System and method for online transcription services

• US 20040064317A1
• Filed: 09/26/2002
• Published: 04/01/2004
• Est. Priority Date: 09/26/2002
• Status: Active Grant

• Current Assignee: Speechink, Inc.
• Original Assignee: Core Mobility (Smith Micro Software Incorporated)
• Inventors: Othmer, Konstantin, Ruf, Michael P.
• Granted Patent: US 7,016,844 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: H04L 67/306 User profiles

Abstract

A system and method for providing a transcription service over a network. The transcription service includes a transcription server, a database, and several communication gateways. A transcription request is received by the system from anyone and includes an audio file, transcription instructions are derived by the system from a requestor profile, from preferences submitted with the audio file, or both. The request is then processed by the transcription server, the audio file is transmitted to at least one transcriber for transcription, transcribers receive the audio file, transcribe the file, and send the transcription back to the transcription server. The transcription server processes the file and sends the transcription to the entity that requested the transcription. Transcription accuracy is validated statistically by the system, thereby enabling reliable transcription from unknown transcription nodes. Profiles may be configured for both transcribers and transcription requestors. A rating and other performance metrics may be generated, monitored and maintained by the transcription system for a transcriber.

Claims

1. A method for providing a transcription service over a network comprising:

receiving audio data from a requester, at least a portion of the audio data to be transcribed by a transcriber;

accessing a requestor profile associated with the requester;

selecting a transcriber to transcribe at least a portion of the audio data, the transcriber selected based on a transcriber profile associated with the transcriber and the requestor profile;

transmitting at least a portion of the audio data to the transcriber over a network;

receiving a transcription from a transcriber, the transcription corresponding to audio data provided by a requester;

transmitting the transcription to the requestor;

receiving feedback from the requester; and

updating a transcriber rating associated with the transcriber who generated the transcription.

2. The method of claim 1 wherein receiving the audio data includes:

receiving supplementary audio file information and an audio file, the supplementary audio file information corresponding to the audio file and stored in a database, the audio file to be transcribed by the selected transcriber.

3. The method of claim 2 wherein selecting a transcriber includes:

comparing a transcriber profile to the transcription preferences to generate a score corresponding to the transcriber; and

comparing the score to a threshold value.

4. The method of claim 2 wherein selecting a transcriber includes:

comparing transcriber profiles for a plurality of candidate transcribers to the transcription preferences to generate a score for each of the plurality of candidate transcribers;

comparing each transcriber score to a threshold value; and

selecting a transcriber from the plurality of transcribers, the selected transcriber having a score that is higher than the other transcribers and higher than the threshold.

5. The method of claim 1 further including:

segmenting the audio data into segments based on a transcription preferences corresponding to the audio data, wherein each segment is sent to a different transcriber over the network.

6. The method of claim 1 further including:

voice masking the audio data based on a transcription preferences corresponding to the audio data.

7. The method of claim 1 further including:

processing the audio data to identify each of a plurality of speakers, wherein processing includes receiving a speech sample corresponding to each speaker, the plurality of speech samples identified by and received from the selected transcriber.

8. The method of claim 1 further including:

processing the audio data to identify each of a plurality of speakers, wherein processing includes processing a speech sample corresponding to each speaker, the plurality of speech samples received from a requester.

9. The method of claim 1 further comprising:

assembling received transcription segments, wherein the received transcription is one of the received transcription segments, the received transcription segments corresponding to audio data segments created from the audio data provided by the requestor, wherein transmitting the transcription includes transmitting a completely assembled transcription.

10. The method of claim 1 further comprising:

monitoring the transcriber rating corresponding to each transcriber within a transcriber pool, wherein monitoring includes;

determining whether an event occurs related to a transcriber; and

if the event occurs, performing an action.

11. A method for providing a transcription service over a network comprising:

receiving audio data from a requestor, at least a portion of the audio data to be transcribed by a transcriber;

accessing a requestor profile associated with the requestor;

selecting a transcriber to transcribe at least a portion of the audio data, the transcriber selected based on a transcriber profile associated with the transcriber and the requestor profile; and

transmitting at least a portion of the audio data to the transcriber over a network.

12. The method of claim 11 wherein the audio data includes voice mail data, the voice mail data to be transcribed by a selected transcriber.

