| US 7,580,842 B1 | ||
| System and method of providing a spoken dialog interface to a website | ||
| Srinivas Bangalore, Morristown, N.J. (US); Junlan Feng, Basking Ridge, N.J. (US); and Mazin G. Rahim, Warren, N.J. (US) | ||
| Assigned to AT&T Intellectual Property II, LP., New York, N.Y. (US) | ||
| Filed on Oct. 30, 2007, as Appl. No. 11/928,886. | ||
| Application 11/928886 is a division of application No. 10/740186, filed on Dec. 18, 2003, granted, now 7,373,300. | ||
| Claims priority of provisional application 60/434257, filed on Dec. 18, 2002. | ||
| This patent is subject to a terminal disclaimer. | ||
| Int. Cl. G10L 15/22 (2006.01); G10L 13/08 (2006.01); G10L 15/18 (2006.01) | ||
| U.S. Cl. 704—270.1 [704/275; 704/260; 704/257] | 17 Claims |
| 1. A system for generating data for use in a spoken dialog service, the system comprising:
a module configured to convert data from a structured database to a structured text data set and a structured task knowledge
base for use by at least one of a plurality of spoken dialog service components;
a module configured to extract linguistic items from the structured database for use by at least one of the plurality of spoken
dialog service components; and
a module configured to automatically generate a spoken dialog service by training each of the plurality of spoken dialog service
components using at least one of the structured text data, the structured task knowledge base or the linguistic items.
|