Report Open Access

Cross-Dataset Music Emotion Recognition: an End-to-End Approach

Pandrea, Ana Gabriela; Gómez-Cañón, Juan Sebastián; Herrera, Perfecto

The topic of Music Emotion Recognition (MER) evolved as music is a fascinating expression of emotions, yet it faces challenges given its subjectivity. Because each language has its particularities in terms of sound and intonation, and implicitly associations made upon them, we hypothesize perceived emotions might vary in different cultures. To address this issue, we test a novel approach towards emotion detection and propose a language sensitive end-to-end model that learns to tag emotions from music with lyrics in English, Mandarin and Turkish.

Files (75.9 kB)
Name Size
ISMIR2020_LBD_AGP_Cross_Dataset_MER.pdf
md5:b99c200f996dcb26ad182b795c188022
75.9 kB Download
49
26
views
downloads
All versions This version
Views 4949
Downloads 2626
Data volume 2.0 MB2.0 MB
Unique views 3737
Unique downloads 2121

Share

Cite as