The paper introduces Modified RISE-eval to evaluate GradCAM and LayerCAM attention maps on speaker recognition networks and reports distinct advantages for each method under different conditions.
In defence of metric learning for speaker recognition
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
eess.AS 2years
2026 2representative citing papers
Hierarchical clustering of speaker recognition embeddings reveals that the network organizes representations by gender at upper levels and by gender-nationality conjunctions at lower levels, interpreted via a proposed cluster-class matching method.
citing papers explorer
-
Explainable AI in Speaker Recognition -- Attention Map Visualisation and Evaluation
The paper introduces Modified RISE-eval to evaluate GradCAM and LayerCAM attention maps on speaker recognition networks and reports distinct advantages for each method under different conditions.
-
Explainable AI in Speaker Recognition -- Making Latent Representations Understandable
Hierarchical clustering of speaker recognition embeddings reveals that the network organizes representations by gender at upper levels and by gender-nationality conjunctions at lower levels, interpreted via a proposed cluster-class matching method.