Interpreting hierarchical organisation of speaker embeddings

• URL: http://arxiv.org/abs/2609.15203v1
• Date: Mon, 14 Sep 2026 08:25:57 GMT
• Title: Interpreting hierarchical organisation of speaker embeddings
• Abstract summary: Speaker recognition neural networks learn latent representations (i.e. speaker embeddings) from input utterances to recognise speaker identities.<n>Existing studies have analysed how speaker embeddings are organised, but rarely frame these analyses within XAI.<n>This work proposes to explain and interpret the organisation of speaker embeddings from an XAI perspective.
• Score: 21.594428525994285
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 algorithm, Single-Linkage Clustering (SLINK), to analyse whether some speaker embeddings naturally form clusters with hierarchical relationships. The resulting hierarchical organisation (i.e. hierarchical clusters) is evaluated using the Cluster-Class Matching (CCM) method. Moreover, we propose a new method, termed Hierarchical Cluster-Class Matching (HCCM), to identify which hierarchical clusters best match individual semantic classes (e.g. male) and conjunctive semantic classes (e.g. UK & male), thereby interpreting the clusters using their matched classes. The matching degree is quantified using a new metric called the L-score, which makes imperfect matches diagnosable. HCCM's results show that hierarchical clusters analysed by SLINK are interpreted using different classes related to speaker identity, gender, and nationality, providing insight into semantics within the hierarchical organisation of our examined speaker embeddings.

Related papers

• Multilingual Multi-Speaker Unit Vocoders: A Systematic Analysis of Discrete Speech Representations [0.0]
  Discrete speech units obtained via k-means clustering of self supervised embeddings entangle phonetic, speaker, and language information.<n>We analyze a BigVGAN based unit vocoder, across four Indian languages.
  arXiv  Detail & Related papers  (2026-06-04T21:54:56Z)
• Explainable AI in Speaker Recognition -- Making Latent Representations Understandable [21.594428525994285]
  This paper proposes to study an XAI topic: uncovering unknown organisational patterns in network representations.<n>It applies two algorithms to analyse how representations form clusters with hierarchical relationships rather than being independent.<n>A new metric, Liebig's score, is proposed to diagnose the factor that most strongly limits matching performance.
  arXiv  Detail & Related papers  (2026-04-25T15:44:20Z)
• Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings [10.299190830046872]
  We present a post-hoc framework to explain, verify, and align semantic hierarchies induced by a VLM over a given set of child classes.<n>We quantify plausibility by comparing the extracted tree against human retrieval using efficient tree-aware and edge-level consistency measures, and we evaluate utility via explainable hierarchical tree-traversal inference.
  arXiv  Detail & Related papers  (2026-03-26T00:38:38Z)
• A Semantics-Aware Hierarchical Self-Supervised Approach to Classification of Remote Sensing Images [12.282079123411947]
  We present a novel Semantics-Aware Hierarchical Consensus (SAHC) method for learning hierarchical features and relationships.<n>The SAHC method is evaluated on three benchmark datasets with different degrees of hierarchical complexity.<n> Experimental results show both the effectiveness of the proposed approach in guiding network learning and the robustness of the hierarchical consensus for remote sensing image classification tasks.
  arXiv  Detail & Related papers  (2025-10-06T15:30:39Z)
• Hierarchical Representation Matching for CLIP-based Class-Incremental Learning [80.2317078787969]
  Class-Incremental Learning (CIL) aims to endow models with the ability to continuously adapt to evolving data streams.<n>Recent advances in pre-trained vision-language models (e.g., CLIP) provide a powerful foundation for this task.<n>We introduce HiErarchical Representation MAtchiNg (HERMAN) for CLIP-based CIL.
  arXiv  Detail & Related papers  (2025-09-26T17:59:51Z)
• Bidirectional Logits Tree: Pursuing Granularity Reconcilement in Fine-Grained Classification [89.20477310885731]
  This paper addresses the challenge of Granularity Competition in fine-grained classification tasks.<n>Existing approaches typically develop independent hierarchy-aware models based on shared features extracted from a common base encoder.<n>We propose a novel framework called the Bidirectional Logits Tree (BiLT) for Granularity Reconcilement.
  arXiv  Detail & Related papers  (2024-12-17T10:42:19Z)
• Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment [53.2701026843921]
  Large-scale pre-trained Vision Language Models (VLMs) have proven effective for zero-shot classification. In this paper, we aim at a more challenging setting, Realistic Zero-Shot Classification, which assumes no annotation but instead a broad vocabulary. We propose the Self Structural Semantic Alignment (S3A) framework, which extracts structural semantic information from unlabeled data while simultaneously self-learning.
  arXiv  Detail & Related papers  (2023-08-24T17:56:46Z)
• Using Representation Expressiveness and Learnability to Evaluate Self-Supervised Learning Methods [61.49061000562676]
  We introduce Cluster Learnability (CL) to assess learnability. CL is measured in terms of the performance of a KNN trained to predict labels obtained by clustering the representations with K-means. We find that CL better correlates with in-distribution model performance than other competing recent evaluation schemes.
  arXiv  Detail & Related papers  (2022-06-02T19:05:13Z)
• Unsupervised Learning of Hierarchical Conversation Structure [50.29889385593043]
  Goal-oriented conversations often have meaningful sub-dialogue structure, but it can be highly domain-dependent. This work introduces an unsupervised approach to learning hierarchical conversation structure, including turn and sub-dialogue segment labels. The decoded structure is shown to be useful in enhancing neural models of language for three conversation-level understanding tasks.
  arXiv  Detail & Related papers  (2022-05-24T17:52:34Z)
• Bi-LSTM Scoring Based Similarity Measurement with Agglomerative Hierarchical Clustering (AHC) for Speaker Diarization [0.0]
  A typical conversation between two speakers consists of segments where their voices overlap, interrupt each other or halt their speech in between multiple sentences. Recent advancements in diarization technology leverage neural network-based approaches to improvise speaker diarization system. We propose a Bi-directional Long Short-term Memory network for estimating the elements present in the similarity matrix.
  arXiv  Detail & Related papers  (2022-05-19T17:20:51Z)
• Learning and Evaluating Representations for Deep One-class Classification [59.095144932794646]
  We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations. In experiments, we demonstrate state-of-the-art performance on visual domain one-class classification benchmarks.
  arXiv  Detail & Related papers  (2020-11-04T23:33:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.