Emotion

Emotion is an ambiguous term with a difficult to find definition. According to the American Psychology Association, it is defined as: "[…] conscious mental reactions (such as anger or fear) subjectively experienced as strong feelings usually directed toward a specific object and typically accompanied by physiological and behavioral changes in the body." ^05471c

Communication¶

Constituents¶

Emotions are communicated by speech (message and prosody) as well as non-verbal cues.

The message of speech seems to convey only ca. 7% of our feelings and attitude. Much more emotional expression comes from prosody (38%) and facial expressions (55%) (from @zhouEmotionalVoiceConversion2022 and @mehrabianDecodingInconsistentCommunications1967).

Prosody¶

Classically, prosodic features are the speech rate, voice quality, Fundamental Frequency (F0), spectral features, duration, F0 contour and F0 energy envelope (timbre/Spectral Envelope). ^dc3104

Expression¶

In the context of Emotional Speech Synthesis (ESS), its often defined in one of two ways:

Discrete theories: Emotions are treated as discrete categories. Typical example: Ekman's Big Six.
Dimensional theories: Emotions are seen as having several dimensions, like arousal, valence and dominance. Typical Example: Russell's Circumplex Model.

Perception¶

Multilayered process, more recently modeled as an inverse process of Russell's Circumplex Model.