Ensemble methods for spoken emotion recognition in call-centres

Detecting emotional state of a child in a conversational computer game

“…Acoustic features of speech have been used extensively to separate emotional coloring present in the speech signal by employing several pattern recognition techniques (Ang et al, 2002;Nwe et al, 2003;Lee and Narayanan, 2005;Batliner et al, 2006;Schuller et al, 2007b;Kapoor et al, 2007;Morrison et al, 2007;Neiberg and Elenius, 2008;Lee et al, 2009). Phoneme, syllable and word level statistics corresponding to F0 (fundamental frequency), energy, duration, spectral parameters, and voice quality parameters are among the features that have been mainly used for emotion recognition.…”

Automatic Recognition of Emotional States From Human Speeches

“…In the previous studies, most emotion recognition schemes use a single classifier, and very few have considered hybrid classification methods (Morrison, 2007). Intuitively, if the individual schemes can be suitably combined, an improvement in accuracy can be expected.…”

“…Scherer (2000) explored the existence of a universal psychobiological mechanism of emotions in speech by studying the recognition of fear, joy, sadness, anger and disgust in nine languages, obtaining 66% of overall accuracy. Two hybrid classification schemes, stacked generalization and the unweighted vote, were proposed and accuracies of 72.18% and 70.54% were achieved respectively, when they were used to recognize anger, disgust, fear, happiness, sadness and surprise (Morrison, 2007). Hybrid classification methods that combined the Support Vector Machines and the Decision Tree were proposed (Nguyen & Bass, 2005).…”

“…As there is a lack of precise definition and models for emotions, automatic recognition of emotions has been a challenging task to researchers. Indeed, research on speech based emotion recognition has been undertaken by many for around two decades (Amir, 2001;Clavel et al, 2004;Cowie & Douglas-Cowie, 1996;Cowie et al, 2001;Dellaert et al, 1996;Lee & Narayanan, 2005;Morrison et al, 2007;Nguyen & Bass, 2005;Nicholson et al, 1999;Petrushin, 1999;Petrushin, 2000;Scherer, 2000;Ser et al, 2008;Ververidis & Kotropoulos, 2006;Yu et al, 2001;Zhou et al, 2006). In engineering, speech emotion recognition has been formulated as a pattern recognition problem that involves feature extraction and emotion classification.…”

Modeling the user state for context-aware spoken interaction in ambient assisted living

“…While balanced utterances are useful for controlled scientifi analysis and experiments, they may reduce the validity of the data. For this reason, many other researchers prefer that the distribution of the emotions in the database reflect their real-world frequency [104,163]. In this case, the number of neutral utterances should be the largest in the emotional speech corpus.…”