13. The method of claim 11 wherein the audio data includes an electronic audio file attached to an electronic mail, the electronic mail attachment to be transcribed by a selected transcriber.

14. The method of claim 11 wherein receiving the audio data includes:

receiving supplementary audio file information and an audio file, the supplementary audio file information corresponding to the audio file and stored in a database, the audio file to be transcribed by the selected transcriber.

15. The method of claim 14 wherein selecting a transcriber includes:

comparing a transcriber profile to the transcription preferences to generate a score corresponding to the transcriber; and

comparing the score to a threshold value.

16. The method of claim 14 wherein selecting a transcriber includes:

comparing transcriber profiles for a plurality of candidate transcribers to the transcription preferences to generate a score for each of the plurality of candidate transcribers;

comparing each transcriber score to a threshold value; and

selecting a transcriber from the plurality of transcribers, the selected transcriber having a score that is higher than the other transcribers and higher than the threshold.

17. The method of claim 11 further including:

processing the audio data based on a transcription preferences corresponding to the audio data.

18. The method of claim 17 wherein processing includes segmenting the audio data into segments, wherein each segment is sent to a different transcriber over the network

19. The method of claim 17 wherein processing includes voice masking the audio data.

20. The method of claim 11 further including:

processing the audio data to identify each of a plurality of speakers.

21. The method of claim 20 wherein processing the audio data to identify each speaker includes receiving a speech sample corresponding to each speaker, the plurality of speech samples identified by and received from the selected transcriber.

22. The method of claim 20 wherein processing the audio data to identify each speaker includes processing a speech sample corresponding to each speaker, the plurality of speech samples received from a requester.

23. The method of claim 20 wherein processing the audio data to identify each speaker includes receiving speaker identities from an integrated conferencing system.

24. The method of claim 11 wherein the audio data includes conference calls.

25. The method of claim 11 wherein the audio data includes an audio track from video.

26. A method for providing a transcription service over a network comprising:

receiving a transcription from a transcriber, the transcription corresponding to audio data provided by a requestor;

transmitting the transcription to the requestor;

receiving feedback from the requestor; and

updating a transcriber rating associated with the transcriber who generated the transcription.

27. The method of claim 26 wherein receiving the transcription includes:

receiving call out information from the transcriber, the call out information associated with the transcription received from the at least one transcriber.

28. The method of claim 26 wherein receiving a transcription includes:

determining whether the transcription has been received within a set period of time; and

transmitting the audio file to an alternate transcriber if the transcription was not received within the set period of time.

29. The method of claim 26 further comprising:

assembling received transcription segments, wherein the received transcription is one of the received transcription segments, the received transcription segments corresponding to audio data segments created from the audio data provided by the requester, wherein transmitting the transcription includes transmitting a completely assembled transcription.

30. The method of claim 26 wherein the transcriber rating includes an accuracy rating and a speed rating.

31. The method of claim 26 further comprising:

monitoring the transcriber rating corresponding to each transcriber within a transcriber pool, wherein monitoring includes;

determining whether an event occurs related to a transcriber; and

if the event occurs, performing an action.

32. The method of claim 31 wherein the event includes the transcriber'"'"'s rating dropping below a threshold level.

33. The method of claim 31 wherein the event includes a transcriber'"'"'s failure to perform transcription services.

34. The method of claim 31 wherein the action includes sending a test vector to the transcriber associated with the event.

35. The method of claim 31 wherein the action includes sending an audio file to be transcribed to several transcribers, the several transcribers including the transcriber associated with the event, the transcription received from each of the several transcribers compared to cross-check the transcription received from the transcriber associated with the event.

36. The method of claim 26 further comprising:

transmitting billing information through a gateway, the billing information including information from which the cost of transcription services may be derived.

37. The method of claim 26 further comprising:

analyzing the received transcription for profanity content.

38. The method of claim 26 further comprising:

formatting the received transcription to include speaker identity labels.

39. A method for providing a transcription service over a network comprising:

identifying a transcriber located at a workstation, the transcriber associated with a transcriber profile and a transcriber rating, the profile and rating stored in the database;

receiving a work request input initiated by the transcriber, the work request input indicating the transcriber is requesting transcription work;

routing an audio file to the transcriber, the audio file associated with a transcription preferences, the transcriber profile determined to have matched the transcription preferences;

receiving a transcription of the audio file from the transcriber; and

updating the transcriber rating based upon the transcription received.

