China
Africa
Explore chapters and articles related to this topic
Key Stakeholders Management: Principles of Effective Direct Communication
Published in Massimo Pirozzi, The Stakeholder Perspective, 2019
Paraverbal communication includes all those paralinguistic aspects, both conscious and unconscious, which can modify, enhance, and attenuate the meaning of an oral communication by influencing considerably its perception in the listeners. There are several paralinguistic aspects that accompany each vocal message, such as, for instance, the intonation, which qualifies each statement in terms of communication intentions, the use of different speeds and pauses, which are helpful to emphasize the diverse parts of oral communication, the loudness, which it is used not only to overcome distance, but also to characterize the communication, the pitch, the timbre, and also some specific forms of paralinguistic respiration, e.g., gasps, sighs, throat-clears, and “mhms”.
Technological Advances to Understand and Improve Individual and Team Resilience in Extreme Environments
Published in Lauren Blackwell Landon, Kelley J. Slack, Eduardo Salas, Psychology and Human Performance in Space Programs, 2020
Sadaf Kazi, Salar Khaleghzadegan, Michael A. Rosen
Paralinguistic communication refers to vocal features devoid of actual communication content, including the speed, volume, and pitch, in addition to other non-verbal cues, including communication flow, gestures, posture, facial expression, and gaze behavior (Schuller & Batliner, 2013). Paralinguistic communication can be assessed through audio recordings (both traditional and recordings that only consist of vocal features without the actual words), and video recordings (e.g., measuring gesture and posture through analysis of video data) or instrumenting individuals with sensors that record body movement and muscle activation, and measuring gaze behavior by using eye-tracking methods.
Hierarchical classifier design for speech emotion recognition in the mixed-cultural environment
Published in Journal of Experimental & Theoretical Artificial Intelligence, 2021
P. Vasuki, Chandrabose Aravindan
Affective Computing works to understand the emotional state of the user, which significantly impacts the performance of its applications in the fields of health, education, entertainment, and data mining. When compared to facial expression (Fang et al., 2018), EEG (Electroencephalograph) and ECG (Electrocardiogram) signals which reflect the emotional state of a person, speech is the best choice to be considered for emotion recognition, because of the easy access of the sensor signals. Speech is a rich and natural communication medium that consists of linguistic and paralinguistic information. Linguistic information conveys the semantics of the utterance, whereas paralinguistic information provides the sentiment and the characteristics of speaker (Vasuki & Divya, 2019) such as age, gender, and emotion. In this paper, we focus only on the speech modality of communication, in the context of affective computing, to identify the emotional state of a person by observing his/her expression in speech.