Abstract A cognitive architecture for inner speech is presented. It is based on the Standard Model of Mind, integrated with modules for self-talking. Briefly, the working memory of the proposed architecture includes the phonological loop as a component which manages the exchanging information between the phonological store and the articulatory control system. The inner dialogue is modeled as a loop where the phonological store hears the inner voice produced by the hidden articulator process. A central executive module drives the whole system, and contributes to the generation of conscious thoughts by retrieving information from long-term memory. The surface form of thoughts thus emerges by the phonological loop. Once a conscious thought is elicited by inner speech, the perception of new context takes place and then repeating the cognitive loop. A preliminary formalization of some of the described processes by event calculus, and early results of their implementation on the humanoid robot Pepper by SoftBank Robotics are discussed.

中文翻译：

---

内在言语的认知架构

摘要 提出了一种内部语音的认知架构。它基于标准思维模型，集成了自我对话模块。简而言之，所提出架构的工作记忆包括作为管理语音存储和发音控制系统之间交换信息的组件的语音循环。内部对话被建模为一个循环，其中语音存储听到隐藏的发音器过程产生的内部声音。一个中央执行模块驱动整个系统，并通过从长期记忆中检索信息来促进有意识的想法的产生。因此，思想的表层形式是通过语音循环出现的。一旦有意识的想法被内在的言语引出，对新环境的感知就会发生，然后重复认知循环。