发表机构
University of Surrey; King's College London（萨里大学; 伦敦国王学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文从可解释人工智能视角，用SLINK层次聚类分析说话人嵌入的层次组织，提出HCCM方法及L-score指标，以性别、国籍等语义类解释簇结构。
AI 中文摘要
说话人识别神经网络从输入话语中学习潜在表示（即说话人嵌入）以识别说话人身份。然而，这些网络的内部机制在很大程度上仍然不透明，这促使了可解释人工智能（XAI）领域的研究以理解它们。尽管如此，现有研究分析了说话人嵌入的组织方式，但很少将这些分析置于XAI框架内。因此，本工作提出从XAI视角解释和阐述说话人嵌入的组织结构。为此，我们应用一种层次聚类算法——单链接聚类（SLINK），来分析某些说话人嵌入是否自然地形成具有层次关系的簇。所得的层次组织（即层次簇）使用簇类匹配（CCM）方法进行评估。此外，我们提出了一种新方法，称为层次簇类匹配（HCCM），以识别哪些层次簇与个体语义类（如男性）和合取语义类（如英国与男性）最佳匹配，从而通过其匹配的类别来解释这些簇。匹配程度使用一种新指标——L分数进行量化，该指标使不完美匹配可诊断。HCCM的结果表明，通过SLINK分析的层次簇可使用与说话人身份、性别和国籍相关的不同类别进行解释，为我们所考察的说话人嵌入的层次组织中的语义提供了见解。
英文摘要
Speaker recognition neural networks recognise speaker identities from input utterances by learning latent representations (i.e. speaker embeddings). However, these networks' internal mechanisms remain largely opaque, motivating research in explainable artificial intelligence (XAI) to understand them. Existing studies have analysed how speaker embeddings are organised, but rarely frame these analyses within XAI. 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 our prepared 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 like male and conjunctive semantic classes like UK & male, thereby interpreting the clusters using their matched classes. We quantify the matching degree with a new metric called the L-score, which makes imperfect matches diagnosable. HCCM's results reveal that the hierarchical clusters analysed by SLINK are well interpreted using classes related to speaker identity, gender, and nationality, showing the semantics inside the hierarchical organisation of the examined speaker embeddings.
CommentsSubmit to ICASSP 2027
