The emotion detection work reported here is part of a larger study aiming to model user behavior in real interactions. We already studied emotions in a real-life corpus with human-human dialogs on a financial task. We now make use of another corpus of real agent-caller spoken dialogs from a medical emergency call center in which emotion manifestations are much more complex, and extreme emotions...

This study examines the perception of paralinguistic intonational meanings deriving from Ohala's Frequency Code (Experiment 1) and Gussenhoven's Effort Code (Experiment 2) in British English and Dutch. Native speakers of British English and Dutch listened to a number of stimuli in their native language and judged each stimulus on four semantic scales deriving from these two codes: SELF-CONFIDEN...

Qualitative analyses are conducted in spontaneous dialogue speech of several speakers, to verify the paralinguistic roles of breathy/whispery voice qualities in communication. Analyses show that breathy/whispery voices carry a variety of emotionor attitude-related paralinguistic information. Breathiness often appeared in emphasized words/phrases, having the effect of calling/catching the listen...

Multiple cues interact to signal multiple functions in intonation simultaneously which makes intonation notoriously complex to analyze. The Autosegmental-Metrical model for intonation analysis has proved to be an excellent vehicle for separating the components, but evidence for the phonetics/phonology dichotomy on which it hinges has proved elusive. Advocating a multidisciplinary approach, this...

The development of theories about form-function relations in intonation should be informed by a better understanding of the dependencies that hold among different phonetic parameters. Fine phonetic detail encodes both linguistically structured meaning and paralinguistic meaning.

Influence of paralinguistic information upon articulatory gesture was examined using EMMA record of tongue, jaw and lips. The focus was upon the contrast between “admiration” and “suspicion.” It was found that previously reported contrast in F2 is related to the horizontal displacement of the tongue body and lip aperture control. These articulatory characteristics were observed not only in vowe...

Laughter is one of the most important paralinguistic events, and it has specific roles in human conversation. The automatic detection of laughter occurrences in human speech can aid automatic speech recognition systems as well as some paralinguistic tasks such as emotion detection. In this study we apply Deep Neural Networks (DNN) for laughter detection, as this technology is nowadays considere...

In this paper we investigate the performance of different classification paradigms, testing each with a range of acoustic features, to find a system that is well suited to speaker likeability classification. We introduce a Sparse Representation Classifier for paralinguistic classification and explore the role of training data selection for a GMM classifier. Results demonstrate that (1) Single d...

In spontaneous speech, emotion information is embedded at several levels: acoustic, linguistic, gestural (non-verbal), etc. For emotion recognition in speech, there is much attention to acoustic level and some attention at the linguistic level. In this study, we identify paralinguistic markers for emotion in the language. We study two Indian languages belonging to two distinct language families...

Prior research on gaze, turn-taking, and backchannels suggests that the speaker’s gaze cues the listener’s paralinguistic responses, including feedback behaviors. To explore how conversants use feedback cues and responses, I studied a corpus of face-to-face conversational interaction, primarily using a conversation-analytic approach. Analysis of the dialogs suggests that paralinguistic behavior...