Speech emotion classification using multiple kernel Gaussian process

Chen, Sih-Huei; Wang, Jia-Ching; Hsieh, Wen-Chi; Chin, Yu-Hao; Ho, Chin-Wen; Wu, Chung-Hsien

doi:10.1109/apsipa.2016.7820708

Cited by 6 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, from Table 3 Furthermore, the performance of the proposed SER system is compared with different works in the Table 4 for EMO-DB and Table 5 for IEMOCAP in terms of the number of optimized features and classification accuracy performance measures. In [46], semi-NMF with k-means clustering initialization was used to transform feature sets, which were further combined with the original dataset to obtain a total of 72 features for SER obtaining 77.74%…”

Section: Resultsmentioning

confidence: 99%

“…Similarly, from Table 3 for the IEMOCAP database, the highest accuracy is achieved with the feature fusion of the optimized MFCC, LPCC, and TEO-AutoCorr features with 53 features obtaining 83.2% accuracy using SVM and 78% accuracy using the Furthermore, the performance of the proposed SER system is compared with different works in the Table 4 for EMO-DB and Table 5 for IEMOCAP in terms of the number of optimized features and classification accuracy performance measures. In [46], semi-NMF with k-means clustering initialization was used to transform feature sets, which were further combined with the original dataset to obtain a total of 72 features for SER obtaining 77.74% accuracy. In [47][48][49][50][51][52], different optimizing and feature selection techniques, namely enhanced kernel isometric mapping, the modified supervised locally linear embedding algorithm, sparse partial least squares regression, sequential floating forward selection, the scaled conjugate gradient, and principal component analysis, were used for improving the classification accuracy by reducing the feature set dimension.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Speech emotion recognition using semi-NMF feature optimization

Bandela¹,

Kumar²

2019

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

In recent times, much research is progressing forward in the field of speech emotion recognition (SER). Many SER systems have been developed by combining different speech features to improve their performances. As a result, the complexity of the classifier increases to train this huge feature set. Additionally, some of the features could be irrelevant in emotion detection and this leads to a decrease in the emotion recognition accuracy. To overcome this drawback, feature optimization can be performed on the feature sets to obtain the most desirable emotional feature set before classifying the features. In this paper, semi-nonnegative matrix factorization (semi-NMF) with singular value decomposition (SVD) initialization is used to optimize the speech features. The speech features considered in this work are mel-frequency cepstral coefficients, linear prediction cepstral coefficients, and Teager energy operator-autocorrelation (TEO-AutoCorr).This work uses k-nearest neighborhood and support vector machine (SVM) for the classification of emotions with a 5-fold cross-validation scheme. The datasets considered for the performance analysis are EMO-DB and IEMOCAP. The performance of the proposed SER system using semi-NMF is validated in terms of classification accuracy. The results emphasize that the accuracy of the proposed SER system is improved remarkably upon using the semi-NMF algorithm for optimizing the feature sets compared to the baseline SER system without optimization.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Speech emotion recognition using semi-NMF feature optimization

Bandela¹,

Kumar²

2019

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

show abstract

“…It can be seen from Figure 4 (2) Verification of APFOA-MKGPR Four benchmark functions are used to verify the prediction accuracy of the proposed APFOA-MKGPR model, which is compared with other four models: GPR, BMA-MKGPR in Yu et al (2013b), LG-MKGPR in Chen et al (2017), and MKGPR in Archambeau and Bach (2010). 1000 samples are randomly generated and used as the training data, and other 100 samples are randomly generated and used as the testing data.…”

Section: Experiments and Discussionmentioning

confidence: 99%

“…Tian et al (2016) adopted a mixed kernel function with a combination of the squared exponential kernel and the rational quadratic kernel to construct the multi-kernel function in GPR. Chen et al (2017) used a combination of the linear kernel and radial basis function kernel to form a mixed kernel function of GPR. Ding et al (2017) presented a new multi-resolution kernel approximation algorithm for GPR.…”

Section: Introductionmentioning

confidence: 99%

Soft sensor for the moisture content of crude oil based on multi-kernel Gaussian process regression optimized by an adaptive variable population fruit fly optimization algorithm

Han

et al. 2019

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

In the practical oilfield production, it has great significance to realize timely and accurate measurement of the moisture content of crude oil. However, there are some drawbacks in the traditional measurement methods, such as: non-real time, high cost, labor-consume, vulnerability to environmental impacts, and so on. In order to solve these problems, a soft sensor model based on multi-kernel Gaussian process regression optimized by an adaptive variable population fruit fly optimization algorithm (APFOA-MKGPR) is presented in this paper. A multiple kernels-based Gaussian process regression method is utilized to deal with the practical production process characterised by multiple operating phases, noises, strong nonlinearity and dynamic. In the multi-kernel function, many parameters (five hyper-parameters in the multi-kernel function and three weights of each kernel function) need to be accurately given, which is difficult to be effectively optimized by the maximum likelihood estimation. So, a swarm intelligence-based adaptive variable population fruit fly optimization algorithm (APFOA) is proposed to train the best model parameters. A novel adaptive variable population mechanism is developed to adaptively adjust the population size and the random flight distance during the iterations, which can realize a combination of the global searching and the local searching for the optimal solutions. The proposed method is verified by four benchmark functions and the actual production data of one oil well, and experimental results show the effectiveness for accurate prediction of the moisture content of crude oil.

show abstract

“…Some researchers have also suggested different classifiers; in the brain emotional learning model (BEL) (Mustaqeem et al (2020)), a multilayer perceptron (MLP) and adaptive neuro-fuzzy inference system are combined for SER. The multikernel Gaussian process (GP) (Chen et al (2016b)) is another proposed classification strategy with two related notions. These provide for learning in the algorithm by combining two functions: the radial basis function (RBF) and the linear kernel function.…”

mentioning

confidence: 99%

Peer Review #1 of "Effect on speech emotion classification of a feature selection approach using a convolutional neural network (v0.1)"

2021

View full text Add to dashboard Cite

Speech emotion classification using multiple kernel Gaussian process

Cited by 6 publications

References 12 publications

Speech emotion recognition using semi-NMF feature optimization

Speech emotion recognition using semi-NMF feature optimization

Soft sensor for the moisture content of crude oil based on multi-kernel Gaussian process regression optimized by an adaptive variable population fruit fly optimization algorithm

Peer Review #1 of "Effect on speech emotion classification of a feature selection approach using a convolutional neural network (v0.1)"

Contact Info

Product

Resources

About