Face and Gesture 2011 2011
DOI: 10.1109/fg.2011.5771357
|View full text |Cite
|
Sign up to set email alerts
|

Emotion representation, analysis and synthesis in continuous space: A survey

Abstract: Despite major advances within the affective computing research field, modelling, analysing, interpreting and responding to naturalistic human affective behaviour still remains as a challenge for automated systems as emotions are complex constructs with fuzzy boundaries and with substantial individual variations in expression and experience. Thus, a small number of discrete categories (e.g., happiness and sadness) may not reflect the subtlety and complexity of the affective states conveyed by such rich sources … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

3
158
0
2

Year Published

2012
2012
2024
2024

Publication Types

Select...
4
4

Relationship

0
8

Authors

Journals

citations
Cited by 266 publications
(163 citation statements)
references
References 93 publications
3
158
0
2
Order By: Relevance
“…They exhibit substantial individual variations in expression and experience [21]. Emotion recognition is such a challenging task that it is unlikely to achieve perfect accuracy [12].…”
Section: Related Workmentioning
confidence: 99%
See 2 more Smart Citations
“…They exhibit substantial individual variations in expression and experience [21]. Emotion recognition is such a challenging task that it is unlikely to achieve perfect accuracy [12].…”
Section: Related Workmentioning
confidence: 99%
“…Shorter pauses and inter-breath stretches are indicative of higher activation. Fast speaking rate, less high-frequency energy, low pitch and large pitch range and longer vowel durations are related to positive valence [21]. We extract features related to statistics of formant contours (Table 1), pitch contours (Table 2), and energy contours ( Table 3).…”
Section: Feature Extractionmentioning
confidence: 99%
See 1 more Smart Citation
“…The first approach is based on the definition of a reduced set of basic emotions, innate and universally recognized. This model is widely used in automatic recognition of emotions, but as well as for human actions and intentions, can be considered more complex models that address a continuous range of affective and emotional states (Gunes et al, 2011). Dimensional models are described by geometric spaces that can use the basic emotions, but represented by a continuous dynamic dimensions such as arousal, valence, expectation, intensity.…”
Section: Detection Of Human Emotionsmentioning
confidence: 99%
“…The neural networks architectures found in literature mainly consist of variants of a multilayer artificial networks [7,8].…”
Section: Introductionmentioning
confidence: 99%