System for transferring personalize matter from one computer to another

Abstract

This invention combines methodologies that enhance voice recognition dictation. It describes features for moving speaker voice files eliminating redundant training of speech recognition dictation applications. It defines how to create synthetic voice models reducing speaker dependency. It combines accuracy and performance into a single measure called RAP Rate. Moreover, the invention describes enhancing voice recognition applications and systems by measure/adjusting hardware and software features for optimal voice recognition dictation incorporating methodical processes based on RAP Rate. Using these approaches and tools the invention includes a method for constructing a handheld transcriber that immediately translates audio speech into text with real-time display. The invention describes a method for applying RAP Rate and synthetic voice models to applications like voice mail to text. With the ability to move and translate voice models the invention describes new services that could be provided for a fee.

What is claimed is: 
     
       1. A computer software application that functions upon a first computer that uses a speech recognition computer program, into which program a first user is enrolled and which program has produced the first user's user voice model files and the first user's enrollment entries, thereby allowing the first user access to the program and increasing the accuracy of the said program, the said application comprising:
 a. a recording means adapted to record the first user's voice model files and enrollment entries, stored on the memory of the first computer, and store the first user's voice model files and enrollment entries in recoverable form as the first user's stored enrollment entries, 
 b. a transfer means adapted to move the first user's user voice model files and the first user's stored enrollment entries to a computer file storage device, and 
 c. an enrollment means adapted to enroll the first user on another computer other than the first computer, said another computer having a speech recognition computer program installed on it, using the first user's stored enrollment entries and the first user's user voice model files from the computer file storage device, to thereby allow the first user to have access to and increase the accuracy of the speech recognition computer program installed on the said another computer. 
 
     
     
       2. A software application as recited in  claim 1  that includes an identification means that can identify that speech recognition computer program installed on a computer. 
     
     
       3. A software application as recited in  claim 1  that can identify users that are enrolled in the speech recognition computer program installed on a computer. 
     
     
       4. A software application as recited in  claim 1  that can copy speech recognition training files, system registry parameters, vocabularies, and macros, and package them as a “Voice Model” separately from the speech recognition computer program. 
     
     
       5. A software application as recited in  claim 1  that can automatically or manually move a Voice Model to another system or physical location. 
     
     
       6. A software application as recited in  claim 1  that can move, install, and enroll a Voice Model including all the specific user parameters, files, and vocabularies from the said first computer to the said another computer. 
     
     
       7. A software application as recited in  claim 1  that obviates the need for training the speech recognition program on the said another computer. 
     
     
       8. A computer software application that functions upon a first computer that uses a speech recognition computer program, into which program a first user is enrolled and which program has produced a first user's user voice model files and a first user's enrollment entries, said application comprising:
 a. a recording means adapted to record the first user's voice model files and enrollment entries, stored on the first computer, and store the first user's enrollment entries in recoverable form as the first user's voice model files and enrollment entries, 
 b. a transfer means adapted to move the first user's user voice model files and the first user's stored enrollment entries to a second computer having a speech recognition computer program installed on it, and 
 c. an enrollment means adapted to enroll the first user on said second computer, using the first user's stored enrollment entries and the first user's user voice model files transferred from the first computer. 
 
     
     
       9. A software application as recited in  claim 8  that includes an identification means that can identify that speech computer recognition program installed on a computer. 
     
     
       10. A software application as recited in  claim 8  that can identify users that are enrolled in the speech recognition computer program installed on a computer. 
     
     
       11. A software application as recited in  claim 8  that can copy speech recognition training files, system registry parameters, vocabularies, and macros, and package them as a “Voice Model” separately from the speech recognition program. 
     
     
       12. A software application as recited in  claim 8  that can automatically
 or manually move a Voice Model to another system or physical location. 
 
     
     
       13. A software application as recited in  claim 8  that can move, install,
 and enroll a Voice Model including all the specific user parameters, files, and vocabularies from the said first computer to the said another computer. 
 
