Emotion Detection from Voice Based Classified Frame-Energy Signal Using K-Means Clustering

Abstract

Emotion detection is a new research era in health informatics and forensic technology. Besides having some challenges, voice based emotion recognition is getting popular, as the situation where the facial image is not available, the voice is the only way to detect the emotional or psychiatric condition of a person. However, the voice signal is so dynamic even in a short-time frame so that, a voice of the same person can differ within a very subtle period of time. Therefore, in this research basically two key criterion have been considered; firstly, this is clear that there is a necessity to partition the training data according to the emotional stage of each individual speaker. Secondly, rather than using the entire voice signal, short time significant frames can be used, which would be enough to identify the emotional condition of the speaker. In this research, Cepstral Coefficient (CC) has been used as voice feature and a fixed valued kmeans clustered method has been used for feature classification. The value of k will depend on the number of emotional situations in human physiology is being an evaluation. Consequently, the value of k does not necessarily consider the volume of experimental dataset. In this experiment, three emotional conditions: happy, angry and sad have been detected from eight female and seven male voice signals. This methodology has increased the emotion detection accuracy rate significantly comparing to some recent works and also reduced the CPU time of cluster formation and matching.

Investigating sentiments in Brazilian and German Blogs

“…The K used in KMeans are K = 3 (three polarities). The use of KMeans proposed by Hossain et al [2018] is justi- Table 1. The Happiness/Joy, Sadness, Fear, Anger, Disgust and Contempt emotions are calculated as the Aus are activated, if they are not activated they will have the intensity value 0.…”

Voice Feature Extraction for Gender and Emotion Recognition

“…The most popular approaches for classifications include Bayesian learning [6], the Linear Discriminant Analysis (LDA), the Support Vector Machine (SVM) [1,3] which is used as an extension of LDA with a high-dimensional feature space, the multi-layer Neural Network (NN) [14], and the Hidden Markov model (HMM) which captures temporal state transitions. The intensity of emotion [3] fluctuates on a voice from a low to a high level of emotion.. Hossain et al [9] used Cepstral Coefficient (CC) as voice feature and a fixed valued k-means clustered method for feature classification where value of k is determined by the number of emotional events that are evaluated in human physiology.SVM [7,8,11] is the most widely used classifier due to its efficiency in classifying high dimensional data where the number of features is greater than number of observations. SVMs have a major benefit over Artificial Neural Network(ANN) that, unlike ANNs, the solution to an SVM is global and exclusive.…”