NEW YORK- SpeechPro, a leading global biometric software provider, recently participated in the 2014 Speaker Recognition i-vector Machine Learning Challenge, held by the National Institute of Standards and Technology (NIST). The largest independent tester of biometric technology in the world, NIST released the results of the challenge in April, which tested the performance of algorithms typically utilized for voice biometrics.
The NIST challenge focused on the development of new methods in using i-vectors for speaker detection in the context of conversational telephone speech. Results were analyzed by comparing more than 12 million pairs of voice tracks to validate the identity of the speakers.
The algorithms embedded in SpeechPro’s VoiceKey technology, which were created by the Speech Technology Center (STC), SpeechPro’s parent company, were tested along with more than 100 submissions from leading companies, universities and laboratories around the globe, including Raytheon, IBM and 3M.
“There’s been an increased interest in the use of voice biometrics and speaker recognition for law enforcement agencies as well as for commercial applications in banking or call-center industries in recent years,” said SpeechPro President Alexey Khitrov. “Discovering the true identity of a voice offers an unprecedented opportunity to protect access to information as well as secure it.”
“STC has engaged voice biometrics for over 15 years,” Khitrov added. “The company invests significant resources in one of the largest R&D team in the industry, and the test results once again confirm the leading position of the technology utilized by SpeechPro products.”