Emotion recognition in speech using neural networks

被引：183

作者：

Nicholson, J ^{[1
]}

Takahashi, K ^{[1
]}

Nakatsu, R ^{[1
]}

机构：

[1] ATR, Media Integrat & Commun Res Labs, Kyoto 6190288, Japan

来源：

NEURAL COMPUTING & APPLICATIONS | 2000年 / 9卷 / 04期

关键词：

context independence; emotion recognition; neural networks; speaker independent; speech;

D O I：

10.1007/s005210070006

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Emotion recognition in speech is a topic on which little research has been done to-date, In this paper we discuss why emotion recognition in speech is a significant and applicable research topic, and present a system for emotion recognition using one-class-in-one neural networks. By using a large database of phoneme balanced words, our system is speaker- and context-independent. We achieve a recognition rate of approximately 50% when testing eight emotions.

引用

页码：290 / 296

页数：7

共 9 条

[1]

Kohonen T., 1995, SELF ORG MAPS

[2]

Markel J. D., 1976, LINEAR PREDICTION SP

[3]

MCGILLOWAY S, 1995, P 13 INT C PHON SCI, V1, P250

[4]

MOZZICONACCI S, 1995, P 13 INT C PHON SCI, V1, P178

[5] TOWARD THE SIMULATION OF EMOTION IN SYNTHETIC SPEECH - A REVIEW OF THE LITERATURE ON HUMAN VOCAL EMOTION [J].

MURRAY, IR ;

ARNOTT, JL .

JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1993, 93 (02) :1097-1108

[6] Construction of interactive movie system for multi-person participation [J].

Nakatsu, R ;

Tosa, N ;

Ochi, T .

IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA COMPUTING AND SYSTEMS, PROCEEDINGS, 1998, :228-232

[7] Artificial neural networks to systems, man, and cybernetics: Characteristics, structures, and applications [J].

Obaidat, MS .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1998, 28 (04) :489-495

[8]

SHEREN KR, 1995, P ICHPS 95, V3, P90

[9]

SHEREN KR, 1995, P ICHPS 95, V1, P182

← 1 →