Detail publikace

Investigation of Bottle-Neck Features for Emotion Recognition

POPKOVÁ, A. POVOLNÝ, F. MATĚJKA, P. GLEMBEK, O. GRÉZL, F. ČERNOCKÝ, J.

Originální název

Investigation of Bottle-Neck Features for Emotion Recognition

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

This paper describes several systems for emotion recognitiondeveloped for the AV+EC 2015 Emotion Recognition Challenge.A complete system, making use of all three modalities (audio, video, andphysiological data), was submitted to the evaluation. The focus of ourwork was, however, on the so called Bottle-Neck features used to complementthe audio features. For the recognition of arousal, we improved theresults of the delivered audio features and combined them favorably withthe Bottle-Neck features. For valence, the best results were obtained withvideo, but a two-output Bottle-Neck structure is not far behind, whichis especially appealing for applications where only audio is available.

Klíčová slova

Emotion recognition, Bottle-Neck features, Context, Fusion

Autoři

POPKOVÁ, A.; POVOLNÝ, F.; MATĚJKA, P.; GLEMBEK, O.; GRÉZL, F.; ČERNOCKÝ, J.

Vydáno

12. 9. 2016

Nakladatel

International Speech Communication Association

Místo

Brno

ISSN

0302-9743

Periodikum

Lecture Notes in Computer Science

Ročník

9924

Číslo

9

Stát

Spolková republika Německo

Strany od

426

Strany do

434

Strany počet

9

URL

BibTex

@inproceedings{BUT163393,
  author="Anna {Popková} and Filip {Povolný} and Pavel {Matějka} and Ondřej {Glembek} and František {Grézl} and Jan {Černocký}",
  title="Investigation of Bottle-Neck Features for Emotion Recognition",
  booktitle="19th International Conference, TSD 2016, Brno , Czech Republic, September 12-16, 2016, Proceedings",
  year="2016",
  series="Lecture Notes in Computer Science, Lecture Notes in Artificial Intelligence",
  journal="Lecture Notes in Computer Science",
  volume="9924",
  number="9",
  pages="426--434",
  publisher="International Speech Communication Association",
  address="Brno",
  doi="10.1007/978-3-319-45510-5\{_}49",
  issn="0302-9743",
  url="https://link.springer.com/chapter/10.1007/978-3-319-45510-5_49"
}

Dokumenty