Voice macros for scanner control

• US 6,816,837 B1
• Filed: 05/06/1999
• Issued: 11/09/2004
• Est. Priority Date: 05/06/1999
• Status: Expired due to Fees

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Davis, Kenneth P.
• Primary Examiner(s): SMITS, TALIVALDIS IVARS
• Application Number:
  US09/306,469
• Time in Patent Office: 2,014 Days
• Field of Search: 704/275
• US Class Current: 704/275
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A voice controlled capture device contains a processor that receives voice macros to control its operation. The capture device receives voice input, digitizes and sends the input to a second processor in a host computer system where speech recognition software within the host computer interprets the voice input to select a macro, and returns commands from the macro to the capture device where they are executed. Utilizing an interface or macro recorder within the capture device, and the speech recognition software within the host computer, the user can create voice macros incorporating individual voice commands. In a second embodiment, the capture device both analyzes the voice input and executes the commands of the macro.

Claims

1. A voice macro control method for a voice controlled capture device comprising the steps of:

(a) receiving a first voice macro command voice input in a voice pickup component of said voice controlled capture device;

(b) converting said first voice macro command voice input into a first digital signal and sending said first digital signal to a host processor;

(c) converting, within said host processor, said first digital signal into a first recognition pattern;

(d) comparing said first recognition pattern to at least one stored recognition pattern stored in a voice macro command recognition table;

(e) when said first recognition pattern matches one of said at least one stored recognition patterns stored in said voice macro command recognition table, retrieving a voice macro command file linked to said one of said at least one stored recognition patterns, and sending said voice macro command file to said capture device;

(f) accessing, within said capture device, at least one command number from said voice macro command file;

(g) finding a matching command number in a voice command recognition table;

(h) retrieving a first voice command file linked to said matching command number in said voice command recognition table; and

(i) executing at least one instruction from said first voice command file.

2. The voice macro control method for a voice controlled capture device according to claim 1 wherein step (b) further comprises the steps of:

(b1) converting said first voice macro command voice input into a first analog signal; and

(b2) converting said first analog signal into said first digital signal.

3. The voice macro control method for a voice controlled capture device according to claim 1 wherein step (c) further comprises the step of:

(c1) performing a plurality of frequency domain transforms on said first digital signal, wherein said plurality of frequency domain transforms generate said first recognition pattern, and further wherein said first recognition pattern is a spectral transform of said first digital signal.

4. The voice macro control method for a voice controlled capture device according to claim 1 wherein step (e) is replaced with the following new step (e) and steps (f), (g), (h), and (i) are not performed:

(e) when said first recognition pattern does not match one of said at least one stored recognition patterns stored in said voice macro command recognition table, outputting an indication of no match.

5. The voice macro control method for a voice controlled capture device according to claim 1 wherein said at least one command number is at least one command text.

6. The voice macro control method for a voice controlled capture device according to claim 1 further comprising the step of:

(j) repeating steps (f) through (i) for a plurality of command numbers from said voice macro command file.

7. The voice macro control method for a voice controlled capture device according to claim 1 further comprising the steps (a0a) through (a0k) performed before step (a):

(a0a) activating a macro recorder to create a first voice macro command;

(a0b) receiving at least one voice command voice input in said voice pickup component;

(a0c) converting said at least one voice command voice input into a second digital signal, and sending said digital signal to a host processor;

(a0d) converting, in said host processor, said second digital signal into a second recognition pattern;

(a0e) comparing said second recognition pattern to at least one stored recognition pattern stored in said voice command recognition table;

(a0f) when said second recognition pattern matches one of said at least one stored recognition patterns stored in said voice command recognition table, storing in a memory a first command number from said one of said at least one stored recognition patterns matching said second recognition pattern, wherein said first command number matches said at least one command number from said voice macro command file;

(a0g) receiving, in said capture device, a first voice input to name said first voice macro command, wherein said first voice macro command voice input matches said first voice input;

(a0h) converting said first voice input into a third digital signal, and sending said digital signal to said host processor;

(a0i) converting, in said host processor, said third digital signal into a first created recognition pattern, wherein said first recognition pattern matches said first created recognition pattern;

(a0j) storing said first created recognition pattern in said voice macro command recognition table; and

(a0k) storing said first command number in said voice macro command file, wherein said voice macro command file is linked to said first created recognition pattern.

