Explainable AI in Speaker Recognition -- Making Latent Representations Understandable

ArXi:2604.23354v1 Announce Type: cross Neural networks can be trained to learn task-relevant representations from data. Understanding how these networks make decisions falls within the Explainable AI (XAI) domain. This paper proposes to study an XAI topic: uncovering unknown organisational patterns in network representations, particularly those representations learned by the speaker recognition network that recognises the speaker identity of utterances. Past studies employed algorithms (e.g.