Open AccessAn Analysis of the Impact of Spectral Contrast Feature in Speech Emotion Recognition
Author(s) -
Shreya Kumar,
Swarnalaxmi Thiruvenkadam
Publication year - 2021
Publication title -
international journal of recent contributions from engineering, science and it
Language(s) - English
Resource type - Journals
ISSN - 2197-8581
DOI - 10.3991/ijes.v9i2.22983
Subject(s) - contrast (vision) , emotion recognition , feature (linguistics) , speech recognition , german , computer science , feature extraction , arousal , pattern recognition (psychology) , artificial intelligence , psychology , linguistics , social psychology , philosophy
Feature extraction is an integral part in speech emotion recognition. Some emotions become indistinguishable from others due to high resemblance in their features, which results in low prediction accuracy. This paper analyses the impact of spectral contrast feature in increasing the accuracy for such emotions. The RAVDESS dataset has been chosen for this study. The SAVEE dataset, CREMA-D dataset and JL corpus dataset were also used to test its performance over different English accents. In addition to that, EmoDB dataset has been used to study its performance in the German language. The use of spectral contrast feature has increased the prediction accuracy in speech emotion recognition systems to a good degree as it performs well in distinguishing emotions with significant differences in arousal levels, and it has been discussed in detail.