     
     
       14. A software application as recited in  claim 8  that obviates the need for training the speech recognition computer program on the said another computer. 
     
     
       15. A computer software application that functions upon a first computer that uses a speech recognition computer program, into which program a first user is enrolled and which program has produced a first user's user voice model files and a first user's enrollment entries, said application comprising:
 a. a recording means adapted to record the first user's voice models and enrollment entries, stored on the first computer, and store the first user's enrollment entries in recoverable form as the first user's stored voice model and enrollment entries, 
 b. a transfer means adapted to move the first user's user voice model files and the first user's stored enrollment entries to a computer file storage device, and to move the first user's user voice model files and the first user's stored enrollment entries from the computer file storage device to another computer other than the first computer, said another computer having a speech recognition computer program installed on it, and 
 c. an enrollment means adapted to enroll the first user on the said another computer, using the first user's stored enrollment entries and the first user's user voice model files from the computer file storage device. 
 
     
     
       16. A software application as recited in  claim 15  that includes an identification means that can identify that speech recognition computer program installed on a computer. 
     
     
       17. A software application as recited in  claim 15  that can identify users that are enrolled in the speech recognition computer program installed on a computer. 
     
     
       18. A software application as recited in  claim 15  that can copy speech recognition training files, system registry parameters, vocabularies, and macros, and package them as a “Voice Model” separately from the speech recognition computer program. 
     
     
       19. A software application as recited in  claim 15  that can automatically or manually move a Voice Model to another system or physical location. 
     
     
       20. A software application as recited in  claim 15  that can move, install, and enroll a Voice Model including all the specific user parameters, files, and vocabularies from the said first computer to the said another computer. 
     
     
       21. A software application as recited in  claim 15  that obviates the need for training the speech recognition computer program on the said another computer. 
     
     
       22. A method for training a second speech recognition computer, so that the second speech recognition computer is more effective at speech recognition than it was prior to the training, comprising the steps of:
 a) training a first speech recognition computer by causing the said first speech recognition computer to form first voice model files that contain the training result, and thereby to cause the first speech recognition computer to be more effective at speech recognition, 
 b) making the said first voice model files accessible to a second speech recognition computer, that is adapted to use the said first voice model files to enhance the effectiveness of the said second speech recognition computer at speech recognition, and 
 c) causing the second speech recognition computer to use the said first voice model files to enhance the effectiveness of said second speech recognition computer at speech recognition. 
 
     
     
       23. A speech recognition computer system, comprising:
 a) a first computer including a memory, said memory containing a first installation of a speech recognition program, and said memory also containing first voice model files that are adapted to be used by the said speech recognition program to increase the accuracy of the said speech recognition program when the said first computer is used by a user to convert the speech of the user into text, said speech recognition program also containing a training module adapted to convert generic voice model files to the first voice model files by monitoring the conversion of the speech of the user into text, 
 b) a second computer including a memory, said memory containing a second installation of the speech recognition program, and 
 c) a transfer device adapted to copy the first voice model files from the first computer to the second computer in such a way that the first voice model files can be utilized by the second installation of the speech recognition program to increase the accuracy of the second installation of the speech recognition program when the said second installation of the speech recognition program is used by the user. 
 
     
     
       24. A system for enrolling users in a speech recognition computer program to increase the accuracy of the program, the system comprising:
 a. a source computer comprising:
 i. memory including a source installation of a speech recognition computer program into which a user is enrolled and which has generated and stored voice model files and enrollment entries associated with the user; 
 ii. a processor adapted to:
 record the user's voice model files and enrollment entries, stored on the source computer, 
 store the user's enrollment entries in recoverable form as the user's voice model files and enrollment entries, and 
 transfer the user's voice model files and the user's enrollment entries to a second computer having a speech recognition computer program installed on it, and 
 
   b. a second computer comprising:
 i. a memory including a second installation of the speech recognition computer program; and 
 ii. a processor adapted to enroll the user in the speech recognition computer program on said second computer, using the user's voice model files and stored enrollment entries that were transferred from the source computer, 
   
       wherein the enrollment of the user on the second computer enables the user to have access to the speech recognition computer program on the second computer and increases the accuracy of the speech recognition computer program on the second computer. 
     