8. The voice macro control method for a voice controlled capture device according to claim 7 wherein step (a0f) is replaced by the following new step (a0f) and steps (a0g), (a0h), (a0i), (a0j), and (a0k) are not performed:

(a0f) when said second recognition pattern does not match one of said at least one stored recognition patterns stored in said voice command recognition table, outputting an indication of no match.

9. The voice macro control method for a voice controlled capture device according to claim 7 wherein said first command number is a first command text, and said at least one command number at least one command text.

10. The voice macro control method for a voice controlled capture device according to claim 7 wherein step (a0f) further comprises the step (a0f1):

(a0f1) repeating steps (a0b) through (a0f) for a plurality of voice command voice inputs.

11. The voice macro control method for a voice controlled capture device according to claim 7 further comprising the step of:

(a01) repeating steps (a0b) through (a0k) for a plurality of voice macro commands.

12. The voice macro control method for a voice controlled capture device according to claim 7 wherein step (a0a) is replaced with the following new step (a0a):

(a0a) selecting a create macro option from a capture device user interface loaded into a memory in a host computer system to create a first voice macro command, wherein said host computer system is in communication with said voice controlled capture device.

13. The voice macro control method for a voice controlled capture device according to claim 1 wherein step (f) is replaced with the following new step (f), step (g) is replaced with the following new step (g), step (h) is replaced with the following new step (h), step (i) is replaced with the following new step (i), and further comprising the new step (j):

(f) accessing at least one digital signal from said voice macro command file;

(g) converting said at least one digital signal into a second recognition pattern;

(h) comparing said second recognition pattern to at least one stored recognition pattern stored in a voice command recognition table;

(i) when said second recognition pattern matches one of said at least one stored recognition patterns stored in said voice command recognition table, retrieving a voice command file linked to said one of said at least one stored recognition patterns; and

(j) executing at least one instruction from said first voice command file.

14. The voice macro control method for a voice controlled capture device according to claim 13 wherein step (g) further comprises the step of:

(g1) performing a plurality of frequency domain transforms on said at least one digital signal from said voice macro command file, wherein said plurality of frequency domain transforms generate said second recognition pattern, and further wherein said second recognition pattern is a spectral transform of said at least one digital signal.

15. The voice macro control method for a voice controlled capture device according to claim 13 wherein step (i) is replaced with the following new step (i), and step (j) is replaced with the following new step (j), and further comprising the new steps (k), (l), and (m):

(i) when said second recognition pattern does not match one of said at least one stored recognition patterns stored in said voice command recognition table, outputting an indication of no match;

(j) outputting a prompt requesting input to continue or input to abort;

(k) when said input to continue is received, performing step (l) and not step (m), and when said input to abort is received, performing step (m) and not step (l);

(l) repeating steps (f) through (k) for a next digital signal from said voice macro command file; and

(m) ending said voice macro control method.

16. The voice macro control method for a voice controlled capture device according to claim 13 further comprising the step of:

(k) repeating steps (f) through (j) for a plurality of digital signals from said voice command file.

17. The voice macro control method for a voice controlled capture device according to claim 13 further comprising the steps (a0a) through (a0h) performed before step (a):

(a0a) activating a macro recorder to create a first voice macro command;

(a0b) receiving at least one voice command voice input in said voice pickup component;

(a0c) converting said at least one voice command voice input into a second digital signal;

(a0d) receiving a first voice input to name said first voice macro command, wherein said first voice macro command voice input matches said first voice input;

(a0e) converting said first voice input into a third digital signal;

(a0f) converting said third digital signal into a first created recognition pattern, wherein said first recognition pattern matches said first created recognition pattern;

(a0g) storing said first created recognition pattern in said voice macro command recognition table; and

(a0h) storing said second digital signal in said voice macro command file, wherein said voice macro command file is linked to said first created recognition pattern.

18. The voice macro control method for a voice controlled capture device according to claim 17 wherein step (a0c) further comprises the step (a0c1):

(a0c1) repeating steps (a0b) through (a0c) for a plurality of voice command voice inputs.

