GDL

Journal from gdlhub / 2022-02-15 16:48:36
Oleh : Abdenour Hacine-Gharbi, Philippe Ravier, King Saud University
Dibuat : 2022-02-15, dengan 0 file

Keyword : Speech emotion recognition, Mutual information, Binning of joint histogram, Features selection, MFCC coefficients, GMM models
Url : http://www.sciencedirect.com/science/article/pii/S1319157819304537
Sumber pengambilan dokumen : web

Mutual information (MI) has been previously used to select the relevant features for the task of speech emotion recognition (SER). However, the procedure does not deliver the optimal number of relevant features. We propose MI based criterion for estimating this number defined as the minimum number of features that explains the variable of the class indices. In order to minimize the MI estimation errors, we also search the best histogram binning choice considering three formulas: Sturges, Scott and LMSE. Four selection strategies MMI, CMI, JMI and TMI have been implemented and applied on 39-features vectors and on large dimension vectors. The feature selection results have been validated on independent text SER system, based on GMM classifier and evaluated on EMO-db database. Results demonstrate that LMSE bin choice gives the best MI estimation and ensures a minimal number of features with slight performance drop. Particularly, using the proposed stopping criterion, the CMI strategy achieves reduction of 48.72% in the case of the 39-features vectors size and 67.86% in the case of large dimension vectors. Moreover, using the recognition rate criterion, the JMI strategy gives a comparable feature reduction with slight improvement of performance but requiring very high computation capabilities.

Deskripsi Alternatif :

Mutual information (MI) has been previously used to select the relevant features for the task of speech emotion recognition (SER). However, the procedure does not deliver the optimal number of relevant features. We propose MI based criterion for estimating this number defined as the minimum number of features that explains the variable of the class indices. In order to minimize the MI estimation errors, we also search the best histogram binning choice considering three formulas: Sturges, Scott and LMSE. Four selection strategies MMI, CMI, JMI and TMI have been implemented and applied on 39-features vectors and on large dimension vectors. The feature selection results have been validated on independent text SER system, based on GMM classifier and evaluated on EMO-db database. Results demonstrate that LMSE bin choice gives the best MI estimation and ensures a minimal number of features with slight performance drop. Particularly, using the proposed stopping criterion, the CMI strategy achieves reduction of 48.72% in the case of the 39-features vectors size and 67.86% in the case of large dimension vectors. Moreover, using the recognition rate criterion, the JMI strategy gives a comparable feature reduction with slight improvement of performance but requiring very high computation capabilities.

Beri Komentar ?#(0) | Bookmark

Properti	Nilai Properti
ID Publisher	gdlhub
Organisasi	King Saud University
Nama Kontak	Herti Yani, S.Kom
Alamat	Jln. Jenderal Sudirman
Kota	Jambi
Daerah	Jambi
Negara	Indonesia
Telepon	0741-35095
Fax	0741-35093
E-mail Administrator	elibrarystikom@gmail.com
E-mail CKO	elibrarystikom@gmail.com