Fine-tuning pretrained speaker verification models on augmented children's speech reduces error rates in English-speaking classrooms, with ECAPA-TDNN nearly halving error on the MPT dataset.
Adversarial data augmentation for robust speaker verification,
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
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
FT-Boosted SV: Towards Noise Robust Speaker Verification for English Speaking Classroom Environments
Fine-tuning pretrained speaker verification models on augmented children's speech reduces error rates in English-speaking classrooms, with ECAPA-TDNN nearly halving error on the MPT dataset.