Real Life Emotion Classification using Spectral Features and Gaussian Mixture Models

被引：5

作者：

Koolagudi, Shashidhar G. ^{[1
]}

Barthwal, Anurag ^{[1
]}

Devliyal, Swati ^{[1
]}

Rao, K. Sreenivasa ^{[2
]}

机构：

[1] Graph Era Univ, Sch Comp, Dehra Dun 248002, Uttarakhand, India

[2] Indian Inst Technol, Kharagpur 721302, W Bengal, India

来源：

INTERNATIONAL CONFERENCE ON MODELLING OPTIMIZATION AND COMPUTING | 2012年 / 38卷

关键词：

emotion classification; spectral features; GMM; MFCC; LPCC; text dependent emotion recognition; text independent emotion recognition; RECOGNITION; SPEECH;

D O I：

10.1016/j.proeng.2012.06.447

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

In this work, spectral features are extracted for speech emotion classification. Mel frequency cepstral coefficients (MFCCs) are used as features. Gaussian mixture models (GMMs) are explored as classifiers. The emotions considered are anger, happy, neutral, sad and surprise. Semi-natural emotional database (Graphic Era University Semi Natural Emotion Speech Corpus) is collected from the dialogues of popular Hindi movies. Average emotion recognition performance, in the case of multiple speaker database is observed to be around 55.60%. Results of male, female, multiple male and multiple female speakers are compared to study the effect of speakers and gender on expression of emotions.

引用

页码：3892 / 3899

页数：8

共 50 条

[41] Vehicle acoustic classification in netted sensor systems using Gaussian mixture models
Necioglu, BF
Christou, CT
George, EB
Jacyna, CM
[J]. SIGNAL PROCESSING, SENSOR FUSION, AND TARGET RECOGNITION XIV, 2005, 5809 : 409 - 419
[42] Speech emotion recognition: Features and classification models
Chen, Lijiang
Mao, Xia
Xue, Yuli
Cheng, Lee Lung
[J]. DIGITAL SIGNAL PROCESSING, 2012, 22 (06) : 1154 - 1160
[43] Comparison of Gaussian mixture and linear mixture models for classification of hyperspectral data
Beaven, SG
Stein, D
Hoff, LE
[J]. IGARSS 2000: IEEE 2000 INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOL I - VI, PROCEEDINGS, 2000, : 1597 - 1599
[44] Speech Emotion Classification via a Modified Gaussian Mixture Model Approach
Hosseini, Zeinab
Ahadi, Seyed Mohammad
Faraji, Neda
[J]. 2014 7TH INTERNATIONAL SYMPOSIUM ON TELECOMMUNICATIONS (IST), 2014, : 487 - 491
[45] Aggregation procedure of Gaussian Mixture Models for additive features
Ridi, Antonio
Gisler, Christophe
Hennebert, Jean
[J]. 2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2016, : 2544 - 2549
[46] Discriminative Model Selection for Gaussian Mixture Models for Classification
Liu, Xiao-Hua
Liu, Cheng-Lin
[J]. 2011 FIRST ASIAN CONFERENCE ON PATTERN RECOGNITION (ACPR), 2011, : 62 - 66
[47] Coding using Gaussian mixture and generalized Gaussian models
Su, JK
Mersereau, RM
[J]. INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, PROCEEDINGS - VOL I, 1996, : 217 - 220
[48] Semantic Scene Classification with Generalized Gaussian Mixture Models
Elguebaly, Tarek
Bouguila, Nizar
[J]. IMAGE ANALYSIS AND RECOGNITION (ICIAR 2015), 2015, 9164 : 159 - 166
[49] Combustion Sound Classification Employing Gaussian Mixture Models
Lupu, E.
Ghiurcau, M. V.
Hodor, V.
Emerich, S.
[J]. PROCEEDINGS OF 2010 IEEE INTERNATIONAL CONFERENCE ON AUTOMATION, QUALITY AND TESTING, ROBOTICS (AQTR 2010), VOLS. 1-3, 2010,
[50] Gaussian Mixture Models for Probabilistic Classification of Breast Cancer
Prabakaran, Indira
Wu, Zhengdong
Lee, Changgun
Tong, Brian
Steeman, Samantha
Koo, Gabriel
Zhang, Paul J.
Guvakova, Marina A.
[J]. CANCER RESEARCH, 2019, 79 (13) : 3492 - 3502

← 1 2 3 4 5 →