Method and apparatus for voice dictation and document production

• US 20020143533A1
• Filed: 07/11/2001
• Published: 10/03/2002
• Est. Priority Date: 03/29/2001
• Status: Active Grant

• Current Assignee: Provox Acquisition LLC
• Original Assignee: Ecentury Capital Partners LP, Mid-Atlantic Venture Fund IV, LP, Southside Rising, LLC, Tall Oaks Provox Partners, LP, Village Ventures Partners Fund A LP, VVN, LLC
• Inventors: Miko, Stephen, Lucas, Mark, Bennington, Steven A.
• Granted Patent: US 6,834,264 B2
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/174 Form filling; Merging
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records

Abstract

Multiple documents including multiple fields may be produced using a voice recognition engine to transcribe dictated notes. An embodiment of an apparatus to generate documents from a user'"'"'s dictation may include a computer interface and a computer in communication with the computer interface including a voice recognition engine, a database, and a memory. A method of entry of dictation into a plurality of documents may include receiving an indication of a selection of a plurality of documents from a list of documents, receiving an indication of a field descriptor of a first field in a document, receiving dictated speech to be entered into the first field, writing transcribed text representative of the dictated speech to the first field, and writing the transcribed text to other fields having the same descriptor in each of the other selected plurality of documents.

Claims

1. An apparatus to generate an editable text file from a user'"'"'s dictation using voice recognition technology, comprising:

a computer interface to allow a user to;

select a dictation subject,

select a document from a plurality of documents, the document including a plurality of fields to store editable text, the plurality of fields including a first subset of fields and a second subset of fields, and

dictate speech into an audio input; and

a computer in communication with the computer interface, comprising;

a voice recognition engine to accept input from the audio input and convert dictated speech to editable text, wherein the editable text is inserted into the first subset of fields, a database to store data related to the dictation subject, wherein data from the database is inserted into the second subset of fields, and

a memory to store the plurality of fields as an editable text file.

2. The apparatus of claim 1, wherein the computer interface is a handheld computer.

3. The apparatus of claim 1, further comprising a communications interface to couple the computer interface and the computer, wherein the communication interface is one of a modem, a LAN (local area network), an Internet connection, a wireless connection, a removable data storage device, and a hard wired link.

4. The apparatus of claim 3, wherein the wireless connection is one of a radio wave connection, a light wave connection, and an infrared connection.

5. The apparatus of claim 1, wherein the voice recognition engine converts dictated speech to editable text with letter granularity.

6. The apparatus of claim 1, further comprising a second database to store processed editable text files.

7. A method of entry of dictation data of a user into a plurality of documents at a computing device, comprising:

receiving an indication of a selection of a plurality of documents from a list of documents, each of the plurality of documents comprising at least one field for data storage, the at least one field having a field descriptor to identify the at least one field;

receiving an indication of the field descriptor of a first field from a first document in the plurality of documents;

receiving dictated speech to be entered into the first field;

writing transcribed text representative of the dictated speech to the first field; and

writing the transcribed text representative of the dictated speech to other fields having a same descriptor as the first descriptor in each of the selected plurality of documents.

8. The method of claim 7, further comprising writing data from a database of fields having a plurality of descriptors to other fields having identical descriptors in each of the selected plurality of documents.

9. The method of claim 7, further comprising automatically transmitting at least one of the plurality of documents to a recipient.

10. The method of claim 7, further comprising simultaneously displaying at least two of the plurality of documents on a display device operatively coupled to the computing device during the step of receiving dictated speech.

11. The method of claim 7, further comprising:

receiving an indication of a selection of a document from among the selected plurality of documents;

receiving an indication of the first field, the indication indicative of a request to edit the transcribed text representative of the dictated speech stored in the first field;

receiving new dictated speech to be entered into the first field; and

writing transcribed text representative of the new dictated speech to the first field.

13. The method of claim 12, wherein the voice recognition engine generates strings of text such that each transcribed letter of spoken dictation in a string of text is referenced to a location, and thus a sound, in an associated audio file.

14. The method of claim 12, wherein the prompting comprises one of an audible cue, a visual cue, and a combined audible and visual cue.

15. The method of claim 12, wherein combining comprises one of insertion of the third string of text within the second string of text, appending the third string of text to the second string of text, and appending the second string of text to the third string of text.

17. The method of claim 16, wherein the second document is a read-only document.

18. The method of claim 16, wherein acquiring data related to a plurality of dictation subjects includes a real-time download of the data related to the plurality of dictation subjects.

19. The method of claim 16, wherein acquiring data related to a plurality of dictation subjects includes a pull of data on demand of data related to one of the plurality of dictation subjects.

20. The method of claim 18, wherein the real time download comprises use of a communication interface, wherein the communication interface is one of a modem, a LAN (local area network) an Internet connection, a wireless connection, a removable data storage device, and a hard wired link.

21. The method of claim 20, wherein the wireless connection is one of a radio wave connection, a light wave connection, and an infrared connection.

22. The method of claim 19, wherein the real time download comprises use of a communication interface, wherein the communication interface is one of a modem, a LAN (local area network) interface, an Internet connection, a wireless connection, a removable data storage device, and a hard wired link.

