A Study of Cross-Linguistic Speech Emotion Recognition Based on 2D Feature Spaces - Publication - MOST Wiedzy

Search

A Study of Cross-Linguistic Speech Emotion Recognition Based on 2D Feature Spaces

Abstract

In this research, a study of cross-linguistic speech emotion recognition is performed. For this purpose, emotional data of different languages (English, Lithuanian, German, Spanish, Serbian, and Polish) are collected, resulting in a cross-linguistic speech emotion dataset with the size of more than 10.000 emotional utterances. Despite the bi-modal character of the databases gathered, our focus is on the acoustic representation only. The assumption is that the speech audio signal carries sufficient emotional information to detect and retrieve it. Several two-dimensional acoustic feature spaces, such as cochleagrams, spectrograms, mel-cepstrograms, and fractal dimension-based space, are employed as the representations of speech emotional features. A convolutional neural network (CNN) is used as a classifier. The results show the superiority of cochleagrams over other feature spaces utilized. In the CNN-based speaker-independent cross-linguistic speech emotion recognition (SER) experiment, the accuracy of over 90% is achieved, which is close to the monolingual case of SER.

Citations

  • 0

    CrossRef

  • 0

    Web of Science

  • 0

    Scopus

Authors (6)

Details

Category:
Articles
Type:
artykuły w czasopismach
Published in:
Electronics no. 9,
ISSN: 2079-9292
Language:
English
Publication year:
2020
Bibliographic description:
Tamulevicius G., Korvel G., Yayak A., Treigys P., Bernataviciene J., Kostek B.: A Study of Cross-Linguistic Speech Emotion Recognition Based on 2D Feature Spaces// Electronics -Vol. 9,iss. 10 (2020), s.1725-
DOI:
Digital Object Identifier (open in new tab) 10.3390/electronics9101725
Sources of funding:
  • Działalność statusowa
Verified by:
Gdańsk University of Technology

seen 5 times

Recommended for you

Meta Tags