Speech monitoring encompasses detection and self-repair of errors.This paper first reviews types of errors and self-repairs,then focuses on three theoretical accounts of how the monitoring mechanism works to detect and correct errors.Product-based theory assumes that there is a monitor which is equipped with phonological,lexical and syntactical rules and pragmatic norms and whose sole function is to monitor errors at varying levels when language is produced.Perception-based theory posits that a central monitor within the conceptualizer functions to accomplish the monitoring job.Node structure theory accounts for monitoring from the node activation hypothesis,i.e.,detection and correction of errors is tied to the activation strength or level of node committed or uncommitted.