Method and apparatus for enrolling a user for voice recognition

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