Search

In this paper we discuss data collection and preliminary experiments for a new speaker verification corpus collected on a small handheld device in multiple environments using multiple microphones. This corpus, which has been made publically available by MIT, is intended for explorations of the problem of robust speaker verification on handheld devices in noisy environments with limited training data. To provide a set of preliminary results, we examine text-dependent speaker verification under a variety of cross-conditional environment and microphone training constraints. Our preliminary results indicate that the presence of noise in the training data improves the robustness of our speaker verification models even when tested in mismatched environments.