US 7,533,023 B2
	Intermediary speech processor in network environments transforming customized speech parameters
Peter Veprek, Santa Barbara, Calif. (US); Ted H. Applebaum, Santa Barbara, Calif. (US); Steven Pearson, Santa Barbara, Calif. (US); and Roland Kuhn, Santa Barbara, Calif. (US)
Assigned to Panasonic Corporation, Osaka (Japan)
Filed on Feb. 12, 2003, as Appl. No. 10/365,235.
Prior Publication US 2004/0158457 A1, Aug. 12, 2004
Int. Cl. G10L 21/00 (2006.01); G10L 15/00 (2006.01); G10L 11/00 (2006.01)

U.S. Cl. 704—270.1  [704/270; 704/275; 704/200; 704/231]

25 Claims

1. A speech processing system customizing speech parameters across a networked environment, comprising: a speech processing application residing on a first computing device, the speech processing application capturing and processing speech of a given user and further capturing customized speech parameters for the given user and communicate the customized speech parameters across a network, wherein the customized speech parameters are further defined as acoustic models unique to the given user; an intermediary speech processor residing on a second computing device in the networked environment, the second computing device being interconnected by the network to the first computing device; said intermediary speech processor receiving the customized speech parameters and transforming the customized speech parameters for use on a third computing device based on hardware characteristics of the third computing device; and a speech processing application residing on the third computing device, the speech processing application residing on the third computing device capturing speech and processing speech, the intermediary speech processor transmitting the transformed customized speech parameters to the speech processing application residing on the third computing device, wherein the speech processing application residing on the third computing device uses the transformed customized speech parameters to process speech.