     
       25. A system as recited in claim 24, wherein the processor of the second computer is adapted to identify the speech recognition program that was on the source computer. 
     
     
       26. A system as recited in claim 24, wherein the processor of the second computer is adapted to identify the users that have previously been enrolled. 
     
     
       27. A system as recited in claim 24, wherein the processor of the source computer is adapted to copy speech recognition training files selected from the group consisting of system registry parameters, vocabularies, and macros, and package them as a “Voice Model” separately from the speech recognition program. 
     
     
       28. A system as recited in claim 24, wherein the processor of the second computer is adapted to install a Voice Model received from the source computer, the Voice Model, including user parameters, files, and vocabularies from the said source computer. 
     
     
       29. A computer readable non-transitory medium on a source computer, the source computer including a source installation of a speech recognition computer program into which a user is enrolled and which has generated voice model files and enrollment entries associated with the user, the computer readable non-transitory medium storing program instructions comprising instructions that cause the source computer to:
 a) record the user's voice model files and enrollment entries,   b) store the user's voice model files and enrollment entries in recoverable form as the user's Voice Model, and   c) transfer the user's stored Voice Model to a destination computer, the destination computer including a destination installation of the speech recognition computer program;   
       wherein the transfer of the user's Voice Model to the destination computer enables the destination computer to enroll the user into the speech recognition computer program on the destination computer and increases the accuracy of the speech recognition computer program on the destination computer. 
     
     
       30. A medium as recited in claim 29 wherein the computer readable non-transitory medium further comprises instructions that cause the source computer to identify the speech recognition computer program installed on the source computer. 
     
     
       31. A medium as recited in claim 29 wherein the computer readable non-transitory medium further comprises instructions that cause the source computer to identify the users that have previously been enrolled. 
     
     
       32. A medium as recited in claim 29 wherein the computer readable non-transitory medium further comprises instructions that cause the source computer to copy speech recognition training files to the destination computer. 
     
     
       33. A medium as recited in claim 29 wherein the computer readable non-transitory medium further comprises instructions that cause the destination computer to install a Voice Model received from the source computer. 
     
     
       34. A computer readable non-transitory medium on a destination computer, the destination computer including a destination installation of a speech recognition computer program, the computer readable non-transitory medium storing program instructions comprising instructions that cause the destination computer to:
 a) receive voice model files and enrollment entries associated with a user from a source computer, the voice model files and enrollment entries having been generated by a source installation of the speech recognition computer program on the source computer into which the user is enrolled; and   b) enroll the user on said destination computer, using the user's stored enrollment entries and the first user's user voice model files transferred from the source computer   
       wherein the enrollment of the user on the destination computer enables the user to have access to the speech recognition computer program on the destination computer and increases the accuracy of the speech recognition computer program on the destination computer. 
     
     
       35. A medium as recited in claim 34 wherein the computer readable non-transitory medium further comprises instructions that cause the destination computer to identify the speech recognition computer program installed on the destination computer. 
     
     
       36. A medium as recited in claim 34 wherein the computer readable non-transitory medium further comprises instructions that cause the destination computer to identify the users that have previously been enrolled on the destination computer. 
     
     
       37. A medium as recited in claim 34 wherein the computer readable non-transitory medium further comprises instructions that cause the destination computer to copy speech recognition training files from the source computer to the destination computer. 
     
     
       38. A medium as recited in claim 34 wherein the computer readable non-transitory medium further comprises instructions that cause the destination computer to install a Voice Model received from the source computer on the destination computer, the Voice Model, including user parameters, files, and vocabularies from the said source computer. 
     
