| US 7,571,098 B1 | ||
| System and method of spoken language understanding using word confusion networks | ||
| Allen Louis Gorin, Berkeley Heights, N.J. (US); Dilek Z. Hakkani-Tur, Parsippany, N.J. (US); Giuseppe Riccardi, Hoboken, N.J. (US); Gokhan Tur, Parsippany, N.J. (US); and Jeremy Huntley Wright, Berkeley Heights, N.J. (US) | ||
| Assigned to AT&T Intellectual Property II, L.P., New York, N.Y. (US) | ||
| Filed on May 29, 2003, as Appl. No. 10/448,149. | ||
| Int. Cl. G10L 15/18 (2006.01); G10L 15/00 (2006.01); G10L 15/06 (2006.01); G10L 15/28 (2006.01); G06F 17/27 (2006.01) | ||
| U.S. Cl. 704—257 [704/9; 704/236; 704/243; 704/255] | 18 Claims |
| 1. A speech processing method, comprising:
at an automatic speech recognition (ASR) engine:
converting a word lattice that describes multiple hypotheses of a received input utterance into a modified word lattice wherein
transitions without any input in the word lattice are represented as epsilon transitions in the modified word lattice; and
at a spoken language understanding (SLU) engine:
receiving the modified word lattice from the ASR engine; and
performing an SLU determination via the SLU engine.
|