# Explainable AI in Speaker Recognition -- Making Latent Representations Understandable

arXiv: https://arxiv.org/abs/2604.23354 · HTML: https://mlsanity.com/paper/2604.23354/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 66 references that are in the map.
- First posted on arXiv 25 Apr 2026.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [GANalyze: Toward Visual Definitions of Cognitive Image Properties](https://mlsanity.com/paper/1906.10112/) (2019)
- [Grad-CAM: Why did you say that?](https://mlsanity.com/paper/1611.07450/) (2016)
- [In defence of metric learning for speaker recognition](https://mlsanity.com/paper/2003.11982/) (2020)
- [Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System](https://mlsanity.com/paper/1804.05160/) (2018)
- [XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models](https://mlsanity.com/paper/2407.15248/) (2024)
- [How humans learn and represent networks](https://mlsanity.com/paper/1909.07186/) (2019)
- [Objective-Based Hierarchical Clustering of Deep Embedding Vectors](https://mlsanity.com/paper/2012.08466/) (2020)
- [Explain to Not Forget: Defending Against Catastrophic Forgetting with XAI](https://mlsanity.com/paper/2205.01929/) (2022)
- [Supervised Hierarchical Clustering using Graph Neural Networks for Speaker Diarization](https://mlsanity.com/paper/2302.12716/) (2023)
- [Intraclass clustering: an implicit learning ability that regularizes DNNs](https://mlsanity.com/paper/2103.06733/) (2021)

## Built on by (most cited first, 3 of 3)

- [Explainable AI in Speaker Recognition -- Attention Map Visualisation and Evaluation](https://mlsanity.com/paper/2606.22901/) (2026)
- [Exploring Second-Order Pattern Recognition in Speaker Recognition](https://mlsanity.com/paper/2609.11182/) (2026)
- [Interpreting hierarchical organisation of speaker embeddings](https://mlsanity.com/paper/2609.15203/) (2026)

## Abstract (arXiv)

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: analysing, visualising and understanding the unknown organisation of network representations, particularly those a speaker recognition network learns from utterances, for recognising speaker identity. Past studies have employed algorithms (e.g. K-means) to analyse the different ways in which network representations can be naturally grouped into clusters, i.e. to analyse different flat clustering phenomena within the space defined by those representations. In contrast, this work applies two algorithms -- Single-Linkage Clustering (SLINK) and Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) -- to analyse the different ways in which representations from the speaker recognition network can form clusters with hierarchical relationships, i.e., to analyse different hierarchical clustering phenomena within the representation space of the speaker recognition network. Furthermore, an algorithm called Hierarchical Cluster-Class Matching (HCCM) is designed to semantically interpret one of the above hierarchical clustering phenomena analysed using SLINK. Given the clusters representing this phenomenon, HCCM identifies which ones best match individual semantic classes related to gender and nationality (e.g. male, female, Ireland, UK) and and-logic conjunctions of these classes (e.g. female and Ireland). The Liebig score metric is also proposed within HCCM to quantify the matching quality of each cluster-class pair and diagnose the factor that limits each match.