Abstract: A method and apparatus enrolls a user for voice recognition by prompting the user to speak a social security number or other number. A voiceprint is extracted from the social security number. Additional sequences of numbers are generated so that the total number of times each decimal digit appears in the social security number or the additional sequences meets or exceeds a threshold value. The user is then prompted to speak the additional sequences and the voiceprint extracted from the social security number is refined to include the additional information received from the responses to the prompts for the sequences. A standard sequence may also be prompted and a voiceprint of the standard sequence compared with the voiceprints of other users speaking the same standard sequence to identify the level of differentiation between the user's voice and other user's voices.