Distributed voice web architecture and associated components and methods

(54) DISTRIBUTED VOICE WEB

ARCHITECTURE AND ASSOCIATED
COMPONENTS AND METHODS

(75) Inventors: James E. White, San Carlos, CA (US);

Matthew Lennig, Palo Alto, CA (US)

(73) Assignee: Nuance Communications, Menlo Park, CA (US)

( * ) Notice: Subject to any disclaimer, the term of this patent is extended or adjusted under 35 U.S.C. 154(b) by 0 days.

(21) Appl. No.: 09/561,680

(22) Filed: May 1, 2000

(51) Int. CI.7 G10L 21/00; G10L 15/00

(52) U.S. CI 704/270.1; 704/270; 704/275

(58) Field of Search 704/270.1, 275,

704/270

(56) References Cited

U.S. PATENT DOCUMENTS

5,915,001 A * 6/1999 Uppalura 704/88.22

5,953,700 A * 9/1999 Kanevsky et al 704/270.1

5,956,683 A * 9/1999 Jacobs et al 704/270.1

5,960,399 A * 9/1999 Barclay et al 704/270.1

6,363,348 Bl * 3/2002 Besling et al 704/270.1

6,366,886 Bl * 4/2002 Dragosh et al 704/270.1

6,434,526 Bl * 8/2002 Cilurzo et al 704/270.1

6,456,974 Bl * 9/2002 Baker et al 704/270.1

6,556,563 Bl * 4/2003 Yarlagadda 370/352

6,560,576 Bl * 5/2003 Cohen et al 704/270

OTHER PUBLICATIONS

"Nuance Speech Recognition System Developer's Manual, Version 6.2", Nuance Communications, Menlo Park, California, 1999, pp 3-14.

"Discontinuous Transmission," Sep. 6, 2002, pp. 1-3, Whatis.com Target Search, http://whatis.techtarget.com/ definition/0„sid9_gci761635,00.html.

A speech-enabled distributed processing system forming a Voice Web includes a gateway, one or more voice content sites coupled to the gateway over a wide area network, and a browser coupled to the gateway over a network, which may or may not be the wide area network. The gateway receives telephone calls from one or more users over telephony connections and performs endpointing of speech of each user. The browser provides the gateway with information enabling the gateway to selectively direct the endpointed speech to a voice content site via the wide area network. The gateway outputs the endpointed speech in the form of application protocol requests onto the wide area network to the appropriate site, as specified by the browser, or to the browser. The gateway receives prompts in the form of application protocol responses from the browser or a voice content site and plays the prompts to the appropriate user over the telephony connection. While accessing a selected voice content site, the gateway reroutes the endpointed speech to the browser if the endpointing result represents a hotword candidate.

54 Claims, 21 Drawing Sheets