基于深度图随机过程的思维语音识别
Deep Graph Random Process for Relational-Thinking-Based Speech Recognition
摘要：
关系思维是人类智能的核心，它的特点是最初依赖于无数与新的感觉信号和先验知识之间的关系有关的无意识感知，然后通过这些感知的耦合和转换成为可识别的概念或对象。这样的心理过程难以在诸如会话自动语音识别（ASR）的现实世界问题中建模，因为感知（如果它们被建模为指示话语之间的关系的图）被认为是无数的并且不能直接观察到。在本文中，我们提出了一种称为深度图随机过程（DGP）的贝叶斯非参数深度学习方法，该方法可以生成表示感知的无限数量的概率图。我们进一步提供了一个封闭形式的解决方案，耦合和转换这些感知图的声学建模。我们的方法是能够成功地推断话语之间的关系，而不使用任何关系数据在训练过程中。在CHiME-2和CHiME-5等ASR任务上的实验结果表明了该方法的有效性和优越性。
英文摘要：
Lying at the core of human intelligence, relational thinking is characterized by initially relying on innumerable unconscious percepts pertaining to relations between new sensory signals and prior knowledge, consequently becoming a recognizable concept or object through coupling and transformation of these percepts. Such mental processes are difficult to model in real-world problems such as in conversational automatic speech recognition (ASR), as the percepts (if they are modelled as graphs indicating relationships among utterances) are supposed to be innumerable and not directly observable. In this paper, we present a Bayesian nonparametric deep learning method called deep graph random process (DGP) that can generate an infinite number of probabilistic graphs representing percepts. We further provide a closed-form solution for coupling and transformation of these percept graphs for acoustic modeling. Our approach is able to successfully infer relations among utterances without using any relational data during training. Experimental evaluations on ASR tasks including CHiME-2 and CHiME-5 demonstrate the effectiveness and benefits of our method.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
