The brain’s ability to bind incoming auditory and visual stimuli depends critically on the temporal structure of this information. Specifically, there exists a temporal window of audiovisual integration within which stimuli are highly likely to be bound together and perceived as part of the same environmental event. Several studies have described the size and malleability of this window in adults, and we have shown in recent work that the size of the multisensory temporal binding window can be narrowed with the use of a perceptual training paradigm. However, the specific mechanisms underlying these changes were not clear, and to rule out the possibility that they could be the result of cognitive biases, a new, two-interval forced choice (2IFC) paradigm was undertaken during which participants were instructed to identify a simultaneously-presented audiovisual pair presented within one of two intervals, and in which the stimulus onset asynchrony between the visual and auditory stimuli in the other interval was variable. While the new training paradigm also resulted in a window narrowing and generalization pattern similar to that seen using the two alternative approach, the 2IFC paradigm resulted in a larger overall decline in window size that took place over a slower time course. These findings indicate that these different methods of multisensory perceptual training both result in substantial alterations in the circuits underlying the perception of audiovisual simultaneity, a hypothesis supported by preliminary imaging data showing blood-oxygen-level dependent (BOLD) changes in canonical multisensory cortical regions after perceptual training. Taken together, these results suggest a high degree of flexibility in multisensory temporal processing and have important implications for interventional strategies that may be used to ameliorate clinical conditions (e.g., autism, dyslexia) in which multisensory temporal function may be impaired.