用信息论方法量化语音中多维度独立性，揭示情感与语言病理特征的编码差异。
Quantifying Dimensional Independence in Speech: An Information-Theoretic Framework for Disentangled Representation Learning
- 引入带边界约束的神经互信息估计，结合非参数验证量化语音特征间依赖关系。
- 跨维度互信息低于0.15纳特，源-滤波器间互信息达0.47纳特，显示弱耦合性。
- 情感由声源主导（80%），语言与病理由滤波器主导（60%和58%），适合表征学习研究者。
语音信号在共享声学通道中编码情绪、语言及病理信息；然而，解耦性通常通过下游任务性能间接评估。本文提出一种信息论框架，通过结合有界神经互信息（MI）估计与非参数验证，量化手工特征中多维度间的统计依赖性。在六个语料库上，跨维度互信息保持较低水平（<0.15纳特），估计边界紧密，表明数据中耦合较弱，而源-滤波器间互信息显著更高（0.47纳特）。归因分析显示，情绪维度中源成分贡献80%的总互信息，语言与病理维度分别由滤波器成分主导（60%和58%）。该研究为语音中维度独立性的量化提供了原则性方法。
原文摘要 · Abstract (English)
Speech signals encode emotional, linguistic, and pathological information within a shared acoustic channel; however, disentanglement is typically assessed indirectly through downstream task performance. We introduce an information-theoretic framework to quantify cross-dimension statistical dependence in handcrafted acoustic features by integrating bounded neural mutual information (MI) estimation with non-parametric validation. Across six corpora, cross-dimension MI remains low, with tight estimation bounds ($< 0.15$ nats), indicating weak statistical coupling in the data considered, whereas Source--Filter MI is substantially higher (0.47 nats). Attribution analysis, defined as the proportion of total MI attributable to source versus filter components, reveals source dominance for emotional dimensions (80\%) and filter dominance for linguistic and pathological dimensions (60\% and 58\%, respectively). These findings provide a principled framework for quantifying dimensional independence in speech.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。