SeVoAuth voice-online original

This is a voiceprint dataset with speaker's normal voice and special voice.

We recruited user test participants by snowballing. We directly invited 34 participants, all of them are family members, friends and classmates of the authors, ranging in age from 16 to 55, with similar technical backgrounds. Next, the involved participants further invited their relatives and friends to join, then 21 additional participants joined our user study. Finally, 56 people participated in our user study.

Participant  register and upload his/her voiceprint information into the system according to prompts, and then repeated voiceprint authentication for 10 times, updated his/her registration information, and repeated authentication for another 10 times. Before the authentication test, we randomly selected a position from ``forward'', ``side'', and ``top'' to request the participant to locate accordingly in the above 20 tests. Before each authentication test, we randomly selected a distance from ``5cm'', ``15cm'', and ``30cm'' to request the participants to locate accordingly.

For privacy concern, we removed their identity information and names and protected sensitive information with encryption and access control.