System and method for providing remote automatic speech recognition services via a packet network

• US 6,078,886 A
• Filed: 04/14/1997
• Issued: 06/20/2000
• Est. Priority Date: 04/14/1997
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: Roe, David Bjorn, Sharp, Robert Douglas, Dragosh, Pamela Leigh
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): Chawan, Vijay B.
• Application Number:
  US08/833,210
• Time in Patent Office: 1,163 Days
• Field of Search: 704/270, 704/243, 704/251, 704/231, 704/255, 707/10, 395/200.32, 395/200.58, 395/200.59, 395/200.33
• US Class Current: 704/270
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• 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
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing
• CPC Class Codes: Y10S 707/99948 Application of database or data structure, e.g. distributed, multimedia, or image

Abstract

A system and method of operating an automatic speech recognition service using a client-server architecture is used to make ASR services accessible at a client location remote from the location of the main ASR engine. The present invention utilizes client-server communications over a packet network, such as the Internet, where the ASR server receives a grammar from the client, receives information representing speech from the client, performs speech recognition, and returns information based upon the recognized speech to the client.

Claims

1. A method of operating an automatic speech recognition service accessible by a client over a packet network, comprising the steps of:

a. receiving from the client over the packet network information corresponding to a grammar used for speech recognition, wherein said grammar corresponds to words associated with information to be inserted in a form;

b. receiving from the client over the packet network information representing speech;

c. recognizing the received speech information by applying an automatic speech recognition algorithm in accordance with the grammar; and

d. sending information based upon the recognized speech over the packet network to the client to used be in the form.

2. The method according to claim 1, further comprising the step of if the information corresponding to a grammar is an address corresponding to the location of a grammar, obtaining access to a grammar located at the corresponding grammar address.

3. The method according to claim 2, wherein the address corresponding to the location of a grammar is a uniform resource locator-compatible address.

4. The method according to claim 1, wherein the information representing speech arrives from the client in a streaming manner.

5. The method according to claim 1, wherein the information representing speech received from the client comprises digitized speech.

6. The method according to claim 1, wherein the information representing speech received from the client comprises compressed digitized speech.

7. The method according to claim 1, wherein the information representing speech received from the client comprises features extracted by the client from digitized speech.

8. The method according to claim 1, wherein the step of recognizing the received speech information is repeated as new speech information is received from the client.

9. The method according to claim 1, wherein the information based upon the recognized speech comprises text information.

10. The method according to claim 1, wherein the information based upon the recognized speech comprises additional speech.

11. The method according to claim 1, wherein the step of sending information based upon the recognized speech is repeated as additional speech information is recognized.

12. The method according to claim 11, further comprising the step of sending to the client revised information based upon recognized speech previously sent to the client.

13. The method according to claim 1, wherein the steps of b, c and d are repeated to create an exchange of information between client and server.

14. The method according to claim 13, wherein the information based upon the recognized speech comprises text information.

15. The method according to claim 13, wherein the information based upon the recognized speech comprises additional speech.

16. The method according to claim 1, further comprising the step of activating a grammar rule in response to a request received from the client over the packet network.

17. The method according to claim 1, further comprising the step of sending over the packet network to the client a handle corresponding to the grammar.

18. A system for operating an automatic speech recognition service accessible by a client over a packet network, comprising:

a. a programmable processor;

b. memory;

c. an audio input device; and

d. a communications interface for establishing a communications link with the client over the packet network;

wherein said processor is programmed to execute a series of steps comprising;

i. receiving from the client over the packet network information corresponding to a grammar used for speech recognition, wherein said grammar corresponds to words associated with information to be inserted in a form;

ii. receiving from the client over the packet network information representing speech;

iii. recognizing the received speech information by applying an automatic speech recognition algorithm in accordance with the grammar; and

iv. sending information based upon the recognized speech over the packet network to the client for use in the form.

19. The system according to claim 18, wherein the processor is further programmed to execute the step of if the information corresponding to a grammar is an address corresponding to the location of a grammar, obtaining access to a grammar located at the corresponding grammar address.

20. The system according to claim 19, wherein the address corresponding to the location of a grammar is a uniform resource locator-compatible address.

21. The system according to claim 18, wherein the information representing speech arrives from the client in a streaming manner.

22. The system according to claim 18, wherein the information representing speech received from the client comprises digitized speech.

23. The system according to claim 18, wherein the information representing speech received from the client comprises compressed digitized speech.

24. The system according to claim 18, wherein the information representing speech received from the client comprises features extracted by the client from digitized speech.

25. The system according to claim 18, wherein the processor is further programmed to repeat the step of recognizing the received speech information as new speech information is received from the client.

26. The system according to claim 18, wherein the information based upon the recognized speech comprises text information.

27. The system according to claim 18, wherein the information based upon the recognized speech comprises additional speech.

