Locality preserved joint nonnegative matrix factorization for speech emotion recognition

Seksan Mathulaprangsan; Yuan Shan Lee; Jia Ching Wang

doi:10.1587/transinf.2018DAL0002

Locality preserved joint nonnegative matrix factorization for speech emotion recognition

Seksan Mathulaprangsan
, Yuan Shan Lee
, Jia Ching Wang

Research output: Contribution to journal › Article › peer-review

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.

Original language	English
Pages (from-to)	821-825
Number of pages	5
Journal	IEICE Transactions on Information and Systems
Volume	E102D
Issue number	4
DOIs	https://doi.org/10.1587/transinf.2018DAL0002
State	Published - 1 Apr 2019

Keywords

Information extraction
Joint dictionary learning
Locality preserving
NMF
Speech emotion recognition

Access to Document

10.1587/transinf.2018DAL0002

Deep Intelligence Based Spoken Language Processing( II )
Wang, J.-C. (PI)
1/01/19 → 31/12/19
Project: Research

Cite this

@article{a69416f6bb684d11b1f909b1be4a3204,

title = "Locality preserved joint nonnegative matrix factorization for speech emotion recognition",

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{\textquoteright}s discriminability is further improved.",

keywords = "Information extraction, Joint dictionary learning, Locality preserving, NMF, Speech emotion recognition",

author = "Seksan Mathulaprangsan and Lee, \{Yuan Shan\} and Wang, \{Jia Ching\}",

note = "Publisher Copyright: Copyright {\textcopyright} 2019 The Institute of Electronics, Information and Communication Engineers.",

year = "2019",

month = apr,

day = "1",

doi = "10.1587/transinf.2018DAL0002",

language = "???core.languages.en\_GB???",

volume = "E102D",

pages = "821--825",

journal = "IEICE Transactions on Information and Systems",

issn = "0916-8532",

number = "4",

}

TY - JOUR

T1 - Locality preserved joint nonnegative matrix factorization for speech emotion recognition

AU - Mathulaprangsan, Seksan

AU - Lee, Yuan Shan

AU - Wang, Jia Ching

PY - 2019/4/1

Y1 - 2019/4/1

N2 - 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.

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.

KW - Information extraction

KW - Joint dictionary learning

KW - Locality preserving

KW - NMF

KW - Speech emotion recognition

UR - https://www.scopus.com/pages/publications/85063996745

U2 - 10.1587/transinf.2018DAL0002

DO - 10.1587/transinf.2018DAL0002

M3 - 期刊論文

AN - SCOPUS:85063996745

SN - 0916-8532

VL - E102D

SP - 821

EP - 825

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

IS - 4

ER -

Locality preserved joint nonnegative matrix factorization for speech emotion recognition

Abstract

Keywords

Access to Document

Fingerprint

Projects

Deep Intelligence Based Spoken Language Processing( II )

Cite this