摘要 |
A user voiceprint model construction method, apparatus, and system. The method comprises: receiving speech information entered by a user (S101); determining whether the speech information carries a preset keyword meeting a model construction requirement (S102); if the determining result is yes, obtaining, by truncating the speech information, a speech segment corresponding to the preset keyword meeting the model construction requirement (S103); and constructing a voiceprint model for the user by using the speech segment (S104). Construction of a user voiceprint model is automatically completed in any scenario in which a speech of a user can be received, thereby facilitating use by the user. |