Similar to the highly advanced speaker identification platforms used by government and law enforcement agencies, the software uses statistical pattern matching techniques, advanced voice classification methods, and inputs from multiple systems to compare speech samples from TOEFL test takers. Launched earlier this month, the speaker identification system offers the ability to create voice prints for detailed analysis to validate TOEFL test takers. The new technology will be used as part of test security investigations in 2012 and beginning in 2013 will gradually be used on a larger scale.
“The inclusion of biometric voice identification technology is yet another tool in the TOEFL test security portfolio to ensure test integrity worldwide,” explains David Hunt, Vice President and Chief Operating Officer of ETS’s Global Division. “Including a state-of-the art speaker identification component to the TOEFL’s security system further strengthens our ability to detect attempts to gain an unfair advantage, a common concern in academia today. ETS is committed to identifying and implementing those protocols deemed most effective by leaders in the security industry in safeguarding against fraudulent behavior.”
More information regarding the TOEFL program’s prevention and detection security processes is available at www.ets.org/toefl/institutions/about/security.