@InProceedings{lakomkin-EtAl:2017:I17-1,
  author    = {Lakomkin, Egor  and  Weber, Cornelius  and  Magg, Sven  and  Wermter, Stefan},
  title     = {Reusing Neural Speech Representations for Auditory Emotion Recognition},
  booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  month     = {November},
  year      = {2017},
  address   = {Taipei, Taiwan},
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {423--430},
  abstract  = {Acoustic emotion recognition aims to categorize the affective state of the
	speaker and is still a difficult task for machine learning models. The
	difficulties come from the scarcity of training data, general subjectivity in
	emotion perception resulting in low annotator agreement, and the uncertainty
	about which features are the most relevant and robust ones for classification.
	In this paper, we will tackle the latter problem. Inspired by the recent
	success of transfer learning methods we propose a set of architectures which
	utilize neural representations inferred by training on large speech databases
	for the acoustic emotion recognition task. Our experiments on the IEMOCAP
	dataset show ~10% relative improvements in the accuracy and F1-score over the
	baseline recurrent neural network which is trained end-to-end for emotion
	recognition.},
  url       = {http://www.aclweb.org/anthology/I17-1043}
}