Acoustic Measures Characterizing Anger across Corpora Collected in Artificial or Natural Context
نویسندگان
چکیده
This paper aims at studying differences between acoustic manifestations of anger across corpora collected in artificial, manipulated or natural context. It aims further at finding measures of naturalness in emotive corpora. Evaluating the degree of naturalness of a corpus can be challenging unless given knowledge upon the task. In corpora consisting of rather acted data, anger is often stronger; we believe that a kind of distance can be computed between anger and the overall corpus data. Such a distance is introduced in this work and evaluated with state-of-art acoustic descriptors in 3 collected corpora. We show the observed differences between the acoustic features obtained with anger samples in these different contexts and propose measures of naturalness. Index Terms — Emotion-detection, anger, naturalness, prototypical emotion.
منابع مشابه
Real-life emotion-related states detection in call centers: a cross-corpora study
In this article, we describe experiments on the detection of three emotional states (Anger, Positive and Neutral) for two French corpora collected in call centers in different contexts (service complaints and medical emergency). These corpora have a high level of privacy. In order to be comparable with results obtained in the community we used the openEAR acoustic features extraction platform i...
متن کاملOn NoMatchs, NoInputs and BargeIns: Do Non-Acoustic Features Support Anger Detection?
Most studies on speech-based emotion recognition are based on prosodic and acoustic features, only employing artificial acted corpora where the results cannot be generalized to telephone-based speech applications. In contrast, we present an approach based on utterances from 1,911 calls from a deployed telephone-based speech application, taking advantage of additional dialogue features, NLU feat...
متن کاملModeling A-Priori Likelihoods for Angry User Turns with Hidden Markov Models
Current studies dealing with the detection of angry users in automated telephone-based speech applications take acoustic and sometimes linguistic information into account in order to classify the emotional state of the caller in single user turns. Angry user turns, however, don’t appear from nowhere and the likelihood of observing another angry turn rises substantially when anger has already be...
متن کاملAn 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 کاملThe FASil speech and multimodal corpora
In the context of the FASiL project, we have studied natural language interactions in a unimodal (speech only) and multimodal (speech and graphics) interface to a personal information management database. We collected multilingual corpora to investigate these interactions in Portuguese, English and Swedish. The corpora are used to train language models, to update acoustic models, to study seman...
متن کامل