What is it about?
SUBESCO is an audio-only emotional speech corpus for Bangla language. It is the largest emotional speech corpus available for this language. Twenty native speakers participated in the gender-balanced set, each recording of 10 sentences simulating seven targeted emotions. Fifty university students participated in the evaluation of this corpus. Overall recognition rate was reported to be above 70% for human perception tests. SUBESCO is an Open Access database, licensed under Creative Common Attribution 4.0 International.
Featured Image
Photo by Icons8 Team on Unsplash
Why is it important?
Studies showed that SER models performed best for the particular languages on which those were trained on. The motivation of creating SUBESCO is to develop a separate dataset for the Bangla language to facilitate the construction of SER as using a non-Bangla dataset to train Bangla SER may yield a poorer recognition rate.
Perspectives
A high rate of reliability and consistency of evaluation task shows that this corpus should be considered as a valuable resource for the research on emotion analysis and classification for Bangla language.
Sadia Sultana
Shahjalal University of Science and Technology
Read the Original
This page is a summary of: SUST Bangla Emotional Speech Corpus (SUBESCO): An audio-only emotional speech corpus for Bangla, PLoS ONE, April 2021, PLOS,
DOI: 10.1371/journal.pone.0250173.
You can read the full text:
Resources
Contributors
The following have contributed to this page
