SOURCE-LINKED INTELLIGENCE

Interpreting hierarchical organisation of speaker embeddings

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Speaker recognition neural networks learn latent representations (i.e. speaker embeddings) from input utterances to recognise speaker identities. However, the internal mechanisms of these networks remain largely opaque, motivating research in explainable artificial intelligence (XAI) to understand them. Nevertheless, existing studies have analysed how speaker embeddings are organised, but rarely frame these analyses within XAI. Hence, this work proposes to explain and interpret the organisation of speaker embeddings from an XAI perspective. To this end, we apply a hierarchical clustering algor

Read original source ↗ Open in workspace

recordType

paper

region

Global