| US 7,590,530 B2 | ||
| Method and apparatus for improved estimation of non-stationary noise for speech enhancement | ||
| David Zhao, Solna (Sweden); Willem Bastiaan Kleijn, Stocksund (Sweden); Alexander Ypma, Veldhoven (Netherlands); and Bert Devries, Eindhoven (Netherlands) | ||
| Assigned to GN Resound A/S, (Denmark) | ||
| Filed on Aug. 23, 2006, as Appl. No. 11/509,166. | ||
| Claims priority of provisional application 60/713675, filed on Sep. 03, 2005. | ||
| Prior Publication US 2007/0055508 A1, Mar. 08, 2007 | ||
| Int. Cl. G10L 21/02 (2006.01) | ||
| U.S. Cl. 704—226 [704/233; 704/200] | 19 Claims |
| 1. A method of enhancing speech, comprising:
receiving noisy speech comprising a clean speech component and a non-stationary noise component;
providing a speech model;
providing a noise model having at least one shape and a gain;
dynamically modifying the at least one shape and the gain of the noise model based at least in part on the speech model and
the received noisy speech using a processor; and
enhancing the noisy speech at least based on the modified noise model.
|