40. The method as claimed in claim 39 further comprising:

receiving transcriber information from the transcriber, the transcriber information stored in the transcriber profile.

41. The method as claimed in claim 39 further comprising:

receiving tag call out information from the transcriber.

42. The method of claim 40 wherein receiving tag call out information includes:

retrievably attaching the call-out information to the transcription in a format compatible with an electronic mail application.

43. The method of claim 40 wherein receiving tag call out information includes:

retrievably attaching the call-out information to the transcription in a format compatible with an electronic calendar application.

44. The method of claim 40 wherein receiving tag call out information includes:

retrievably attaching the call-out information to the transcription in a format compatible with an electronic contact list application.

45. A method for providing a transcription service comprising:

providing access to a user to audio data, the audio data stored in a database;

receiving input from the user, the input indicating the audio data is to be transcribed; and

forwarding the audio data from the database to a data file gateway.

46. The method of claim 45 further comprising:

receiving transcription preference information, the transcription preference information forwarded with the data file to the data file gateway.

47. The method of claim 45 wherein providing access to the data file and receiving input are implemented through a voice activated interface.

48. The method of claim 45 wherein providing access to the data file and receiving input are implemented through a keypad interface on a telephone device.

49. The method of claim 45 further comprising:

receiving transcription billing information from a server.

50. A method for managing a pool of transcribers providing transcriptions over a network, comprising:

receiving feedback on a transcription provided by a transcriber, the feedback received by a transcription server, the transcription received by the transcription server from the transcriber over a network;

determining a rating for the transcriber, the rating based at least in part on the feedback received; and

determining compensation for the transcriber based on the rating for the transcriber.

51. The method of claim 50 further comprising:

determining whether an event occurs associated with a transcriber; and

if the event occurs, performing an action regarding the transcriber.

52. The method of claim 51 wherein the event includes the transcriber'"'"'s rating dropping below a threshold level.

53. The method of claim 51 wherein the event includes a transcriber'"'"'s failure to perform transcription services.

54. The method of claim 51 wherein the action includes initiating the transmission of an audio file to be transcribed to several transcribers, the several transcribers including the transcriber associated with the event, the transcription received from each of the several transcribers compared to cross-check the transcription received from the transcriber associated with the event.

55. The method of claim 51 wherein the action includes initiating the transmission of at least one test vector the transcriber, the test vector including an audio file generated by the transcription server.

56. The method of claim 51 wherein the action includes closing the transcriber'"'"'s account with the system.

57. The method of claim 51 wherein the action includes adjusting transcriber compensation in real time.

58. The method of claim 56 wherein transcriber compensation is adjusted based on the volume of transcription requests.

59. The method of claim 56 wherein transcriber compensation is adjusted based on the number of available transcribers at any given time.

60. The method of claim 56 wherein transcriber compensation is adjusted based on transcriber performance history.

61. The method of claim 59 wherein performance history includes transcriber rating, speed, accuracy and availability history.

62. A method for providing a high quality transcription service over a network comprising:

sending audio data from a server to a selected transcriber over a network;

receiving a transcription from the transcriber, the transcription associated with the audio data; and

analyzing the transcription by the server.

63. The method as claimed in claim 62 wherein sending audio data includes sending a test vector, analyzing the transcription including comparing the transcription to a perfect text transcription of the audio file to determine the accuracy of the selected transcriber.

64. The method as claimed in claim 62 wherein analyzing the transcription includes detecting profanity in the transcription.

65. The method of claim 62 further comprising updating the transcriber profile

66. The method of claim 65 wherein the transcriber profile is updated in real time

67. The method of claim 65 wherein the transcriber profile is updated automatically by the system based on the results of test vectors.

68. A method for compensating transcribers for transcriptions provided by the transcriber over a network comprising:

receiving a transcription request;

determining a base transcription cost;

determining a transcriber to perform a transcription associated with the transcription request; and

determining a total transcriber compensation amount.

69. The method of claim 68 wherein determining a base transcription cost includes:

assessing transcription demand; and

determining the supply of transcribers.

70. The method of claim 68 further comprising:

providing the transcription request and the total transcriber compensation amount to a transcriber.

