Locality Preserved Joint Nonnegative Matrix Factorization for Speech Emotion Recognition

Seksan MATHULAPRANGSAN
Yuan-Shan LEE
Jia-Ching WANG

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E102-D    No.4    pp.821-825
Publication Date: 2019/04/01
Publicized: 2019/01/28
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2018DAL0002
Type of Manuscript: Special Section LETTER (Special Section on Data Engineering and Information Management)
Category: 
Keyword: 
NMF,  joint dictionary learning,  locality preserving,  speech emotion recognition,  information extraction,  

Full Text: PDF(1.1MB)>>
Buy this Article



Summary: 
This study presents a joint dictionary learning approach for speech emotion recognition named locality preserved joint nonnegative matrix factorization (LP-JNMF). The learned representations are shared between the learned dictionaries and annotation matrix. Moreover, a locality penalty term is incorporated into the objective function. Thus, the system's discriminability is further improved.


open access publishing via