Unveiling the Acoustic Properties that Describe the Valence Dimension
نویسندگان
چکیده
One of the main challenges in emotion recognition from speech is to discriminate emotions in the valence domain (positive versus negative). While acoustic features provide good characterization in the activation/arousal dimension (excited versus calm), they usually fail to discriminate between sentences with different valence attributes (e.g., happy versus anger). This paper focuses on this dimension, which is key in many behavioral problems (e.g., depression). First, a regression analysis is conducted to identify the most informative features. Separate support vector regression (SVR) models are trained with various feature groups. The results reveal that spectral and F0 features produce the most accurate predictions of valence. Then, sentences with similar activation, but with different valence are carefully studied. The discriminative power in valence domain of individual features is studied with logistic regression analysis. This controlled experiment reveals differences between positive and negative emotions in the F0 distribution (e.g., positive skewness). The study also uncovers characteristic trends in the spectral domain.
منابع مشابه
An Acoustic Study of Emotivity-Prosody Interface in Persian Speech Using the Tilt Model
This paper aims to explore some acoustic properties (i.e. duration and pitch amplitude of speech) associated with three different emotions: anger, sadness and joy against neutrality as a reference point, all being intentionally expressed by six Persian speakers. The primary purpose of this study is to find out if there is any correspondence between the given emotions and prosody patterning in P...
متن کاملAutomatic Recognition of Spontaneous Emotions in Speech Using Acoustic and Lexical Features
We developed acoustic and lexical classifiers, based on a boosting algorithm, to assess the separability on arousal and valence dimensions in spontaneous emotional speech. The spontaneous emotional speech data was acquired by inviting subjects to play a first-person shooter video game. Our acoustic classifiers performed significantly better than the lexical classifiers on the arousal dimension....
متن کاملEffect of non-acoustic properties on the sound absorption of polyurethane foams
In this paper the influence of non-acoustic properties on the sound absorption coefficient of polyurethane foams as a porous medium is investigated. Biot’s equations with transfer matrix method, as the solution approach are employed to evaluate the sound absorption coefficient of selected polyurethane foams. The major issue is the dependency of non-acoustic properties on each other which makes ...
متن کاملVisualizing acoustic similarities between emotions in speech: an acoustic map of emotions
In this paper, we introduce a visual analysis method to assess the discriminability and confusiability between emotions according to automatic emotion classifiers. The degree of acoustic similarities between emotions can be defined in terms of distances that are based on pair-wise emotion discrimination experiments. By employing Multidimensional Scaling, the discriminability between emotions ca...
متن کاملCorrelation Between the Acoustic and Cell Morphology of Polyurethane/Silica Nanocomposite Foams: Effect of Various Proportions of Silica at Low Frequency Region
Introduction: Reducing noise pollution has become an essential issue due to the increase in public concern and also social demands for a better lifestyle. Using sound absorption materials is a preferred method to reduce the noise pollution. Undesirable properties of pure polyurethane such as poor absorption of mechanical energy in narrow frequency ranges can be improved by providing polymeric n...
متن کامل