71. A computer program product for execution by a server computer for providing a transcription service over a network comprising:

computer code for receiving audio data from a requester, at least a portion of the audio data to be transcribed by a transcriber;

computer code for accessing a requester profile associated with the requester;

computer code for selecting a transcriber to transcribe at least a portion of the audio data, the transcriber selected based on a transcriber profile associated with the transcriber and the requestor profile; and

computer code for transmitting at least a portion of the audio data to the transcriber over a network.

72. The computer program product of claim 71 wherein receiving the audio data includes:

computer code for receiving supplementary audio file information and an audio file, the supplementary audio file information corresponding to the audio file and stored in a database, the audio file to be transcribed by the selected transcriber.

73. The computer program product of claim 72 wherein selecting a transcriber includes:

computer code for comparing a transcriber profile to the transcription preferences to generate a score corresponding to the transcriber; and

computer code for comparing the score to a threshold value.

74. The computer program product of claim 71 further including:

computer code for processing the audio data based on a transcription preferences corresponding to the audio data, wherein processing includes segmenting the audio data into segments, wherein each segment is sent to a different transcriber over the network

75. The computer program product of claim 71 further including:

computer code for processing the audio data based on a transcription preferences corresponding to the audio data, wherein processing includes voice masking the audio data.

76. A computer program product for execution by a server computer for providing a transcription service over a network comprising:

computer code for receiving a transcription from a transcriber, the transcription corresponding to audio data provided by a requestor;

computer code for transmitting the transcription to the requestor;

computer code for receiving feedback from the requestor; and

computer code for updating a transcriber rating associated with the transcriber who generated the transcription.

77. The computer program product of claim 76 further comprising:

computer code for assembling received transcription segments, wherein the received transcription is one of the received transcription segments, the received transcription segments corresponding to audio data segments created from the audio data provided by the requestor, wherein transmitting the transcription includes transmitting a completely assembled transcription.

78. The computer program product of claim 76 further comprising:

computer code for monitoring the transcriber rating corresponding to each transcriber within a transcriber pool, wherein monitoring includes;

determining whether an event occurs related to a transcriber; and

if the event occurs, performing an action.

79. A computer program product for execution by a server computer for providing a transcription service over a network comprising:

computer code for identifying a transcriber located at a workstation, the transcriber associated with a transcriber profile and a transcriber rating, the profile and rating stored in the database;

computer code for receiving a work request input initiated by the transcriber, the work request input indicating the transcriber is requesting transcription work;

computer code for routing an audio file to the transcriber, the audio file associated with a transcription preferences, the transcriber profile determined to have matched the transcription preferences;

computer code for receiving a transcription of the audio file from the transcriber; and

computer code for updating the transcriber rating based upon the transcription received.

80. A computer program product for execution by a server computer for providing a transcription service comprising:

computer code for providing access to a user to audio data, the audio data stored in a database;

computer code for receiving input from the user, the input indicating the audio data is to be transcribed; and

computer code for forwarding the audio data from the database to a data file gateway.

81. A computer program product for execution by a server computer for managing a pool of transcribers providing transcriptions over a network, comprising:

computer code for receiving feedback on a transcription provided by a transcriber, the feedback received by a transcription server, the transcription received by the transcription server from the transcriber over a network;

computer code for determining a rating for the transcriber, the rating based at least in part on the feedback received; and

computer code for determining compensation for the transcriber based on the rating for the transcriber.

82. A computer program product for execution by a server computer for providing a high quality transcription service over a network comprising:

computer code for sending audio data from a server to a selected transcriber over a network;

computer code for receiving a transcription from the transcriber, the transcription associated with the audio data; and

computer code for analyzing the transcription by the server.

83. The computer program product as claimed in claim 82 wherein sending audio data includes sending a test vector, analyzing the transcription including comparing the transcription to a perfect text transcription of the audio file to determine the accuracy of the selected transcriber.

84. A computer program product for execution by a server computer for compensating transcribers for transcriptions provided by the transcriber over a network comprising:

computer code for receiving a transcription request;

computer code for determining a base transcription cost, wherein determining the base transcription cost includes;

assessing transcription demand; and

determining the supply of transcribers;

computer code for determining a transcriber to perform a transcription associated with the transcription request; and

computer code for determining a total transcriber compensation amount.