"How charming it is that there are words and sounds. Are not words and sounds rainbows and illusive bridges between things eternally separated?" (Friedrich Nietzsche). Speech recognition is inherently multi-sensory in the sense that listeners rely on both auditory and visual cues. However, descriptions of the systems-level processes responsible for "integrating" auditory and visual information are generally lacking. This book explores a parallel interactive framework of audiovisual speech integration. Critically, reaction time predictions along with accuracy measures are examined in a series of empirical studies and computational simulations to explore these issues.