19. The voice macro control method for a voice controlled capture device according to claim 17 further comprising the step of:

(a0i) repeating steps (a0b) through (a0h) for a plurality of voice macro commands.

20. The voice macro control method for a voice controlled capture device according to claim 17 wherein step (a0a) is replaced with the following new step (a0a):

(a0a) selecting a create macro option from a capture device user interface loaded into a memory in a host computer system to create a first voice macro command, wherein said host computer system is in communication with said voice controlled capture device.

21. A voice controlled capture system comprising:

a voice pickup component for receiving a first voice macro command voice input and converting said first voice macro command voice input into a first analog signal, said voice pickup component being contained in a voice capture device;

an analog-to-digital converter connected to said voice pickup component for receiving and converting said first analog signal into a first digital signal;

a controller connected to said analog-to-digital converter for receiving said first digital signal, and for sending said first digital signal to a host processor;

a memory, contained in said host processor, for storing voice analysis software, for storing a voice macro command recognition table, and for storing a voice command recognition table;

wherein said controller sends said first digital signal to said voice analysis software to convert said first digital signal into a first recognition pattern, and further wherein said host processor compares said first recognition pattern to at least one stored recognition pattern stored in said voice macro command recognition table, and when said first recognition pattern matches one of said at least one stored recognition patterns, said host processor retrieves a voice macro command file linked to said one of said at least one stored recognition patterns, and accesses at least one command number from said voice macro command file, and finds a matching command number in said voice command recognition table, wherein said host processor retrieves a first voice command file linked to said matching command number, and sends said voice command file to said controller which executes at least one instruction from said first voice command file.

22. The voice controlled capture system according to claim 21 wherein said voice analysis software performs a plurality of frequency domain transforms on said first digital signal, and further wherein said plurality of frequency domain transforms generates said first recognition pattern which is a spectral transform of said first digital signal.

23. The voice controlled capture system according to claim 21 wherein said at least one command number is at least one command text.

24. The voice controlled capture system according to claim 21 wherein said host processor accesses a plurality of command numbers from said voice macro command file, and finds a plurality of matching command numbers in said voice command recognition table, wherein said host processor retrieves a plurality of voice command files linked to said plurality of matching command numbers, and said controller executes a plurality of at least one instructions from said plurality of voice command files.

25. The voice controlled capture system according to claim 21 further comprising:

a macro recorder stored in said memory for creating a first voice macro command;

wherein, after said macro recorder is activated, at least one voice command voice input is received and converted by said voice pickup component into a second analog signal, and said analog-to-digital converter receives and converts said second analog signal into a second digital signal, and said controller sends said digital signal to said voice analysis software to convert said second digital signal into a second recognition pattern, wherein said host processor compares said second recognition pattern to at least one stored recognition pattern stored in said voice command recognition table, and when said second recognition pattern matches one of said at least one stored recognition patterns stored in said voice command recognition table, a first command number from said one of said at least one stored recognition patterns matching said second recognition pattern is stored in said memory, wherein said at least one command number matches said first command number, and further wherein a first voice input to name said first voice macro command is received and converted by said voice pickup component into a third analog signal, wherein said first voice macro command voice input matches said first voice input, and said analog-to-digital converter receives and converts said third analog signal into a third digital signal, and said controller sends said third digital signal to said voice analysis software to convert said third digital signal into a first created recognition pattern, wherein said first recognition pattern matches said first created recognition pattern, and said first created recognition pattern is stored in said voice macro command recognition table, and said first command number is stored in said voice macro command file, wherein said voice macro command file is linked to said first created recognition pattern.

26. The voice controlled capture system according to claim 25 wherein said first command number is a first command text, and said at least one command number is at least one command text.

27. The voice controlled capture system according to claim 25 wherein a plurality of voice command voice inputs are processed in creating said first voice macro command.

