Challenges in real-life emotion annotation and machine learning based detection

By Laurence Y. Devillers, Laurence Vidrascu, Lori Faith Lamel. Neural Networks, 2005

400 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Experimental and Cognitive Psychology, Social Psychology

View Paper: https://www.semanticscholar.org/paper/76be1962855bcb641eeb70bccb25566968b2834b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Experimental and Cognitive Psychology

In Social Psychology

Citations in the corpus

In a Nervous Voice: Acoustic Analysis and Perception of Anxiety in Social Phobics’ Speech (2008, background): “The majority of studies on the vocal expression of fear have been conducted on posed expressions, though a couple of studies on authentic fear expressions do exist (e.g., Devillers et al. 2005; Kuroda et al. 1976; Williams and Stevens 1969).”
Emotion Assessment: Arousal Evaluation Using EEG's and Peripheral Physiological Signals (2006, background): “Most studies focus on the analysis of facial expressions or of speech ([5], [ 6 ]).”
Building Naturalistic Emotionally Balanced Speech Corpus by Retrieving Emotional Speech from Existing Podcast Recordings (2019, background): “A criticism of this approach is the lack of naturalness, as the acted renditions resemble more prototypical behaviors rather than the ambiguous emotional displays observed during daily interactions [23], [24], [25], [26].”
Short-term emotion assessment in a recall paradigm (2009, background): “Moreover, the emotion felt is often a mixture of several basic emotions yielding a more complex representation using probabilistic, fuzzy or multi-labels models (Devillers et al., 2005).”
Recognising realistic emotions and affect in speech: State of the art and lessons learnt from the first challenge (2011, background): “Representatives for such real-life settings are TV-recordings (The Vera-Am-Mittag (VAM) Corpus (Grimm et al., 2008)), call-centre interactions (Devillers et al., 2005b; Liscombe et al., 1845), multi-party interaction (the ICSI meeting corpus (Laskowski, 2009)), or The Speech In Minimal Invasive…”
Paralinguistics in speech and language - State-of-the-art and the challenge (2013, background): “…training or adaptation phases, where s(n), x, y are the speech signal, feature vector, and target vector, respectively igh comma indicates altered versions, and subscripts diverse vectors. ost of them used by different teams have high levels of privacy and cannot be shared (Devillers et al., 2005).”
IEMOCAP: interactive emotional dyadic motion capture database (2008, methodology): “These values are consistent with the agreement levels reported in previous work for similar tasks [27, 37, 51].”
Emotion Recognition (2009, background): “They are, moreover, often restricted to only a few emotions, such as joy or frustration [3, 5, 7].”
Speech emotion recognition (2018, neutral): “pressed in the speech of others—or any other modality accessible to humans.(13) Self-assessment could be an option,”