     
       39. A method for transferring a voice model associated with a user of a speech recognition computer program installed on a source computer to a destination computer to increase the accuracy of a speech recognition computer program installed on the destination computer, the method comprising the steps of:
 a) receiving, at the source computer, a request from the user to transfer the user's voice model to a second computer, the voice model comprising data stored in a memory of the source computer;   b) examining the memory of the source computer to identify and select the voice model data associated with the user that should be transferred;   c) copying the selected voice model files to a transfer medium for transfer to the destination computer;   d) retrieving, at the destination computer, the selected voice model files from the transfer medium;   e) installing the retrieved voice model files on the destination computer; and   f) enrolling the user into the speech recognition computer program on the destination computer.   
     
     
       40. A method as recited in claim 39, wherein the voice model data comprises one or more data groups selected from the group consisting of speech recognition training files, system registry parameters, user vocabularies, macros, user settings, and initialization files. 
     
     
       41. A method as recited in claim 39, wherein the transfer medium is selected from the group consisting of floppy disks, CDs, DVDs, networks, USB memory disks, other data transfer devices, and other memory devices. 
     
     
       42. A method as recited in claim 39, wherein the step of examining further comprises selecting the voice model data at least in part by accessing the system registry to identify the location in the memory of the user's voice model. 
     
     
       43. A method as recited in claim 39, wherein the step of copying further comprises generating an initialization file based on the selected voice model data; and the step of installing comprises using the initialization file to determine where the voice model data should be installed on the destination computer. 
     
     
       44. A method as recited in claim 39, wherein the step of copying further comprises generating a registry file, the registry file comprising entries from a system registry on the source computer; and the step of installing comprises updating a system registry on the destination computer based on the registry file on the source computer. 
     
     
       45. A method as recited in claim 39, wherein the step of enrolling comprises accessing the initialization file/registry file included in the voice model data from the source computer to configure the speech recognition computer program on the destination computer. 
     
     
       46. A method as recited in claim 39, wherein the step of examining further comprises identifying the speech recognition program installed on the source computer. 
     
     
       47. A method as recited in claim 39, wherein the step of installing further comprises identifying the speech recognition program installed on the destination computer. 
     
     
       48. A method as recited in claim 39, wherein the method further comprises identifying the existing users enrolled in the speech recognition program on the destination computer. 
     
     
       49. A method as recited in claim 39, wherein the method further comprises receiving a user name from the user to be used in enrolling the user into the program. 
     
     
       50. A method as recited in claim 39, wherein the method further comprises determining whether the program already includes an enrolled user with the user name and if so, prompting the user to indicate whether to overwrite the existing user or enroll under a different user name. 
     
     
       51. A computer readable non-transitory medium on a source computer, the source computer including a source installation of a speech recognition computer program into which a user is enrolled and which has generated a voice model associated with the user, the computer readable non-transitory medium storing program instructions comprising instructions that cause the first computer to:
 a) receive a request from the user to transfer, the request comprising an indication of the voice model to transfer and a transfer medium to be used;   b) examine the memory to identify and select the data to transfer;   c) package the selected data into a format for use by a destination computer;   d) copy the packaged data to a transfer medium for transfer; and   e) transfer the packed data from the transfer medium to the destination computer;   wherein the transfer of the packaged data to the destination computer enables the destination computer to enroll the user into the speech recognition computer program on the destination computer and increase the accuracy of the speech recognition computer program on the destination computer.   
     
     
       52. A method as recited in claim 51, wherein the voice model data comprises one or more data groups selected from the group consisting of speech recognition training files, system registry parameters, user vocabularies, macros, user settings, and initialization files. 
     
     
       53. A method as recited in claim 51, wherein the transfer medium is selected from the group consisting of floppy disks, CDs, DVDs, networks, USB memory disks, other data transfer devices, and other memory devices. 
     
     
       54. A method as recited in claim 51, wherein the step of examining further comprises selecting the voice model data at least in part by accessing the system registry to identify the location in the memory of the user's voice model. 
     
     
       55. A method as recited in claim 51, wherein the step of copying further comprises generating an initialization file based on the selected voice model data; and the step of installing comprises using the initialization file to determine where the voice model data should be installed on the destination computer. 
     
