Detail publikace

Enhancing multilingual recognition of emotion in speech by language identification

SAGHA, H. MATĚJKA, P. GAVRYUOKOVA, M. POVOLNÝ, F. MARCHI, E. SCHULLER, B.

Originální název

Enhancing multilingual recognition of emotion in speech by language identification

Anglický název

Enhancing multilingual recognition of emotion in speech by language identification

Jazyk

en

Originální abstrakt

We investigate, for the first time, if applying model selection based on automatic language identification (LID) can improve multilingual recognition of emotion in speech. Six emotional speech corpora from three language families (Germanic, Romance, Sino-Tibetan) are evaluated. The emotions are represented by the quadrants in the arousal/valence plane, i. e., positive/ negative arousal/valence. Four selection approaches for choosing an optimal training set depending on the current language are compared: within the same language family, across language family, use of all available corpora, and selection based on the automatic LID. We found that, on average, the proposed LID approach for selecting training corpora is superior to using all the available corpora when the spoken language is not known.

Anglický abstrakt

We investigate, for the first time, if applying model selection based on automatic language identification (LID) can improve multilingual recognition of emotion in speech. Six emotional speech corpora from three language families (Germanic, Romance, Sino-Tibetan) are evaluated. The emotions are represented by the quadrants in the arousal/valence plane, i. e., positive/ negative arousal/valence. Four selection approaches for choosing an optimal training set depending on the current language are compared: within the same language family, across language family, use of all available corpora, and selection based on the automatic LID. We found that, on average, the proposed LID approach for selecting training corpora is superior to using all the available corpora when the spoken language is not known.

Dokumenty

BibTex


@inproceedings{BUT163404,
  author="Pavel {Matějka} and Filip {Povolný}",
  title="Enhancing multilingual recognition of emotion in speech by language identification",
  annote="We investigate, for the first time, if applying model selection based on
automatic language identification (LID) can improve multilingual recognition of
emotion in speech. Six emotional speech corpora from three language families
(Germanic, Romance, Sino-Tibetan) are evaluated. The emotions are represented by
the quadrants in the arousal/valence plane, i. e., positive/ negative
arousal/valence. Four selection approaches for choosing an optimal training set
depending on the current language are compared: within the same language family,
across language family, use of all available corpora, and selection based on the
automatic LID. We found that, on average, the proposed LID approach for selecting
training corpora is superior to using all the available corpora when the spoken
language is not known.",
  address="International Speech Communication Association",
  booktitle="17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION - Proceedings (INTERSPEECH 2016)",
  chapter="163404",
  doi="10.21437/Interspeech.2016-333",
  edition="NEUVEDEN",
  howpublished="online",
  institution="International Speech Communication Association",
  number="9",
  year="2016",
  month="september",
  pages="2949--2953",
  publisher="International Speech Communication Association",
  type="conference paper"
}