Automatic Recognition of Emotions from Speech: A Review of the Literature and Recommendations for Practical Realisation

Abstract

Abstract. In this article we give guidelines on how to address the major technical challenges of automatic emotion recognition from speech in human-computer interfaces, which include audio segmentation to find appropriate units for emotions, extraction of emotion relevant features, classification of emotions, and training databases with emotional speech. Research so far has mostly dealt with offline evaluation of vocal emotions, and online processing has hardly been addressed. Online processing is, however, a necessary prerequisite for the realization of human-computer interfaces that analyze and respond to the user's emotions while he or she is interacting with an application. By means of a sample application, we demonstrate how the challenges arising from online processing may be solved. The overall objective of the paper is to help readers to assess the feasibility of human-computer interfaces that are sensitive to the user's emotional voice and to provide them with guidelines of how to technically realize such interfaces.

Emotionality in Computer-Mediated Environments: Analyzing the Emotional Content of Psychotherapeutic Communication

“…The intensity of sound (i.e., the pitch and volume) and the speed of articulation were considered to be the main indicators for distinguishing intensity, activation, and potency of clients' emotional states. This is consistent with studies of acoustics features in emotional expressions [46,47]. For example, there are influential associations between vocal cues (e.g., rate of speech, loudness) and emotions such as fear anxiety, sadness, and depression [48].…”

Sparsely Connected and Disjointly Trained Deep Neural Networks for Low Resource Behavioral Annotation: Acoustic Classification in Couples’ Therapy

“…Great advances have been made during last decade on assessing human state through technical way. For example, speech emotion recognition works [1][2][3] have shown effectiveness of extracting emotional content from human speech signals. In addition, Deep Neural Networks (DNN) have been employed for many related speech tasks [4][5][6].…”

Speech Emotion Recognition System Using Gaussian Mixture Model and Improvement proposed via Boosted GMM

“…It may be also useful in automatic translation systems in which the emotional state of the speaker plays an important role in communication between parties. In aircraft cockpits, it has been found that speech recognition systems trained to stressedspeech achieve better performance than those trained by normal speech [6].…”