     
       56. A method as recited in claim 51, wherein the step of copying further comprises generating a registry file, the registry file comprising entries from a system registry on the source computer; and the step of installing comprises updating a system registry on the destination computer based on the registry file on the source computer. 
     
     
       57. A method as recited in claim 51, wherein the step of enrolling comprises accessing the initialization file/registry file included in the voice model data from the source computer to configure the speech recognition computer program on the destination computer. 
     
     
       58. A method as recited in claim 51, wherein the step of examining further comprises identifying the speech recognition program installed on the source computer. 
     
     
       59. A method as recited in claim 51, wherein the step of installing further comprises identifying the speech recognition program installed on the destination computer. 
     
     
       60. A method as recited in claim 51, wherein the method further comprises identifying the existing users enrolled in the speech recognition program on the destination computer. 
     
     
       61. A method as recited in claim 51, wherein the method further comprises receiving a user name from the user to be used in enrolling the user into the program. 
     
     
       62. A method as recited in claim 51, wherein the method further comprises determining whether the program already includes an enrolled user with the user name and if so, prompting the user to indicate whether to overwrite the existing user or enroll under a different user name. 
     
     
       63. A computer readable non-transitory medium on a destination computer, the destination computer including a destination installation of a speech recognition computer program, the computer readable non-transitory medium storing program instructions, comprising instructions that cause the first computer to:
 a) receive a request from a user to load a voice model, the voice model comprising data generated by a speech recognition program installed on a source computer;   b) retrieve voice model data from a transfer medium to the destination computer, the voice model data being associated with the voice model selected by the user:   c) determine whether the user has previously been enrolled in the speech recognition program on the destination computer;   d) prompt, in response to determining that the user was previously enrolled in the speech recognition program on the destination computer, the user to indicated whether to overwrite existing voice model data on the destination computer;   e) install the voice model data on the destination computer;   f) enroll the user in the speech recognition program on the destination computer;   
       wherein the enrollment of the user on the destination computer enables the user to have access to the speech recognition computer program on the destination computer and increases the accuracy of the speech recognition computer program on the destination computer. 
     
     
       64. A method as recited in claim 63, wherein the voice model data comprises one or more data groups selected from the group consisting of speech recognition training files, system registry parameters, user vocabularies, macros, user settings, and initialization files. 
     
     
       65. A method as recited in claim 63, wherein the transfer medium is selected from the group consisting of floppy disks, CDs, DVDs, networks, USB memory disks, other data transfer devices, and other memory devices. 
     
     
       66. A method as recited in claim 63, wherein the step of examining further comprises selecting the voice model data at least in part by accessing the system registry to identify the location in the memory of the user's voice model. 
     
     
       67. A method as recited in claim 63, wherein the step of copying further comprises generating an initialization file based on the selected voice model data; and the step of installing comprises using the initialization file to determine where the voice model data should be installed on the destination computer. 
     
     
       68. A method as recited in claim 63, wherein the step of copying further comprises generating a registry file, the registry file comprising entries from a system registry on the source computer; and the step of installing comprises updating a system registry on the destination computer based on the registry file on the source computer. 
     
     
       69. A method as recited in claim 63, wherein the step of enrolling comprises accessing the initialization file/registry file included in the voice model data from the source computer to configure the speech recognition computer program on the destination computer. 
     
     
       70. A method as recited in claim 63, wherein the step of examining further comprises identifying the speech recognition program installed on the source computer. 
     
     
       71. A method as recited in claim 63, wherein the step of installing further comprises identifying the speech recognition program installed on the destination computer. 
     
     
       72. A method as recited in claim 63, wherein the method further comprises identifying the existing users enrolled in the speech recognition program on the destination computer. 
     
     
       73. A method as recited in claim 63, wherein the method further comprises receiving a user name from the user to be used in enrolling the user into the program. 
     
     
       74. A method as recited in claim 63, wherein the method further comprises determining whether the program already includes an enrolled user with the user name and if so, prompting the user to indicate whether to overwrite the existing user or enroll under a different user name.