In this study, we tested whether modified cognitive interviewing (MCI) is a valid method for distinguishing between genuine and deceptive human eyewitness accounts. 102 healthy military personnel were the participants of this study. 54 were assigned to a manual task condition and 48 to a cognitive task condition. Of the 54 assigned to the manual task, 17 truly performed the task and were truthful when interviewed about their activities; 18 performed the task and, when interviewed denied having performed the task; 19 read the instructions regarding the manual task and when interviewed falsely claimed to have performed the task. Of the 48 participants assigned to the cognitive task, 20 performed the task and reported truthfully about their activities; 13 performed the task and denied having participated in the task; 15 read the instructions about the cognitive task and when interviewed claimed to have actually performed the task. The transcripts of interviews were rated by individuals trained in cognitive interviewing; forensic speech variables (response length, unique word count and type-token ratio (TTR)) were coded from transcripts. Human rater judgments and computer-based speech analysis performed better than chance; computer based judgments were superior to the human judgments (i.e., 80% vs. 62%, respectively). Speech content variables derived from MCI differed significantly, and in different ways, between the truthful and false claimant participants and also between the truthful and denial type participants. MCI derived statement analysis methods are a scientifically valid method that can be used by professionals tasked with distinguishing between true claims, false claims and denials.