Publication Details

Enhancing multilingual recognition of emotion in speech by language identification

SAGHA Hesam, MATĚJKA Pavel, GAVRYUOKOVA Maryna, POVOLNÝ Filip, MARCHI Erik and SCHULLER Björn W. Enhancing multilingual recognition of emotion in speech by language identification. In: 17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION - Proceedings (INTERSPEECH 2016). San Francisco: International Speech Communication Association, 2016, pp. 2949-2953. ISSN 1990-9772. Available from: https://www.isca-speech.org/archive/Interspeech_2016/pdfs/0333.PDF
Czech title
Rozšíření multilingválního rozpoznávání emocí v řeči pomocí rozpoznávání jazyka
Type
conference paper
Language
english
Authors
Sagha Hesam (UNIPAS)
Matějka Pavel, Ing., Ph.D. (DCGM FIT BUT)
Gavryuokova Maryna (UNIPAS)
Povolný Filip, Ing. (Phonexia)
Marchi Erik (UNIPAS)
Schuller Björn W. (UNIPAS)
URL
Keywords

multilingual emotion recognition, language identification, language families

Abstract

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.

Published
2016
Pages
2949-2953
Journal
Proceedings of Interspeech - on-line, no. 9, ISSN 1990-9772
Proceedings
17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION - Proceedings (INTERSPEECH 2016)
Conference
Interspeech Conference, San Francisco, US
Publisher
International Speech Communication Association
Place
San Francisco, US
DOI
UT WoS
000409394401295
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB12240,
   author = "Hesam Sagha and Pavel Mat\v{e}jka and Maryna Gavryuokova and Filip Povoln\'{y} and Erik Marchi and W. Bj{\"{o}}rn Schuller",
   title = "Enhancing multilingual recognition of emotion in speech by language identification",
   pages = "2949--2953",
   booktitle = "17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION - Proceedings (INTERSPEECH 2016)",
   journal = "Proceedings of Interspeech - on-line",
   number = 9,
   year = 2016,
   location = "San Francisco, US",
   publisher = "International Speech Communication Association",
   ISSN = "1990-9772",
   doi = "10.21437/Interspeech.2016-333",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12240"
}
Back to top