Fulltext present in this item

Thumbnail
Fulltext: 91351.pdf
Format: PDF
Description: author's version
Title: Arousal and valence prediction in spontaneous emotional speech: felt versus perceived emotion
Author(s): Truong, K.P. ; Leeuwen, D.A. van ; Neerincx, M.A. ; Jong, F. M. G de
Publication year: 2009
In: Proceedings of Interspeech 2009, pp. 2027-2030
Publisher: Brighton : ISCA
Related links: http://lands.let.ru.nl/literature/leeuwen.2009.2.pdf
Annotation: Interspeech
Publication type: Article in monograph or in proceedings

Please use this identifier to cite or link to this item : https://hdl.handle.net/2066/91351   https://hdl.handle.net/2066/91351

Display more details
Subject: Linguistic Information Processing
Organization: Taalwetenschap
Book title: Proceedings of Interspeech 2009
Page start: p. 2027
Page end: p. 2030
Abstract:
In this paper, we describe emotion recognition experiments car- ried out for spontaneous affective speech with the aim to com- pare the added value of annotation of felt emotion versus an- notation of perceived emotion. Using speech material avail- able in the TNO-GAMING corpus (a corpus containing audio- visual recordings of people playing videogames), speech-based affect recognizers were developed that can predict Arousal and Valence scalar values. Two types of recognizers were devel- oped in parallel: one trained with felt emotion annotations (generated by the gamers themselves) and one trained with perceived/observed emotion annotations (generated by a group of observers). The experiments showed that, in speech, with the methods and features currently used, observed emotions are easier to predict than felt emotions. The results suggest that recognition performance strongly depends on how and by whom the emotion annotations are carried out
Languages used: English (eng)

This item appears in the following Collection(s)

Browse

Statistics