Detail publikace

Multimodal Emotion Recognition for AVEC 2016 Challenge

POVOLNÝ, F. MATĚJKA, P. HRADIŠ, M. POPKOVÁ, A. OTRUSINA, L. SMRŽ, P. WOOD, I. ROBIN, C. LAMEL, L.

Originální název

Multimodal Emotion Recognition for AVEC 2016 Challenge

Anglický název

Multimodal Emotion Recognition for AVEC 2016 Challenge

Jazyk

en

Originální abstrakt

This paper describes a systems for emotion recognition and its application on the dataset from the AV+EC 2016 Emotion Recognition Challenge. The realized system was produced and submitted to the AV+EC 2016 evaluation, making use of all three modalities (audio, video, and physiological data). Our work primarily focused on features derived from audio. The original audio features were complement with bottleneck features and also text-based emotion recognition which is based on transcribing audio by an automatic speech recognition system and applying resources such as word embedding models and sentiment lexicons. Our multimodal fusion reached CCC=0.855 on dev set for arousal and 0.713 for valence. CCC on test set is 0.719 and 0.596 for arousal and valence respectively.

Anglický abstrakt

This paper describes a systems for emotion recognition and its application on the dataset from the AV+EC 2016 Emotion Recognition Challenge. The realized system was produced and submitted to the AV+EC 2016 evaluation, making use of all three modalities (audio, video, and physiological data). Our work primarily focused on features derived from audio. The original audio features were complement with bottleneck features and also text-based emotion recognition which is based on transcribing audio by an automatic speech recognition system and applying resources such as word embedding models and sentiment lexicons. Our multimodal fusion reached CCC=0.855 on dev set for arousal and 0.713 for valence. CCC on test set is 0.719 and 0.596 for arousal and valence respectively.

Dokumenty

BibTex


@inproceedings{BUT133512,
  author="Filip {Povolný} and Pavel {Matějka} and Michal {Hradiš} and Anna {Popková} and Lubomír {Otrusina} and Pavel {Smrž} and Ian {Wood} and Cecile {Robin} and Lori {Lamel}",
  title="Multimodal Emotion Recognition for AVEC 2016 Challenge",
  annote="This paper describes a systems for emotion recognition and its application on the
dataset from the AV+EC 2016 Emotion Recognition Challenge. The realized system
was produced and submitted to the AV+EC 2016 evaluation, making use of all three
modalities (audio, video, and physiological data). Our work primarily focused on
features derived from audio. The original audio features were complement with
bottleneck features and also text-based emotion recognition which is based on
transcribing audio by an automatic speech recognition system and applying
resources such as word embedding models and sentiment lexicons. Our multimodal
fusion reached CCC=0.855 on dev set for arousal and 0.713 for valence. CCC on
test set is 0.719 and 0.596 for arousal and valence respectively.",
  address="Association for Computing Machinery",
  booktitle="AVEC '16 Proceedings of the 6th International Workshop on Audio/Visual Emotion Challenge",
  chapter="133512",
  doi="10.1145/2988257.2988268",
  edition="NEUVEDEN",
  howpublished="online",
  institution="Association for Computing Machinery",
  year="2016",
  month="october",
  pages="75--82",
  publisher="Association for Computing Machinery",
  type="conference paper"
}