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
本文提出发现说话人识别网络中的二阶模式，并设计HCNA方法通过外推机制识别未见语音表现出的二阶模式，实验证明该方法显著提升性能。
AI 中文摘要
在经典模式识别任务中，神经网络被训练用于识别人类定义的输入模式。一些可解释人工智能（XAI）方法能够解释网络将输入识别为人类定义模式时所依据的其他潜在模式；在本工作中，我们将这些潜在模式称为二阶模式，并提出发现它们的方法。为此，我们应用层次聚类算法来分析说话人识别网络从语音中学习到的表示是否自然地形成层次聚类。每个生成的聚类代表一个二阶模式，该模式表征了网络如何将某些已知语音识别为说话人身份。随后，使用现有的层次聚类-类别匹配（HCCM）方法对所有生成的二阶模式进行语义解释。此外，我们提出一个新任务，即二阶模式识别，以识别一个未见语音是否表现出哪些已发现的、表征已知语音的二阶模式。为实现此目标，我们设计了层次聚类导航与分配（HCNA）方法。当未见语音的网络表示位于被视为该二阶模式的聚类的外推空间内时，HCNA识别该已知二阶模式适用于该未见语音。我们的实验表明，HCNA引入的外推机制显著提高了二阶模式识别任务的性能。
英文摘要
In traditional pattern recognition tasks, neural networks are trained to recognise human-defined patterns (e.g. audio categories) in model inputs (e.g. audio). Meanwhile, some Explainable AI (XAI) methods explain latent patterns characterising the network's recognition of inputs as human-defined patterns; this work calls these latent patterns second-order patterns and proposes to discover them. Accordingly, we apply a hierarchical clustering algorithm to analyse whether our speaker recognition network's representations learned from known utterances naturally form hierarchical clusters. Each resulting cluster is a second-order pattern that characterises a context in our network's recognition of the known utterances as speaker identities. All discovered second-order patterns are then interpreted using the Hierarchical Cluster-Class Matching (HCCM) method. Moreover, we propose a new task, second-order pattern recognition, to identify which of the discovered second-order patterns characterising the recognition of known utterances also apply to unseen utterances, thereby characterising the recognition of unseen utterances. Accordingly, we design the Hierarchical Cluster Navigation and Assignment (HCNA) method. HCNA recognises a second-order pattern as applying to an unseen utterance when the utterance's network representation lies within the extrapolation space of the cluster regarded as that second-order pattern. Experimental results demonstrate that the extrapolation space introduced in HCNA substantially improves task performance.
CommentsSubmit to ICASSP 2027
