Speech emotion recognition in emotional feedback for Human-Robot Interaction

Abstract

Abstract-For robots to plan their actions autonomously and interact with people, recognizing human emotions is crucial. For most humans nonverbal cues such as pitch, loudness, spectrum, speech rate are efficient carriers of emotions. The features of the sound of a spoken voice probably contains crucial information on the emotional state of the speaker, within this framework, a machine might use such properties of sound to recognize emotions. This work evaluated six different kinds of classifiers to predict six basic universal emotions from non-verbal features of human speech. The classification techniques used information from six audio files extracted from the eNTERFACE05 audiovisual emotion database. The information gain from a decision tree was also used in order to choose the most significant speech features, from a set of acoustic features commonly extracted in emotion analysis. The classifiers were evaluated with the proposed features and the features selected by the decision tree. With this feature selection could be observed that each one of compared classifiers increased the global accuracy and the recall. The best performance was obtained with Support Vector Machine and bayesNet.

Aviation Profiling Method Based on Deep Learning Technology for Emotion Recognition by Speech Signal

“…The data in Table 4 show that the proposed classification method surpasses most of the known models of emotion detection based on the speech signal. At the same time, in (Razuri et al, 2015) the share of correct answers is 96.97%, which is 3.78% higher than the results of this study. However, it should be noted that the classification according to the base (Martin et al, 2006) in the work (Razuri et al, 2015) was made only for 6 types of emotions without determining the neutral state.…”

“…At the same time, in (Razuri et al, 2015) the share of correct answers is 96.97%, which is 3.78% higher than the results of this study. However, it should be noted that the classification according to the base (Martin et al, 2006) in the work (Razuri et al, 2015) was made only for 6 types of emotions without determining the neutral state. Also, in (Razuri et al, 2015), 264 samples of audio signals extracted from video recordings were used for the study, with one statement for each emotion.…”

“…However, it should be noted that the classification according to the base (Martin et al, 2006) in the work (Razuri et al, 2015) was made only for 6 types of emotions without determining the neutral state. Also, in (Razuri et al, 2015), 264 samples of audio signals extracted from video recordings were used for the study, with one statement for each emotion. For these reasons, it can be assumed that the generalizing ability of the classification algorithms proposed in the study (Razuri et al, 2015) is insufficient.…”

“…Also, in (Razuri et al, 2015), 264 samples of audio signals extracted from video recordings were used for the study, with one statement for each emotion. For these reasons, it can be assumed that the generalizing ability of the classification algorithms proposed in the study (Razuri et al, 2015) is insufficient.…”

Applying Multitask Deep Learning to Emotion Recognition in Speech

“…Такие модели получили широкое распространение в интерфейсах человек-компьютер, в целом, и голосовых пользовательских интерфейсов (Alexa, Cortana, Siri, Алиса), в частности. Кроме того, модели распознавания эмоций получили широкое распространение в следующих областях: в приложениях речевого анализа в области медицины [1], безопасности [2], робототехники [3], автоматизированных систем [4]. Тем не менее, на текущем этапе своего развития, модели автоматического распознавания эмоций в речи не могут обеспечить должную производительность на реальных данных [5], что определяет необходимость разработки новых подходов к распознаванию эмоций человека в речи.…”