Deep neural networks are inherently opaque and challenging to interpret. Unlike hand-crafted feature-based models, we struggle to comprehend the concepts learned and how they interact within these models. This understanding is crucial not only for debugging purposes but also for ensuring fairness in ethical decision-making. In our study, we conduct a post-hoc functional interpretability analysis of pretrained speech models using the probing framework [1]. Specifically, we analyze utterance-level representations of speech models trained for various tasks such as speaker recognition and dialect identification. We conduct layer and neuron-wise analyses, probing for speaker, language, and channel properties. Our study aims to answer the following questions: i) what information is captured within the representations? ii) how is it represented and distributed? and iii) can we identify a minimal subset of the network that possesses this information? Our results reveal several novel findings, including: i) channel and gender information are distributed across the network, ii) the information is redundantly available in neurons with respect to a task, iii) complex properties such as dialectal information are encoded only in the task-oriented pretrained network, iv) and is localised in the upper layers, v) we can extract a minimal subset of neurons encoding the pre-defined property, vi) salient neurons are sometimes shared between properties, vii) our analysis highlights the presence of biases (for example gender) in the network. Our cross-architectural comparison indicates that: i) the pretrained models capture speaker-invariant information, and ii) CNN models are competitive with Transformer models in encoding various understudied properties.

翻译：深度神经网络本质上是黑箱模型且难以解释。与基于手工特征的传统模型不同，我们难以理解这些模型所学习的概念及其交互方式。这种理解不仅对调试至关重要，也对确保伦理决策的公平性不可或缺。本研究采用探测框架[1]对预训练语音模型进行事后功能性可解释性分析。具体而言，我们分析了面向说话人识别、方言辨识等不同任务训练的语音模型的语句级表征，通过逐层和逐神经元分析，探测说话人、语言和信道属性。本研究旨在回答以下问题：i) 表征中捕获了哪些信息？ii) 这些信息如何表示和分布？iii) 能否识别出包含这些信息的最小网络子集？研究结果揭示了多项新颖发现，包括：i) 信道和性别信息分布于整个网络，ii) 信息在神经元层面关于特定任务存在冗余性，iii) 方言信息等复杂属性仅编码于任务导向的预训练网络，iv) 且集中于网络高层，v) 可提取编码预设属性的最小神经元子集，vi) 重要神经元有时在属性间共享，vii) 分析揭示了网络中存在的偏差（如性别偏差）。跨架构比较表明：i) 预训练模型捕获了说话人不变信息，ii) CNN模型在编码多种待研究属性方面与Transformer模型具有可比性。