Speech Emotion Classification Research Articles

Loss-Scaled Large-Margin Gaussian Mixture Models for Speech Emotion Classification

This paper considers a learning framework for speech emotion classification using a discriminant function based on Gaussian mixture models (GMMs). The GMM parameter set is estimated by margin scaling with a loss function to reduce the risk of predicting emotions with high loss. Here, the loss function is defined as a function of a distance metric using the Watson and Tellegen's emotion model. Margin scaling is known to have good generalization ability and can be considered appropriate for emotion modeling where the parameter set is likely to be over-fitted to the training data set whose characteristics may differ from those of the testing data set. Our learning framework is formulated as a constrained optimization problem which is solved using semi-definite programming. Three tasks were evaluated: acted emotion classification, natural emotion classification, and cross database emotion classification. In each task, four loss functions were evaluated. In all experiments, results consistently show that margin scaling improves the classification accuracy over other learning frameworks based on the maximum-likelihood, maximum mutual information and max-margin framework without margin scaling. Experiment results also show that margin scaling substantially reduces the overall loss compared to the max-margin framework without margin scaling.

Real Life Emotion Classification using Spectral Features and Gaussian Mixture Models

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

A Study on Feature Analysis and Recognition of Practical Speech Emotion

Practical speech emotions as impatience and happiness are studied especially for evaluation of emotional well-being in real world applications. Induced natural speech emotion data is collected with a computer game, 74 emotion features are extracted, prosody features and voice quality features are analyzed according to dimensional emotion model, evaluation and selection of acoustic features are carried out for practical emotions in this paper, a method of practical speech emotion classification with rejection decision is proposed for real world occasions. The experiment results show, the speech features analyzed in this paper are suitable for classification of practical speech emotions like impatience and happiness, average recognition rate is above 75%, and the method of emotion classification with rejection decision is necessary for the proper recognition decision of ambiguous or unknown emotion samples, especially for the real world challenges.

Classification of Emotional Speech Based on an Automatically Elaborated Hierarchical Classifier

Current machine-based techniques for vocal emotion recognition only consider a finite number of clearly labeled emotional classes whereas the kinds of emotional classes and their number are typically application dependent. Previous studies have shown that multistage classification scheme, because of ambiguous nature of affect classes, helps to improve emotion classification accuracy. However, these multistage classification schemes were manually elaborated by taking into account the underlying emotional classes to be discriminated. In this paper, we propose an automatically elaborated hierarchical classification scheme (ACS), which is driven by an evidence theory-based embedded feature-selection scheme (ESFS), for the purpose of application-dependent emotions' recognition. Experimented on the Berlin dataset with 68 features and six emotion states, this automatically elaborated hierarchical classifier (ACS) showed its effectiveness, displaying a 71.38% classification accuracy rate compared to a 71.52% classification rate achieved by our previously dimensional model-driven but still manually elaborated multistage classifier (DEC). Using the DES dataset with five emotion states, our ACS achieved a 76.74% recognition rate compared to a 81.22% accuracy rate displayed by a manually elaborated multistage classification scheme (DEC).

Survey on speech emotion recognition: Features, classification schemes, and databases

Recently, increasing attention has been directed to the study of the emotional content of speech signals, and hence, many systems have been proposed to identify the emotional content of a spoken utterance. This paper is a survey of speech emotion classification addressing three important aspects of the design of a speech emotion recognition system. The first one is the choice of suitable features for speech representation. The second issue is the design of an appropriate classification scheme and the third issue is the proper preparation of an emotional speech database for evaluating system performance. Conclusions about the performance and limitations of current speech emotion recognition systems are discussed in the last section of this survey. This section also suggests possible ways of improving speech emotion recognition systems.

Learning the Fréchet Mean over the Manifold of Symmetric Positive-Definite Matrices

The present manuscript tackles the problem of learning the average of a set of symmetric positive-definite (SPD) matrices. Averages are computed via the notion of Fréchet mean, and the associated metric dispersion is interpreted as the variance of the patterns around the Fréchet mean. Also, the problem of continuous interpolation of two SPD patterns is tackled within the manuscript. The property of volume conservation of the Fréchet mean and of the considered interpolatory scheme for SPD matrices is discussed as well. The paper describes several applications where the technique could be readily exploited, including in machine learning, intelligent control, pattern classification, speech emotion classification and diffusion tensor data analysis in medicine.

Multi-stage classification of emotional speech motivated by a dimensional emotion model

This paper deals with speech emotion analysis within the context of increasing awareness of the wide application potential of affective computing. Unlike most works in the literature which mainly rely on classical frequency and energy based features along with a single global classifier for emotion recognition, we propose in this paper some new harmonic and Zipf based features for better speech emotion characterization in the valence dimension and a multi-stage classification scheme driven by a dimensional emotion model for better emotional class discrimination. Experimented on the Berlin dataset with 68 features and six emotion states, our approach shows its effectiveness, displaying a 68.60% classification rate and reaching a 71.52% classification rate when a gender classification is first applied. Using the DES dataset with five emotion states, our approach achieves an 81% recognition rate when the best performance in the literature to our knowledge is 76.15% on the same dataset.

Support vector machines employing cross-correlation for emotional speech recognition

Emotional speech classification is a current area of research with wide variety of applications in intelligent human–machine interaction systems. For classifying emotional speech signals, it is quite common to use either statistical features or temporal features. This paper proposes a relatively new cross-correlation based feature extractor and is aided with support vector machine classifier for emotional speech recognition. In this paper the proposed technique has been utilized for classification of four kinds of emotional speech signals. The support vector machine classifier employs suitable features extracted from crosscorrelograms of emotional speech signals. This cross-correlation aided SVM classification system could achieve an overall classification accuracy as high as 84.55%. The results also divulge that the SVM classifier detects anger emotion efficiently with a recognition rate of 95.04%.