28. The system according to claim 18, wherein the processor is further programmed to repeat the step of sending information based upon the recognized speech as additional speech information is recognized.

29. The system according to claim 28, wherein the processor is further programmed to execute the step of sending to the client revised information based upon recognized speech previously sent to the client.

30. The system according to claim 18, wherein the processor is further programmed to repeat the steps of b, c and d to create an exchange of information between client and server.

31. The system according to claim 30, wherein the information based upon the recognized speech comprises text information.

32. The system according to claim 30, wherein the information based upon the recognized speech comprises additional speech.

33. The system according to claim 18, wherein the processor is further programmed to execute the step of activating a grammar rule in response to a request received from the client over the packet network.

34. The system according to claim 18, wherein the processor is further programmed to execute the step of sending over the packet network to the client a handle corresponding to the grammar.

35. An article of manufacture, comprising a computer-readable medium having stored thereon instructions for operating an automatic speech recognition service accessible by a client over a packet network, said instructions which, when performed by a processor, cause the processor to execute a series of steps comprising:

a. receiving from the client over the packet network information corresponding to a grammar used for speech recognition, wherein said grammar corresponds to words associated with information to be inserted in a form;

b. receiving from the client over the packet network information representing speech;

c. recognizing the received speech information by applying an automatic speech recognition algorithm in accordance with the grammar; and

d. sending information based upon the recognized speech over the packet network to the client to be used in the form.

36. The article of manufacture according to claim 35, wherein the instructions, when performed by a processor, further cause the processor to execute the step of if the information corresponding to a grammar is an address corresponding to the location of a grammar, obtaining access to a grammar located at the corresponding grammar address.

37. The article of manufacture according to claim 36, wherein the address corresponding to the location of a grammar is a uniform resource locator-compatible address.

38. The article of manufacture according to claim 35, wherein the information representing speech arrives from the client in a streaming manner.

39. The article of manufacture according to claim 35, wherein the information representing speech received from the client comprises digitized speech.

40. The article of manufacture according to claim 35, wherein the information representing speech received from the client comprises compressed digitized speech.

41. The article of manufacture according to claim 35, wherein the information representing speech received from the client comprises features extracted by the client from digitized speech.

42. The article of manufacture according to claim 35, wherein the instructions, when performed by a processor, further cause the processor to repeat the step of recognizing the received speech information as new speech information is received from the client.

43. The article of manufacture according to claim 35, wherein the information based upon the recognized speech comprises text information.

44. The article of manufacture according to claim 35, wherein the information based upon the recognized speech comprises additional speech.

45. The article of manufacture according to claim 35, wherein the instructions, when performed by a processor, further cause the processor to repeat the step of sending information based upon the recognized speech as additional speech information is recognized.

46. The article of manufacture according to claim 45, wherein the instructions, when performed by a processor, further cause the processor to execute the step of sending to the client revised information based upon recognized speech previously sent to the client.

47. The article of manufacture according to claim 35, wherein the instructions, when performed by a processor, further cause the processor to repeat the steps of b, c and d to create an exchange of information between client and server.

48. The article of manufacture according to claim 47, wherein the information based upon the recognized speech comprises text information.

49. The article of manufacture according to claim 47, wherein the information based upon the recognized speech comprises additional speech.

50. The article of manufacture according to claim 35, wherein the instructions, when performed by a processor, further cause the processor to execute the step of activating a grammar rule in response to a request received from the client over the packet network.

51. The article of manufacture according to claim 35, wherein the instructions, when performed by a processor, further cause the processor to execute the step of sending over the packet network to the client a handle corresponding to the grammar.

52. A method of operating an automatic form-filling service remotely accessible by a client over a packet network, comprising the steps of:

a. receiving from the client over the packet network information corresponding to a grammar used for speech recognition, wherein said grammar corresponds to words associated with text information to be inserted in the form;

b. receiving from the client over the packet network information representing speech;

c. recognizing the received speech information by applying an automatic speech recognition algorithm in accordance with the grammar; and

d. sending text corresponding to the recognized speech over the packet network to the client for insertion in the form.

53. The method according to claim 52, further comprising the step of if the information corresponding to a grammar is an address corresponding to the location of a grammar, obtaining access to a grammar located at the corresponding grammar address.

54. The method according to claim 53, wherein the address corresponding to the location of a grammar is a uniform resource locator-compatible address.

55. The method according to claim 52, wherein the information representing speech received from the client comprises digitized speech.

56. The method according to claim 52, wherein the information representing speech received from the client comprises compressed digitized speech.

57. The method according to claim 52, wherein the information representing speech received from the client comprises features extracted by the client from digitized speech.

58. The method according to claim 52, further comprising the step of activating a grammar rule in response to a request received from the client over the packet network.

59. The method according to claim 52, further comprising the step of sending over the packet network to the client a handle corresponding to the grammar.