System and method for providing and using universally accessible voice and speech data files

• US 20020080927A1
• Filed: 01/25/2002
• Published: 06/27/2002
• Est. Priority Date: 11/14/1996
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Uppaluru, Premkumar V.
• Granted Patent: US 6,885,736 B2
• Time in Patent Office: Days
• US Class Current: 379/88.01
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04M 2201/405 involving speaker-dependent recognition adaptation to speaker for speech recognition G10L15/07
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

A system and method provides universal access to voice-based documents containing information formatted using MIME and HTML standards using customized extensions for voice information access and navigation. These voice documents are linked using HTML hyper-links that are accessible to subscribers using voice commands, touch-tone inputs and other selection means. These voice documents and components in them are addressable using HTML anchors embedding HTML universal resource locators (URLs) rendering them universally accessible over the Internet. This collection of connected documents forms a voice web. The voice web includes subscriber-specific documents including speech training files for speaker dependent speech recognition, voice print files for authenticating the identity of a user and personal preference and attribute files for customizing other aspects of the system in accordance with a specific subscriber.

Claims

1. A method for delivering caller-customized services to a telephone caller, comprising:

storing caller-specific information in a computer file on a computer network in accordance with a universal resource locator (URL) address;

prompting the caller to input identifying information;

responsive to the identifying information, determining a URL for the file storing the caller-specific information;

retrieving the caller-specific information from the file stored at the URL;

processing the call in accordance with the caller-specific information.

2. The method of claim 1 wherein the stored caller-specific information is a master voice signature for the caller, and wherein processing the call in accordance with the caller specific information comprises:

prompting the caller for a voice signature;

recording the voice signature; and

comparing the voice signature to the recorded voice signature to determine whether there is a match.

3. The method of claim 1 wherein the stored caller-specific information is a speaker dependent speech recognition training file for the caller;

and wherein processing the call in accordance with the caller-specific information comprises;

prompting the caller for voice commands;

recording the voice commands; and

performing speaker dependent speech recognition on the voice commands using the training file for the caller.

4. The method of claim 1 wherein the stored caller-specific information is a preferences file including a specification of caller preferences.

5. The method of claim 1 wherein the stored caller-specific information is a caller attributes file including a specification of caller attributes.

6. A method of delivering caller-customized voice-based information to a caller, comprising:

storing caller-specific information in a computer file at a universal resource locator (URL);

determining a URL associated with the caller;

retrieving the caller-specific information using the URL;

processing at least one caller command received over the telephone to determine a service request;

retrieving information responsive to the service request and responsive to the caller-specific information; and

playing back the retrieved information to the caller over the telephone.

7. The method of claim 6 wherein playing back the retrieved information to the caller over the telephone includes performing text to speech conversion on at least a portion of the retrieved information.

8. The method of claim 6 wherein retrieving information responsive to the service request and responsive to the caller-specific information comprises:

generating a database query form responsive to the service request;

customizing the database query form using the caller-specific information; and

performing a database search using the query form.

9. The method of claim 8 wherein generating a database query form responsive to the service request includes:

storing a voice form associated with the service request at a universal resource locator (URL) address in the computer network wherein the voice form is stored in a markup language;

playing the voice form to the caller to generate at least one information prompt for the caller;

collecting information from the caller in response to each prompt; and

generating a database query form using at least a portion of the collected information.

10. The method of claim 9 wherein collecting information from the caller in response to each prompt includes collecting touch tone inputs from the caller.

11. The method of claim 9 wherein collecting information from the caller in response to each prompt includes collecting voice command inputs from the caller and performing speech recognition on the voice command inputs.

12. The method of claim 8 wherein playing back the retrieved information to the caller over the telephone includes performing text to speech conversion on at least some of the retrieved information.

13. The method of claim 8 wherein the database stores information previously stored by the caller.

14. The method of claim 8 wherein the database stores calendar and appointment information.

15. The method of claim 8 wherein the database stores address book information.

16. The method of claim 8 wherein the database stores electronic mail information.

17. The method of claim 8 wherein the database stores stock portfolio information.

18. The method of claim 8 wherein the database stores news headlines information.

20. The method of claim 19 wherein collecting information from the caller in response to each prompt comprises includes the processing of touch tone inputs supplied by the caller.

21. The method of claim 20 wherein collecting information from the caller in response to each prompt includes the processing voice inputs supplied by the caller.

22. The method of claim 19 further comprising during a second calling session:

receiving a service request from a caller;

retrieving at least a portion of the collected information; and

presenting the retrieved information to the caller.

23. The method of claim 19 wherein storing the collected information comprises storing the collected information in a first markup language document and including in the document a hyperlink to a second markup language document.

