Speaker Identification using Three Signal Voice Domains during Human-Robot Interaction : [Late Breaking Reports]

This LBR describes a novel method for user recognition in HRI, based on analyzing the peculiarities of users voices, and specially focused at being used in a robotic system. The method is inspired by acoustic fingerprinting techniques, and is made of two phases: a) enrollment in the system: the features of the user's voice are stored in files called voiceprints, b)searching phase: the features extracted in real time are compared with the voiceprints using a pattern matching method to obtain the most likely user (match). The audio samples are described thanks to features in three different signal domains: time, frequency, and time-frequency. Using the combination of these three domains has enabled significant increases in the accuracy of user identification compared to existing techniques. Several tests using an independent user voice database show that only half a second of user voice is enough to identify the speaker. The recognition is text-independent: users do not need to say a specific sentence (key-pass) to get identified for the robot.