Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
Concept
Emotional prosody
Summary
Emotional prosody or affective prosody is the various non-verbal aspects of language that allow people to convey or understand emotion. It includes an individual's tone of voice in speech that is conveyed through changes in pitch, loudness, timbre, speech rate, and pauses. It can be isolated from semantic information, and interacts with verbal content (e.g. sarcasm).
Emotional prosody in speech is perceived or decoded slightly worse than facial expressions but accuracy varies with emotions. Anger and sadness are perceived most easily, followed by fear and happiness, with disgust being the most poorly perceived.
Studies have found that some emotions, such as fear, joy and anger, are portrayed at a higher frequency than emotions such as sadness.
Anger: Anger can be divided into two types: "anger" and "hot anger". In comparison to neutral speech, anger is produced with a lower pitch, higher intensity, more energy (500 Hz) across the vocalization, higher first formant (first sound produced) and faster attack times at voice onset (the start of speech). "Hot anger", in contrast, is produced with a higher, more varied pitch, and even greater energy (2000 Hz).
Disgust: In comparison to neutral speech, disgust is produced with a lower, downward directed pitch, with energy (500 Hz), lower first formant, and fast attack times similar to anger. Less variation and shorter durations are also characteristics of disgust.
Fear: Fear can be divided into two types: "panic" and "anxiety". In comparison to neutral speech, fearful emotions have a higher pitch, little variation, lower energy, and a faster speech rate with more pauses.
Sadness: In comparison to neutral speech, sad emotions are produced with a higher pitch, less intensity but more vocal energy (2000 Hz), longer duration with more pauses, and a lower first formant.
Decoding emotions in speech includes three stages: determining acoustic features, creating meaningful connections with these features, and processing the acoustic patterns in relation to the connections established.
Official source
About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.