24. The method of claim 23 wherein the hyperlink is determined responsive to at least a portion of the collected information.

25. The method of claim 19 wherein storing the collected information comprises storing the collected information in a first markup language document and including in a second markup language document a hyperlink to the first markup language document.

26. The method of claim 25 wherein the hyperlink is determined responsive to at least a portion of the collected information.

28. The system of claim 27 wherein the telecommunications device is a telephone.

29. The system of claim 27 wherein the telecommunications device is a computer with a telecommunications interface.

30. The system of claim 27 further comprising a database for storing information and wherein at least one voice web page is a query form for searching the database.

31. The system of claim 27 wherein at least one voice web page is a form for collecting user information.

32. The system of claim 31 wherein the form is adapted to collect voice input from a user.

33. The system of claim 31 wherein the form is adapted to collect touch tone input from a user.

34. The system of claim 30 wherein at least one web page is a voice form for providing the user with voice prompts to collect database search information.

35. The system of claim 34 wherein the voice form is adapted to collect touch tone input from a user.

36. The system of claim 34 wherein the voice form is adapted to collect voice input from a user.

38. The method of claim 37 wherein the computer network is an Internet.

39. The method of claim 38 wherein the personal profile includes data for voice authentication and further comprising:

receiving a user authentication request;

retrieving user authentication data from the personal profile;

collecting voice data from the user;

processing the collected voice data; and

comparing the processed voice data to the authentication data to authenticate the identity of the system user.

40. The method of claim 39 wherein collecting voice data from the user includes collecting voice data from the user using a telephone.

41. The method of claim 38 wherein the personal profile includes data for speaker dependent speech recognition and further comprising:

receiving a voice command from the user;

performing speaker dependent speech recognition to identify the voice command; and

executing the recognized voice command.

42. The method of claim 41 wherein receiving a voice command from the user includes receiving a voice command from the user using a telephone.

43. The method of claim 38 further comprising performing a database query using at least a portion of the information stored in the personal profile.

44. The method of claim 38 further comprising customizing the presentation of information to the user in response to at least a portion of the information stored in the personal profile.

45. The method of claim 37 wherein the computer network is an intranet.

46. The method of claim 45 wherein the personal profile includes data for voice authentication and further comprising:

receiving a user authentication request;

retrieving user authentication data from the personal profile;

collecting voice data from the user;

processing the collected voice data; and

comparing the processed voice data to the authentication data to authenticate the identity of the system user.

47. The method of claim 46 wherein the collecting voice data from the user includes collecting voice data from the user using a telephone.

48. The method of claim 45 wherein the personal profile includes data for speaker dependent speech recognition and further comprising:

receiving a voice command from the user;

performing speaker dependent speech recognition to identify the voice command; and

executing the recognized voice command.

49. The method of claim 48 wherein receiving a voice command from the user includes receiving a voice command from the user using a telephone.

50. The method of claim 45 further comprising performing a database query using at least a portion of the information stored in the personal profile.

51. The method of claim 45 further comprising customizing the presentation of information to the user in response to at least a portion of the information stored in the personal profile.

19. A method of processing voice-based information received from a telephone caller over a computer network, comprising:

storing a voice form at a universal resource locator (URL) address in the computer network wherein the voice form is stored in a markup language with voice extensions; and

during a calling session;

playing the voice form to the caller to generate at least one information prompt for the caller;

collecting information from the caller in response to each prompt; and

storing the collected information.

27. A system for providing voice-based information over a computer network, the system comprising:

a user profile each stored at a unique URL address;

a plurality of voice web pages each having a unique universal resource locator (URL) address and each being specified in a markup language including voice extensions;

a telecommunications interface for receiving user voice commands and for playing back requested information;

a processing agent stored on a computer in the network, the processing agent adapted to customize the voice web pages in accordance with the user profile; and

a voice web browser adapted to playback customized voice web pages over the telecommunications device.

37. In a computer system coupled to a computer network, a method of providing user specific input to a computer program, comprising:

determining a universal resource locator (URL) address corresponding to a user;

retrieving, over the computer network, a personal profile associated with the user wherein the personal profile is stored at the determined URL address; and

accessing information included in the personal profile to affect the execution of a computer program.

