| US 7,533,020 B2 | ||
| Method and apparatus for performing relational speech recognition | ||
| James F. Arnold, Helena, Mont. (US); Michael W. Frandsen, Helena, Mont. (US); Anand Venkataraman, Palo Alto, Calif. (US); Douglas A. Bercow, Menlo Park, Calif. (US); Gregory K. Myers, San Francisco, Calif. (US); David J. Israel, Palo Alto, Calif. (US); Venkata Ramana Rao Gadde, Santa Clara, Calif. (US); Horacio Franco, Menlo Park, Calif. (US); and Harry Bratt, Mountain View, Calif. (US) | ||
| Assigned to Nuance Communications, Inc., Burlington, Mass. (US) | ||
| Filed on Feb. 23, 2005, as Appl. No. 11/63,357. | ||
| Application 11/063357 is a continuation in part of application No. 09/967228, filed on Sep. 28, 2001, granted, now 6,996,519. | ||
| Prior Publication US 2005/0234723 A1, Oct. 20, 2005 | ||
| This patent is subject to a terminal disclaimer. | ||
| Int. Cl. G10L 15/18 (2006.01) | ||
| U.S. Cl. 704—257 | 23 Claims |
| 1. A method for performing speech recognition, the method comprising:
acquiring a speech signal from a user;
performing a first recognition pass by applying a first language model to said speech signal, said first language model being
constrained in accordance with a structured data source; and
generating a subsequent language model based at least in part on results from said first recognition pass.
|