Enhanced multiclass SVM with thresholding fusion for speech-based emotion classification

Yang, Na; Yuan, Jianbo; Zhou, Yun; Demirkol, Ilker; Duan, Zhiyao; Heinzelman, Wendi; Sturge‐Apple, Melissa L.

doi:10.1007/s10772-016-9364-2

Cited by 25 publications

(17 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A novel method for speech emotion recognition has been proposed by [16], which is based on hidden factor analysis, in which the acoustic features are broken down into an emotion specific component and an emotion independent specific component, where later is adopted for classification with improved accuracy. Similar work has also been reported by [17] using Support Vector Machine, combining outputs with a fusion method, to improve accuracy at the cost of dropping some samples by not classifying them. However, [18] have used classifiers such as k-Nearest Neighbor, Linear Discriminant Analysis along with Support Vector Machine for Polish language emotion recognition, with Linear Discriminant Analysis giving best results for five features with accuracy of 80% and Support Vector Machine for fifteen features with accuracy of 78.7%.…”

Section: Related Worksupporting

confidence: 56%

Impact of Feature Extraction and Feature Selection Algorithms on Punjabi Speech Emotion Recognition Using Convolutional Neural Network

Kaur

Singh

2022

ACM Trans. Asian Low-Resour. Lang. Inf. Process.

View full text Add to dashboard Cite

The challenge to refine the spontaneity and productivity of a machine and human coherence, speech emotion recognition has been an overriding area of research. The trustability and fulfillment of such emotion recognition are largely involved with the feature extraction and selection processes. An important role is played in exploring and distinguishing audio content during the feature extraction phase. Also, the features that have been extracted should be tough to a number of disturbances and reliable enough for an adequate classification system. This paper focuses on three main components of a Speech Emotion Recognition (SER) Process. The first one is the optimal feature extraction method for Punjabi SER system. The second one is the use of an appropriate feature selection method that desires to select effectual features from the ones extracted in the first step, and removes the redundant features, to improve the conduct of emotion recognition. The third one is the classification model that has been used further for emotion recognition. So, the scope of this paper is to explain the three main steps of Punjabi SER system, feature extraction, feature selection, and emotion recognition with classifier. The results have been calculated and compared for number of feature set combinations, with and without feature selection process. A total of 10 experiments are carried out and various performance metrics such as precision, recall, F1-score, accuracy, etc. are used to demonstrate the results.

show abstract

Section: Related Worksupporting

confidence: 56%

Impact of Feature Extraction and Feature Selection Algorithms on Punjabi Speech Emotion Recognition Using Convolutional Neural Network

Kaur

Singh

2022

ACM Trans. Asian Low-Resour. Lang. Inf. Process.

View full text Add to dashboard Cite

show abstract

“…A set of methods on speech emotion classification is based on hidden Markov model [15], Gaussian Mixture Model (GMM) [16], Self-Organizing Map (SOM) [17], and neural network [18]. Singular Value Decomposition (SVD) classifier is used in [19], whereas, in [20], ensemble software regression model is proposed for emotion classification. A deep belief network based on high-and low-level features is also proposed for SEC [21].…”

Section: Introductionmentioning

confidence: 99%

Emotion classification from speech signal based on empirical mode decomposition and non-linear features

Krishnan

Raj

Rajangam

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

Emotion recognition system from speech signal is a widely researched topic in the design of the Human–Computer Interface (HCI) models, since it provides insights into the mental states of human beings. Often, it is required to identify the emotional condition of the humans as cognitive feedback in the HCI. In this paper, an attempt to recognize seven emotional states from speech signals, known as sad, angry, disgust, happy, surprise, pleasant, and neutral sentiment, is investigated. The proposed method employs a non-linear signal quantifying method based on randomness measure, known as the entropy feature, for the detection of emotions. Initially, the speech signals are decomposed into Intrinsic Mode Function (IMF), where the IMF signals are divided into dominant frequency bands such as the high frequency, mid-frequency , and base frequency. The entropy measures are computed directly from the high-frequency band in the IMF domain. However, for the mid- and base-band frequencies, the IMFs are averaged and their entropy measures are computed. A feature vector is formed from the computed entropy measures incorporating the randomness feature for all the emotional signals. Then, the feature vector is used to train a few state-of-the-art classifiers, such as Linear Discriminant Analysis (LDA), Naïve Bayes, K-Nearest Neighbor, Support Vector Machine, Random Forest, and Gradient Boosting Machine. A tenfold cross-validation, performed on a publicly available Toronto Emotional Speech dataset, illustrates that the LDA classifier presents a peak balanced accuracy of 93.3%, F1 score of 87.9%, and an area under the curve value of 0.995 in the recognition of emotions from speech signals of native English speakers.

show abstract

“…The proposed method could include most words that could effectively solve the word similarity calculation problem in the dictionary. Many work related to SVM in the parallel environment (or distributed system) have introduced in Ngoc et al [15], Wen et al [16], and Rao [17] . There are many researcher papers using Cloudera and Hadoop [18] Map/reduce.…”

Section: Related Workmentioning

confidence: 99%

English Semantic Similarity based on Map Reduce Classification for Agricultural Complaints

Rslan¹,

Khafagy²,

Munir³

et al. 2021

IJACSA

View full text Add to dashboard Cite

Due to environmental changes, including global warming, climatic changes, ecological impact, and dangerous diseases like the Coronavirus epidemic. Since coronavirus is a hazardous disease that causes many deaths, government of Egypt undertook many strict regulations, including lockdowns and social distancing measures. These circumstances have affected agricultural experts' presence to help farmers or advise on solving agricultural problems. For helping this issue, this work focused on improving support for farmers on the major field crops in Egypt Retrieving solutions corresponding to farmer query. For our work, we have mainly focused on detecting the semantic similarity between large agriculture dataset and user queries using Latent Semantic Analysis (LSA) based on Term Frequency Weighting and Inverse Document Frequency (TF-IDF) method. In this research paper, we apply SVM MapReduce classifier as a framework for paralleling and distributing the work on the dataset to classify the dataset. Then we apply different approaches for computing the similarity of sentences. We presented a system based on semantic similarity methods and support vector machine algorithm to detect the similar complaints of the user query. Finally, we run different experiments to evaluate the performance and efficiency of the proposed system as the system performs approximately 77.8%~94.8% in F-score measure. The experimental results show that the accuracy of SVM classifier is approximately 88.68%~89.63% and noted the leverage of SVM classification to the semantic similarity measure between sentences.

show abstract

Enhanced multiclass SVM with thresholding fusion for speech-based emotion classification

Cited by 25 publications

References 47 publications

Impact of Feature Extraction and Feature Selection Algorithms on Punjabi Speech Emotion Recognition Using Convolutional Neural Network

Impact of Feature Extraction and Feature Selection Algorithms on Punjabi Speech Emotion Recognition Using Convolutional Neural Network

Emotion classification from speech signal based on empirical mode decomposition and non-linear features

English Semantic Similarity based on Map Reduce Classification for Agricultural Complaints

Contact Info

Product

Resources

About