Adding speaker-contrastive or BYOL self-supervised pretraining to a Whisper-based model improves low-resource speech emotion recognition on Urdu, German, and Bangla.
Modular neural-svm scheme for speech emotion recognition using anova feature selec- tion method,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Learning More with Less: Self-Supervised Approaches for Low-Resource Speech Emotion Recognition
Adding speaker-contrastive or BYOL self-supervised pretraining to a Whisper-based model improves low-resource speech emotion recognition on Urdu, German, and Bangla.