52. A speech processing system, comprising:

a computer network;

a gateway computer coupled to the computer network adapted to receive subscriber commands;

a server computer program coupled to the network;

a user profile stored on the computer network;

voice web pages stored on the computer network wherein each voice web pages is addressable by a universal resource locator (URL) address unique within the computer network and wherein each voice web page includes voice information; and

speech processing software adapted to operate in the computer network and adapted to perform the method comprising;

receiving a user identifier;

receiving a command;

determining a URL address associated with a voice web page responsive to the command;

determining a URL address associated with the user profile responsive to the user identifier;

retrieving the user profile;

retrieving the voice web page; and

generating an output responsive to the user command and information included in the retrieved voice web page and the user profile.

53. The system of claim 52 wherein the computer network is an Internet.

54. The system of claim 53 wherein the user profile includes voice print information and wherein the command received by the speech processing software is a command to authenticate the identity of a user.

55. The system of claim 53 wherein the user profile includes speech training information and wherein the command received by the speech processing software is a digitized version of a spoken command and wherein the digitized version is processed using retrieved speech training information.

56. The system of claim 53 further comprising a database query form customized in accordance with at least a portion of the user profile.

57. The system of claim 53 wherein the speech processing software is further adapted to perform the method comprising:

searching a database to return a query result; and

presenting the query result responsive to at least a portion of the user profile.

58. The system of claim 53 further comprising a user directory having a plurality of entries, each entry corresponding to a user identifier and each entry being mapped to a URL address and wherein determining the URL address associated with a voice document responsive to the user identifier and the command includes retrieving a URL address from the user directory.

59. The system of claim 53 wherein the computer network is an Internet.

60. The system of claim 59 wherein the user profile includes voice signature information and wherein the command received by the speech processing software is a command to authenticate the identity of a user.

61. The system of claim 59 wherein the user profile includes speech training information and wherein the command received by the speech processing software is a digitized version of a spoken command and wherein the digitized version is processed using retrieved speech training information.

62. The system of claim 59 further comprising a database query form customized in accordance with at least a portion of the user profile.

63. The system of claim 59 wherein the speech processing software is further adapted to perform the method comprising:

searching a database to return a query result; and

presenting the query result responsive to at least a portion of the user profile.

64. The system of claim 59 further comprising a user directory having a plurality of entries, each entry corresponding to a user identifier and each entry being mapped to a URL address and wherein determining the URL address associated with a voice document responsive to the user identifier and the command includes retrieving a URL address from the user directory.

65. A method for authenticating the identity of a telephone caller, the method comprising:

storing a master voice signature for the caller in a computer file addressable by a universal resource locator (URL) address; and

during the call;

determining the URL for the caller'"'"'s master voice signature;

prompting the caller for a voice signature;

recording the voice signature;

retrieving caller'"'"'s master voice signature; and

comparing the recorded voice signature to the master voice signature to determine whether there is a match.

66. A system for delivering information over a telephone, comprising:

a database;

a database query form;

a first processing agent programmed to perform the method comprising;

collecting user information using a voice based telecommunications device;

including at least some of the collected information to the database query form;

searching the database by applying the database query form to the database to retrieve information; and

generating a voice web page having a universal resource locator (URL) address using the retrieved information; and

a voice web browser adapted to play voice web pages to a user.

67. The system of claim 66 wherein the database is a business white pages database including business name, address and phone number information.

68. The system of claim 67 further comprising:

a yellow page database including business advertising information; and

a second processing agent wherein the voice web page generated by the first processing agent includes a hyperlink to the second processing agent and wherein the second processing agent is programmed to perform the method comprising;

searching the yellow page database to retrieve information; and

generating a voice web page using the retrieved information.

69. The system of claim 68 wherein the hyperlink identifies an entry in the yellow page database and wherein searching the yellow page database comprises locating the yellow page database entry identified by the hyperlink.

70. The system of claim 68 further comprising:

an order page database including business order information; and

a third processing agent wherein the voice web page generated by the second processing agent includes a second hyperlink to the third processing agent and wherein the third processing agents is programed to perform the method comprising;

searching the order page database to retrieve information; and

generating a voice web page using the retrieved information.

71. The system of claim 70 wherein the second hyperlink identifies an entry in the order page database and wherein searching the order page database comprises locating the order page database entry identified by the hyperlink.

72. A method providing user profile information to a plurality of request sources, comprising:

collecting user profile information for a plurality of users;

storing the collected profile information in a profile database;

receiving a request from a request source for at least a portion of the profile information associated with a specified user;

dynamically creating a markup language document including the requested profile information wherein the markup language document is stored at a location identified by a universal resource locator (URL) address; and

providing the markup language document to the request source.

73. The method of claim 72 wherein the user profile information is stored in accordance with a specified structure.

74. The method of claim 73 wherein the specified structure corresponds to a hierarchy of services.

75. The method of claim 72 wherein the markup language document is a hypertext markup language document containing the user profile information stored in a table format.