摘要 |
<P>PROBLEM TO BE SOLVED: To provide a lip sync server system in which phoneme segmentation is performed from a speech data and a words data, and a result of the phoneme segmentation is provided for a number of users. <P>SOLUTION: The lip sync server system 60 comprises: a user management server 80 for managing user's information and request implementation by transmitting and receiving the data with a client terminal; one or more speech recognition servers 84, that is, a speech recognition device for performing the phoneme segmentation; a lip sync service server 82 for performing the phoneme segmentation by using the speech recognition server 84, and returning its result to the user management server 80; and a firewall 76 which is provided between the user management server 80 and the lip sync service server 82. <P>COPYRIGHT: (C)2009,JPO&INPIT |