The influence of alcoholic intoxication on the short-time energy function of speech

Abstract

This study investigates rhythmic features based on the short-time energy function of speech signals with the aim of finding robust, speaker-independent features that indicate speaker intoxication. Data from the German Alcohol Language Corpus, which comprises read, spontaneous, and command&control speech uttered by 162 speakers of both genders and various age groups when sober and intoxicated, were analyzed. Energy contours are compared directly (Root Mean Squared Error, statistical correlation, or the Euclidean distance in the spectral space of the contour) and by parameterization of the contour using the Discrete Cosine Transform (DCT) and the first and second moments of the lower DCT spectrum. Contours are also analyzed by Principal Components Analysis aiming at fundamental "eigen contour" changes that might encode intoxication. Energy contours differ significantly with intoxication in terms of distance measures, the second and fourth DCT coefficients, and the first and second moments of the lower DCT spectrum. Principal Components Analysis did not yield interpretable "eigen contours" that could be used in distinguishing intoxicated from sober contours.

Entrainment profiles: Comparison by gender, role, and feature set

“…In our approach, rhythm within a turn is represented in terms of syllable rate (number of detected syllable nuclei per second) and the influence of the syllable level of the prosodic hierarchy on the energy and f0 contours. To quantify the syllabic influence on any of these contours we performed a discrete cosine transform (DCT) on this contour as in [35]. We then calculated the syllable influence w as the relative weight of the coefficients around the syllable rate r (+/ − 1 Hz to account for syllable rate fluctuations) within all coefficients below 10 Hz as follows:…”

Prosodic entrainment in dialog acts

“…This influence manifests itself in regular fluctuations at the syllable rate. To quantify the syllabic influence on any of these contours we performed a discrete cosine transform (DCT) on this contour as in [29]. We then calculated the syllable influence w as the Figure 2: Rhythm features: Quantifying the influence of syllable rate on the f0 contour (analogously for the energy contour).…”

CoPaSul Manual -- Contour-based parametric and superpositional intonation stylization

“…To extract the relative weight of the low-and high-frequency components of a contour, a discrete cosine transform (DCT) is applied on the contour as in [7]. For the absolute DCT coefficient values the first n rhy *:rhy:nsm spectral moments are calculated that (up to the forth moment) give the mean, variance, skew, and kurtosis of the DCT coefficient weight distribution, repsectively.…”