Difference between revisions of "Publications/dehak.09.interspeechb"

From LRDE

 
Line 6: Line 6:
 
| booktitle = Interspeech
 
| booktitle = Interspeech
 
| note = Open Performance Sub-Challenge Prize
 
| note = Open Performance Sub-Challenge Prize
| urllrde = 200909-INTERSPEECH-A
 
 
| abstract = In this paper, we describe systems that were developed for the Open Performance Sub-Challenge of the INTERSPEECH 2009 Emotion Challenge. We participate to both two-class and five-class emotion detection. For the two-class problemthe best performance is obtained by logistic regression fusion of three systems. Theses systems use short- and long-term speech features. This fusion achieved an absolute improvement of 2,6% on the unweighted recall value compared with [6]. For the five-class problem, we submitted two individual systems: cepstral GMM vs. long-term GMM-UBM. The best result comes from a cepstral GMM and produced an absolute improvement of 3,5% compared to [6].
 
| abstract = In this paper, we describe systems that were developed for the Open Performance Sub-Challenge of the INTERSPEECH 2009 Emotion Challenge. We participate to both two-class and five-class emotion detection. For the two-class problemthe best performance is obtained by logistic regression fusion of three systems. Theses systems use short- and long-term speech features. This fusion achieved an absolute improvement of 2,6% on the unweighted recall value compared with [6]. For the five-class problem, we submitted two individual systems: cepstral GMM vs. long-term GMM-UBM. The best result comes from a cepstral GMM and produced an absolute improvement of 3,5% compared to [6].
 
| lrdenewsdate = 2009-06-22
 
| lrdenewsdate = 2009-06-22

Latest revision as of 11:14, 26 April 2016

Abstract

In this paper, we describe systems that were developed for the Open Performance Sub-Challenge of the INTERSPEECH 2009 Emotion Challenge. We participate to both two-class and five-class emotion detection. For the two-class problemthe best performance is obtained by logistic regression fusion of three systems. Theses systems use short- and long-term speech features. This fusion achieved an absolute improvement of 2,6% on the unweighted recall value compared with [6]. For the five-class problem, we submitted two individual systems: cepstral GMM vs. long-term GMM-UBM. The best result comes from a cepstral GMM and produced an absolute improvement of 3,5% compared to [6].


Bibtex (lrde.bib)

@InProceedings{	  dehak.09.interspeechb,
  author	= {Pierre Dumouchel and Najim Dehak and Yazid Attabi and
		  R\'eda Dehak and Narj\`es Boufaden},
  title		= {Cepstral and Long-Term Features for Emotion Recognition},
  booktitle	= {Interspeech},
  year		= 2009,
  month		= sep,
  note		= {Open Performance Sub-Challenge Prize},
  abstract	= {In this paper, we describe systems that were developed for
		  the Open Performance Sub-Challenge of the INTERSPEECH 2009
		  Emotion Challenge. We participate to both two-class and
		  five-class emotion detection. For the two-class problem,
		  the best performance is obtained by logistic regression
		  fusion of three systems. Theses systems use short- and
		  long-term speech features. This fusion achieved an absolute
		  improvement of 2,6\% on the unweighted recall value
		  compared with [6]. For the five-class problem, we submitted
		  two individual systems: cepstral GMM vs. long-term GMM-UBM.
		  The best result comes from a cepstral GMM and produced an
		  absolute improvement of 3,5\% compared to [6].}
}