Detection of negative emotional states in real-world scenario

This source preferred by Theodoros Kostoulas

Authors: Kostoulas, T., Ganchev, T., Mporas, I. and Fakotakis, N.

Start date: 29 October 2007

Journal: Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI

Volume: 2

Pages: 502-509

ISSN: 1082-3409

DOI: 10.1109/ICTAI.2007.106

In the present work we evaluate a detector of negative emotional states (DNES) that serves the purpose of enhancing a spoken dialogue system, which operates in smart-home environment. The DNES component is based on Gaussian mixture models (GMMs) and a set of commonly used speech features. In comprehensive performance evaluation we utilized a well-known acted speech database and real-world speech recordings. The real-world speech was collected during interaction of naïve users with our smart-home spoken dialogue system. The experimental results show that the accuracy of recognizing negative emotions on the realworld data is lower than the one reported when testing on the acted speech database, though much promising, considering that, often, humans are unable to distinguish the emotion of other humans judging only from speech. © 2007 IEEE.

This data was imported from Scopus:

Authors: Kostoulas, T., Ganchev, T., Mporas, I. and Fakotakis, N.

Journal: Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI

Volume: 2

Pages: 502-509

ISBN: 9780769530154

ISSN: 1082-3409

DOI: 10.1109/ICTAI.2007.106

In the present work we evaluate a detector of negative emotional states (DNES) that serves the purpose of enhancing a spoken dialogue system, which operates in smart-home environment. The DNES component is based on Gaussian mixture models (GMMs) and a set of commonly used speech features. In comprehensive performance evaluation we utilized a well-known acted speech database and real-world speech recordings. The real-world speech was collected during interaction of naïve users with our smart-home spoken dialogue system. The experimental results show that the accuracy of recognizing negative emotions on the realworld data is lower than the one reported when testing on the acted speech database, though much promising, considering that, often, humans are unable to distinguish the emotion of other humans judging only from speech. © 2007 IEEE.

The data on this page was last updated at 04:53 on March 24, 2019.