@InProceedings{lakomkin-weber-wermter:2017:EACLshort,
  author    = {Lakomkin, Egor  and  Weber, Cornelius  and  Wermter, Stefan},
  title     = {Automatically augmenting an emotion dataset improves classification using audio},
  booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {194--197},
  abstract  = {In this work, we tackle a problem of speech emotion classification. One of the
	issues in the area of affective computation is that the amount of annotated
	data is very limited. On the other hand, the number of ways that the same
	emotion can be expressed verbally is enormous due to variability between
	speakers. This is one of the factors that limits performance and
	generalization. We propose a simple method that extracts audio samples from
	movies using textual sentiment analysis. As a result, it is possible to
	automatically construct a larger dataset of audio samples with positive,
	negative emotional and neutral speech. We show that pretraining recurrent
	neural network on such a dataset yields better results on the challenging
	EmotiW corpus. This experiment shows a potential benefit of combining textual
	sentiment analysis with vocal information.},
  url       = {http://www.aclweb.org/anthology/E17-2031}
}