Computational paralinguistic analysis is increasingly being used in a wide range of applications, including securitysensitive applications such as speaker verification, deceptive speech detection, and medical diagnostics. While state-ofthe-art machine learning techniques, such as deep neural networks, can provide robust and accurate speech analysis, they are susceptible to adversarial attacks. ...

Analyzing and assessing the quality of classroom lessons on a range of quality dimensions is a number one educational research topic, as this allows developing teacher trainings and interventions to improve lesson quality. We model this assessment as a text classification task, exploiting linguistic features to predict the scores in several lesson quality dimensions relevant for educational res...

We deal with the topic of segmenting emotion-related (emotional/affective) episodes into adequate units for analysis and automatic processing/classification—a topic that has not been addressed adequately so far. We concentrate on speech and illustrate promising approaches by using a database with children’s emotional speech. We argue in favour of the word as basic unit and map sequences of word...

Speech parameters originating from voice source and vocal tract were analyzed to find acoustic correlates of dimensional descriptions of emotional states. To achieve this goal best, we adopted the Utsunomiya University Spoken Dialogue Database, which was designed for studies on paralinguistic information in expressive conversational speech. Analyses for four female and two male speakers showed:...

This paper describes tools and techniques for accessing large quantities of speech data and for the visualisation of discourse interactions and events at levels above that of linguistic content. We are working with large quantities of dialogue speech including business meetings, friendly discourse, and telephone conversations, and have produced web-based tools for the visualisation of non-verba...

This paper presents details and progress of the JST/CREST ESP Project, part of the “Information Technology for Life in an Advanced Media Society” series of research projects. The purpose of the research is to determine the acoustic variables that indicate different attitudes and emotions in speech and to map these to linguistic objects and frameworks so that a model of the paralinguistic struct...

In the area of speech technology, tasks that involve the extraction of non-lingustic information have been receiving more attention recently. The Computational Paralinguistics Challenge (ComParE 2013) sought to develop techniques to efficiently detect a number of paralinguistic events, including the detection of non-linguistic events (laughter and fillers) in speech recordings as well as catego...

We face many options when designing a system that automatically generates prosody from linguistic and paralinguistic information. The literature provides several candidate phonetic models, phonological models and mapping tools to actually implement the system. We detail here some dimensions along which these models have to be compared. We show also that systems employing quite similar phonetic ...

This study tests the hypothesis that, among the other paralinguistic information conveyed by voice qualities, irregular vocal fold vibration (glottalization) can serve as a cue to speaker identity. Earlier studies that have reported systematic differences across speakers in the rate and type of intermittent glottalization support this idea. Still, it remains an open question whether human liste...