System and method of providing generated speech via a network

• US 8,209,184 B1
• Filed: 10/12/2006
• Issued: 06/26/2012
• Est. Priority Date: 04/14/1997
• Status: Expired due to Fees

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Sharp, Robert Douglas, Dragosh, Pamela Leigh, Roe, David Bjorn
• Primary Examiner(s): Sked, Matthew
• Application Number:
  US11/548,882
• Time in Patent Office: 2,084 Days
• Field of Search: None
• US Class Current: 704/270.1
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• CPC Class Codes: H04M 7/006 Networks other than PSTN/ISDN providing telephone service, e.g. Voice over Internet Protocol (VoIP) , including next generation networks with a packet-switched transport layer H04L65/00 takes precedence; aspects not specific to the type of network H04M3/00; special services in those networks H04M3/42

Abstract

A system and method of operating an automatic speech recognition application over an Internet Protocol network is disclosed. The ASR application communicates over a packet network such as an Internet Protocol network or a wireless network. A grammar for recognizing received speech from a user over the IP network is selected from a plurality of grammars according to a user-selected application. A server receives information representing speech over the IP network, performs speech recognition using the selected grammar, and returns information based upon the recognized speech. Sub-grammars may be included within the grammar to recognize speech from sub-portions of a dialog with the user.

Claims

1. A method of synthesizing speech from a server remotely accessible over a network, the method comprising, at the server:

receiving over a network an identification of a spoken dialog application from a plurality of spoken dialog applications, the identified spoken dialog application having an associated grammar;

recognizing received user speech from a user using the associated grammar; and

transmitting synthesized speech to the user from the server in response to the recognized user speech information over the network.

2. The method of claim 1, further comprising:

identifying a sub-portion of a dialog with a user;

selecting a sub-grammar according to the identified sub-portion of the dialog; and

recognizing speech from the user for the identified sub-portion of the dialog using the selected sub-grammar.

3. The method of claim 2, wherein each sub-grammar is associated with a task.

4. The method of claim 1, wherein the associated grammar is identified by a universal resource locator (URL) compatible address associated with the spoken dialog application.

5. The method of claim 1, wherein the network is an internet protocol network.

6. A system for synthesizing speech over a network, the system comprising:

a module configured to receive an identification over a network of a spoken dialog application from a plurality of spoken dialog applications, the identified spoken dialog application having an associated grammar;

a module configured to recognize received user speech from a user using the associated grammar; and

a module configured to transmit synthesized speech from the server to the user in response to the recognized user speech input information over the network.

7. The system of claim 6, further comprising:

a module configured to identify a sub-portion of a dialog with a user;

a module configured to select a sub-grammar according to the identified sub-portion of the dialog; and

a module configured to recognize speech from the user for the identified sub-portion of the dialog using the selected sub-grammar.

8. The system of claim 7, wherein each sub-grammar is associated with a task.

9. The system of claim 6, wherein the associated sub-grammar is identified by a universal resource locator (URL) compatible address associated with the spoken dialog application.

10. A computer readable medium storing instructions for controlling a computing device for providing speech over a network, the instructions comprising:

receiving an identification over a network of a spoken dialog application from a plurality of spoken dialog applications, the identified spoken dialog application having an associated grammar;

recognizing received user speech from a user using the associated grammar; and

transmitting synthesized speech from the server to the user in response to the recognized user speech information over the network.

11. The computer readable medium of claim 10, wherein the network is an internet protocol network.

12. The computer readable medium of claim 10, wherein the instructions further comprise:

identifying a sub-portion of a dialog with a user;

selecting a subgrammar according to an identified sub-portion of the dialog; and

recognizing speech from the user for the identified sub-portion of the dialog using the selected sub-grammar.

13. The computer readable medium of claim 12, wherein each sub-grammar is associated with a task.

14. The computer readable medium of claim 10, wherein the an associated grammar is identified by a universal resource locator (URL) compatible address associated with the spoken dialog application.

15. A method of synthesizing speech from a server remotely accessible over a network, the method comprising, at the server:

receiving speech information from a user over a network;

recognizing the speech information using a grammar selected from a plurality of grammars; and

transmitting synthesized speech from the server to the user in response to the recognized user speech information over the network.

16. The method of claim 15, wherein the network is an internet protocol network.

17. The method of claim 15, wherein the grammar is selected based on a received identification of a spoken dialog application having the selected grammar.