering |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.4316/AECE.2014.02003 |
| _version_ | 1819043647629295616 |
|---|---|
| author | XU, X. HUANG, C. WU, C. WANG, Q. ZHAO, L. |
| author_facet | XU, X. HUANG, C. WU, C. WANG, Q. ZHAO, L. |
| author_sort | XU, X. |
| collection | DOAJ |
| description | In this paper, the algorithm based on graph learning and graph embedding framework, Speaker-Penalty Graph Learning (SPGL),
is proposed in the research of speech emotion recognition to solve the problems caused by different speakers. Graph embedding
framework theory is used to construct the dimensionality reduction stage of speech emotion recognition. Special penalty
and intrinsic graphs of the graph embedding framework is proposed to penalize the impacts from different speakers in the
task of speech emotion recognition. The original speech emotion features are extracted by various categories, reflecting
different characteristics of each speech sample. According to the experiments in speech emotion corpus using different
classifiers, the proposed method with linear and kernelized mapping forms can both achieve relatively better performance
than the state-of-the-art dimensionality reduction methods. |
| first_indexed | 2024-12-21T10:00:07Z |
| format | Article |
| id | doaj.art-a50df1e83b80404282a1339d586e83cc |
| institution | Directory Open Access Journal |
| issn | 1582-7445 1844-7600 |
| language | English |
| last_indexed | 2024-12-21T10:00:07Z |
| publishDate | 2014-05-01 |
| publisher | Stefan cel Mare University of Suceava |
| record_format | Article |
| series | Advances in Electrical and Computer Engineering |
| spelling | doaj.art-a50df1e83b80404282a1339d586e83cc2022-12-21T19:07:57ZengStefan cel Mare University of SuceavaAdvances in Electrical and Computer Engineering1582-74451844-76002014-05-01142172210.4316/AECE.2014.02003Graph Learning Based Speaker Independent Speech Emotion RecognitionXU, X.HUANG, C.WU, C.WANG, Q.ZHAO, L.In this paper, the algorithm based on graph learning and graph embedding framework, Speaker-Penalty Graph Learning (SPGL), is proposed in the research of speech emotion recognition to solve the problems caused by different speakers. Graph embedding framework theory is used to construct the dimensionality reduction stage of speech emotion recognition. Special penalty and intrinsic graphs of the graph embedding framework is proposed to penalize the impacts from different speakers in the task of speech emotion recognition. The original speech emotion features are extracted by various categories, reflecting different characteristics of each speech sample. According to the experiments in speech emotion corpus using different classifiers, the proposed method with linear and kernelized mapping forms can both achieve relatively better performance than the state-of-the-art dimensionality reduction methods.http://dx.doi.org/10.4316/AECE.2014.02003speech emotion recognitionspeaker penalty graph learninggraph embedding frameworkdimensionality reduction |
| spellingShingle | XU, X. HUANG, C. WU, C. WANG, Q. ZHAO, L. Graph Learning Based Speaker Independent Speech Emotion Recognition Advances in Electrical and Computer Engineering speech emotion recognition speaker penalty graph learning graph embedding framework dimensionality reduction |
| title | Graph Learning Based Speaker Independent Speech Emotion Recognition |
| title_full | Graph Learning Based Speaker Independent Speech Emotion Recognition |
| title_fullStr | Graph Learning Based Speaker Independent Speech Emotion Recognition |
| title_full_unstemmed | Graph Learning Based Speaker Independent Speech Emotion Recognition |
| title_short | Graph Learning Based Speaker Independent Speech Emotion Recognition |
| title_sort | graph learning based speaker independent speech emotion recognition |
| topic | speech emotion recognition speaker penalty graph learning graph embedding framework dimensionality reduction |
| url | http://dx.doi.org/10.4316/AECE.2014.02003 |
| work_keys_str_mv | AT xux graphlearningbasedspeakerindependentspeechemotionrecognition AT huangc graphlearningbasedspeakerindependentspeechemotionrecognition AT wuc graphlearningbasedspeakerindependentspeechemotionrecognition AT wangq graphlearningbasedspeakerindependentspeechemotionrecognition AT zhaol graphlearningbasedspeakerindependentspeechemotionrecognition |