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.
Seksan MATHULAPRANGSAN
National Central University
Yuan-Shan LEE
National Central University
Jia-Ching WANG
National Central University,Pervasive Artificial Intelligence Research (PAIR) Labs
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Seksan MATHULAPRANGSAN, Yuan-Shan LEE, Jia-Ching WANG, "Locality Preserved Joint Nonnegative Matrix Factorization for Speech Emotion Recognition" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 4, pp. 821-825, April 2019, doi: 10.1587/transinf.2018DAL0002.
Abstract: 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.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018DAL0002/_p
Copy
@ARTICLE{e102-d_4_821,
author={Seksan MATHULAPRANGSAN, Yuan-Shan LEE, Jia-Ching WANG, },
journal={IEICE TRANSACTIONS on Information},
title={Locality Preserved Joint Nonnegative Matrix Factorization for Speech Emotion Recognition},
year={2019},
volume={E102-D},
number={4},
pages={821-825},
abstract={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.},
keywords={},
doi={10.1587/transinf.2018DAL0002},
ISSN={1745-1361},
month={April},}
Copy
TY - JOUR
TI - Locality Preserved Joint Nonnegative Matrix Factorization for Speech Emotion Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 821
EP - 825
AU - Seksan MATHULAPRANGSAN
AU - Yuan-Shan LEE
AU - Jia-Ching WANG
PY - 2019
DO - 10.1587/transinf.2018DAL0002
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2019
AB - 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.
ER -