Speech Emotion Recognition: A Comprehensive Survey

被引：36

作者：

Al-Dujaili, Mohammed Jawad ^{[1
]}

Ebrahimi-Moghadam, Abbas ^{[2
]}

机构：

[1] Univ Kufa, Fac Engn, Dept Elect & Commun, Najaf, Iraq

[2] Ferdowsi Univ Mashhad, Fac Engn, Elect Engn Dept, Mashhad, Iran

来源：

WIRELESS PERSONAL COMMUNICATIONS | 2023年 / 129卷 / 04期

关键词：

Speech; Emotion recognition; Feature extraction; Feature reduction; Classification; Classification composition; FEATURES; IDENTIFICATION; ALGORITHMS; MFCC; GMM;

D O I：

10.1007/s11277-023-10244-3

中图分类号：

TN [电子技术、通信技术];

学科分类号：

0809 ;

摘要：

Speech emotion recognition could be considered a new topic in speech processing where he plays that plays an essential role in human interaction. Emotions are a king of speech that recognizes the three significant aspects of designing the speech emotion recognition system. This article reviews the work on speech emotion recognition and is helpful for further research. Firstly, speech emotion recognition databases are described for evaluating system performance. Secondly, the choice of feature is presented in the speech representation. And third is the design of a suitable class. While the section fourth explains the multiple classifier system and its impact on system. In the fifth part of the article, we review the most important challenges in the system speech emotion recognition. The final results obtained from the system function and its constraints are discussed, and we provide directions to improve speech emotion recognition systems.

引用

页码：2525 / 2561

页数：37

共 125 条

[1] Egyptian Arabic speech emotion recognition using prosodic, spectral and wavelet features [J].

Abdel-Hamid, Lamiaa .

SPEECH COMMUNICATION, 2020, 122 :19-30

[2] Robust Speech Emotion Recognition Using CNN plus LSTM Based on Stochastic Fractal Search Optimization Algorithm [J].

Abdelhamid, Abdel Aziza ;

El-Kenawy, El-Sayed M. ;

Alotaibi, Bandar ;

Amer, Ghadam ;

Abdelkader, Mahmoud Y. ;

Ibrahim, Abdelhameed ;

Eid, Marwa Metwally .

IEEE ACCESS, 2022, 10 :49265-49284

[3] Speech emotion recognition: Emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers [J].

Akcay, Mehmet Berkehan ;

Oguz, Kaya .

SPEECH COMMUNICATION, 2020, 116 :56-76

[4]

Al Dujaili M. J., 2021, Int. J. Elect. Comput. Eng., V11, P1259, DOI 10.11591/ijece.v11i2.pp1259-1264

[5] Novel Approach for Reinforcement the Extraction of ECG Signal for Twin Fetuses Based on Modified BSS [J].

Al-Dujaili, Mohammed Jawad ;

Mezeel, Mushtaq Talib .

WIRELESS PERSONAL COMMUNICATIONS, 2021, 119 (03) :2431-2450

[6] Spoken emotion recognition using hierarchical classifiers [J].

Albornoz, Enrique M. ;

Milone, Diego H. ;

Rufiner, Hugo L. .

COMPUTER SPEECH AND LANGUAGE, 2011, 25 (03) :556-570

[7] Emotion Recognition from Speech Signal in Multilingual [J].

Albu, Corina ;

Lupu, Eugen ;

Arsinte, Radu .

6TH INTERNATIONAL CONFERENCE ON ADVANCEMENTS OF MEDICINE AND HEALTH CARE THROUGH TECHNOLOGY, MEDITECH 2018, 2019, 71 :157-161

[8]

Alghifari M. F., 2018, Indones. J. Electr. Eng. Comput. Sci, V10, P554, DOI 10.11591/ijeecs.v10.i2.pp554-561.

[9] New approach in quantification of emotional intensity from the speech signal: emotional temperature [J].

Alonso, Jesus B. ;

Cabrera, Josue ;

Medina, Manuel ;

Travieso, Carlos M. .

EXPERT SYSTEMS WITH APPLICATIONS, 2015, 42 (24) :9554-9564

[10] Improved speech emotion recognition with Mel frequency magnitude coefficient [J].

Ancilin, J. ;

Milton, A. .

APPLIED ACOUSTICS, 2021, 179

← 1 2 3 4 5 6 7 8 9 10 →