m (Scipediacontent moved page Draft Content 696191418 to Machot et al 2011a) |
|||
Line 3: | Line 3: | ||
This paper presents a real-time emotion recognition concept of voice streams. A comprehensive solution based on Bayesian Quadratic Discriminate Classifier(QDC) is developed. The developed system supports Advanced Driver Assistance Systems (ADAS) to detect the mood of the driver based on the fact that aggressive behavior on road leads to traffic accidents. We use only 12 features to classify between 5 different classes of emotions. We illustrate that the extracted emotion features are highly overlapped and how each emotion class is effecting the recognition ratio. Finally, we show that the Bayesian Quadratic Discriminate Classifier is an appropriate solution for emotion detection systems, where a real-time detection is deeply needed with a low number of features. | This paper presents a real-time emotion recognition concept of voice streams. A comprehensive solution based on Bayesian Quadratic Discriminate Classifier(QDC) is developed. The developed system supports Advanced Driver Assistance Systems (ADAS) to detect the mood of the driver based on the fact that aggressive behavior on road leads to traffic accidents. We use only 12 features to classify between 5 different classes of emotions. We illustrate that the extracted emotion features are highly overlapped and how each emotion class is effecting the recognition ratio. Finally, we show that the Bayesian Quadratic Discriminate Classifier is an appropriate solution for emotion detection systems, where a real-time detection is deeply needed with a low number of features. | ||
− | |||
− | |||
− | |||
− | |||
− | |||
Line 15: | Line 10: | ||
* [http://vi.uni-klu.ac.at/publications/papers/2011A_Novel.pdf http://vi.uni-klu.ac.at/publications/papers/2011A_Novel.pdf] | * [http://vi.uni-klu.ac.at/publications/papers/2011A_Novel.pdf http://vi.uni-klu.ac.at/publications/papers/2011A_Novel.pdf] | ||
+ | |||
+ | * [http://link.springer.com/content/pdf/10.1007/978-3-642-24806-1_21 http://link.springer.com/content/pdf/10.1007/978-3-642-24806-1_21], | ||
+ | : [http://dx.doi.org/10.1007/978-3-642-24806-1_21 http://dx.doi.org/10.1007/978-3-642-24806-1_21] under the license http://www.springer.com/tdm | ||
+ | |||
+ | * [http://vi.uni-klu.ac.at/publications/papers/2011A_Novel.pdf http://vi.uni-klu.ac.at/publications/papers/2011A_Novel.pdf], | ||
+ | : [https://link.springer.com/chapter/10.1007%2F978-3-642-24806-1_21 https://link.springer.com/chapter/10.1007%2F978-3-642-24806-1_21], | ||
+ | : [https://dblp.uni-trier.de/db/series/sci/sci391.html#MachotMFSAK12 https://dblp.uni-trier.de/db/series/sci/sci391.html#MachotMFSAK12], | ||
+ | : [https://rd.springer.com/chapter/10.1007/978-3-642-24806-1_21 https://rd.springer.com/chapter/10.1007/978-3-642-24806-1_21], | ||
+ | : [https://academic.microsoft.com/#/detail/126921796 https://academic.microsoft.com/#/detail/126921796] |
This paper presents a real-time emotion recognition concept of voice streams. A comprehensive solution based on Bayesian Quadratic Discriminate Classifier(QDC) is developed. The developed system supports Advanced Driver Assistance Systems (ADAS) to detect the mood of the driver based on the fact that aggressive behavior on road leads to traffic accidents. We use only 12 features to classify between 5 different classes of emotions. We illustrate that the extracted emotion features are highly overlapped and how each emotion class is effecting the recognition ratio. Finally, we show that the Bayesian Quadratic Discriminate Classifier is an appropriate solution for emotion detection systems, where a real-time detection is deeply needed with a low number of features.
The different versions of the original document can be found in:
Published on 01/01/2011
Volume 2011, 2011
DOI: 10.1007/978-3-642-24806-1_21
Licence: CC BY-NC-SA license
Are you one of the authors of this document?