23. The method of claim 22, wherein the wireless connection is one of a radio wave connection, a light wave connection, and an infrared connection.

24. The method of claim 16, wherein the voice recognition engine generates the first text portion such that each transcribed letter of dictated voice stored in the editable text file is referenced to a location, and thus a sound, in the audio file.

25. The method of claim 16, further comprising deletion of the audio file and the editable text file after the step of storing the edited first text portion as a read-only document.

26. The method of claim 16, wherein receiving edits to the first text portion include newly spoken voice dictation from another user, different from the user.

28. The machine readable medium of claim 27, wherein the second document is a read-only document.

29. The machine readable medium of claim 27, wherein the instruction to acquire data related to a plurality of dictation subjects includes a real-time download of the data related to the plurality of dictation subjects.

30. The machine readable medium of claim 27, wherein the instruction to acquire data related to a plurality of dictation subjects includes a pull of data on demand of data related to one of the plurality of dictation subjects.

31. The machine readable medium of claim 29, wherein the real time download comprises use of a communication interface, wherein the communication interface is one of a modem, a LAN (local area network) an Internet connection, a wireless connection, a removable data storage device, and a hard wired link.

32. The machine readable medium of claim 31, wherein the wireless connection is one of a radio wave connection, a light wave connection, and an infrared connection.

33. The machine readable medium of claim 30, wherein the real time download comprises use of a communication interface, wherein the communication interface is one of a modem, a LAN (local area network) interface, an Internet connection, a wireless connection, a removable data storage device, and a hard wired link.

34. The machine readable medium of claim 33, wherein the wireless connection is one of a radio wave connection, a light wave connection, and an infrared connection.

35. The machine readable medium of claim 27, wherein the voice recognition engine generates the first text portion such that each transcribed letter of dictated voice stored in the editable text file is referenced to a location, and thus a sound, in the audio file.

36. The machine readable medium of claim 27, further comprising instructions to delete the audio file and the editable text file after the instructions to store the edited first text portion as a read-only document.

37. The machine readable medium of claim 27, wherein edits to the first text portion include newly spoken voice dictation from another user, different from the user.

12. A method of generating text including variable data in an electronic spoken dictation-to-text system, comprising:

converting spoken dictation to a first string of text in a voice recognition engine;

decoding a macro name in the first string of text, the macro name having associated therewith a second string of text and a variable value;

prompting a user for the variable value;

converting additional spoken dictation to a third string of text in the voice recognition engine, the third string of text comprising a representation of the variable value; and

combining the second string of text with the third string of text.

16. A method of generating a document from spoken dictation of a user, comprising:

acquiring data related to a plurality of dictation subjects;

populating a database with the acquired data related to the plurality of dictation subjects;

receiving identification of a first document from a plurality of documents, the first document having a plurality of fields for data entry;

receiving identification of a first field in the plurality of fields for data entry;

receiving dictated voice into an audio input device;

generating, by a voice recognition engine operatively coupled to the audio input device, a first audio portion and a first text portion from the dictated voice, wherein the first audio portion and the first text portion are associated with the first field for data, and wherein the first audio portion is stored in an audio file and the first text portion is stored in an editable text file;

storing the audio file and editable text file in a first logical memory location;

receiving edits to the first text portion; and

storing the edited first text portion as a second document in a second logical memory location.

27. A machine readable medium having stored thereon a plurality of executable instructions, the plurality of instructions comprising instructions to:

acquire data related to a plurality of dictation subjects;

populate a database with the acquired data related to the plurality of dictation subjects;

receive identification of a first document from a plurality of documents, the first document having a plurality of fields for data entry;

receive identification of a first field in the plurality of fields for data entry;

receive dictated voice into an audio input device;

generate, by a voice recognition engine operatively coupled to the audio input device, a first audio portion and a first text portion from the dictated voice, wherein the first audio portion and the first text portion are associated with the first field for data, and wherein the first audio portion is stored in an audio file and the first text portion is stored in an editable text file;

store the audio file and editable text file in a first logical memory location;

receive edits to the first text portion; and

store the edited first text portion as a second document in a second logical memory location.

38. A method of generating a document by dictation to a handheld computing device, comprising:

selecting, by a first user at the handheld computing device;

a first dictation subject from a set of dictation subjects,

application data having a plurality of fields for data entry, and

a first field from the plurality of fields;

dictating, by the first user, speech into the handheld computing device, wherein the dictated speech is associated by an index with the first field;

repeating the dictating and associating for other fields in the plurality of fields;

storing the dictated speech as an audio file, the index, and the application data in a memory of the handheld computing device;

transferring the audio file, index, and application data to a memory of a server via a data transfer mechanism;

processing, at the server, the audio file content in a voice recognition engine to generate transcribed text associated with the plurality of fields of the application data in accordance with the index;

storing the processed audio file content as an editable transcribed text file;

editing, by a second user having access to the server, the editable transcribed text file;

updating a voice model of the first user based on editing by the second user;

storing the editable transcribed text file as a read-only transcribed text file in a read-only format;

deleting the editable transcribed text file, index, and audio file from the memory of the server; and

generating a report from the read-only transcribed text file.