28. The voice controlled capture system according to claim 25 wherein a plurality of voice macro commands are created.

29. The voice controlled capture system according to claim 21 wherein said host processor accesses at least one digital signal from said voice macro command file instead of said at least one command number, and further wherein said at least one digital signal is converted into a second recognition pattern, and said second recognition pattern is compared to at least one stored recognition pattern stored in said voice command recognition table, and when said second recognition pattern matches one of said at least one stored recognition patterns stored in said voice command recognition table, a voice command file linked to said one of said at least one stored recognition patterns is retrieved, and said controller executes at least one instruction from said first voice command file.

30. A voice controlled capture device system comprising:

a voice controlled capture device, said voice controlled capture device further comprising

a voice pickup component for receiving a first voice macro command voice input and converting said first voice macro command voice input into a first analog signal;

an analog-to-digital converter connected to said voice pickup component for receiving and converting said first analog signal into a first digital signal;

a controller connected to said analog-to-digital converter for receiving said first digital signal;

a host connection connected to said controller for sending said first digital signal; and

a host computer system, said host computer system further comprising

a communications interface in communication with said host connection for receiving said first digital signal from said host connection;

a memory connected to said communications interface for receiving and storing said first digital signal, and for storing voice analysis software, for storing a voice macro command recognition table, for storing a voice command recognition table, and for storing a capture device user interface;

wherein said capture device user interface calls said voice analysis software to convert said first digital signal into a first recognition pattern, and further wherein said capture device user interface compares said first recognition pattern to at least one stored recognition pattern stored in said voice macro command recognition table, and when said first recognition pattern matches one of said at least one stored recognition patterns, said capture device user interface retrieves a voice macro command file linked to said one of said at least one stored recognition patterns, and accesses at least one command number from said voice macro command file, and finds a matching command number in said voice command recognition table, wherein said capture device user interface retrieves a first voice command file linked to said matching command number, and sends at least one instruction from said first voice command file to said controller, wherein said controller executes said at least one instruction.

31. The voice controlled capture device system according to claim 30 wherein said voice analysis software performs a plurality of frequency domain transforms on said first digital signal, and further wherein said plurality of frequency domain transforms generates said first recognition pattern which is a spectral transform of said first digital signal.

32. The voice controlled capture device system according to claim 30 wherein said at least one command number is at least one command text.

33. The voice controlled capture device system according to claim 30 wherein said capture device user interface accesses a plurality of command numbers from said voice macro command file, and finds a plurality of matching command numbers in said voice command recognition table, wherein said capture device user interface retrieves a plurality of voice command files linked to said plurality of matching command numbers, and sends a plurality of at least one instructions from said plurality of voice command files to said controller, wherein said controller executes said plurality of at least one instructions.

34. The voice controlled capture device system according to claim 30 further comprising:

a create macro option within said capture device user interface for creating a first voice macro command;

wherein, after said create macro option is selected, at least one voice command voice input is received and converted by said voice pickup component into a second analog signal, and said analog-to-digital converter receives and converts said second analog signal into a second digital signal, and said controller sends said second digital to said memory in said host computer system through said host connection and through said communications interface, wherein said capture device user interface calls said voice analysis software to convert said second digital signal into a second recognition pattern, wherein said capture device user interface compares said second recognition pattern to at least one stored recognition pattern stored in said voice command recognition table, and when said second recognition pattern matches one of said at least one stored recognition patterns stored in said voice command recognition table, a first command number from said one of said at least one stored recognition patterns matching said second recognition pattern is stored in said dynamic memory, wherein said at least one command number matches said first command number, and further wherein a first voice input to name said first voice macro command is received and converted by said voice pickup component into a third analog signal, wherein said first voice macro command voice input matches said first voice input, and said analog-to-digital converter receives and converts said third analog signal into a third digital signal, and said controller sends said third digital to said memory in said host computer system through said host connection and through said communications interface, and said capture device user interface calls said voice analysis software to convert said third digital signal into a first created recognition pattern, wherein said first recognition pattern matches said first created recognition pattern, and said first created recognition pattern is stored in said voice macro command recognition table, and said first command number is stored in said voice macro command file, wherein said voice macro command file is linked to said first created recognition pattern.

35. The voice controlled capture device system according to claim 34 wherein said first command number is a first command text, and said at least one command number is at least one command text.

36. The voice controlled capture device system according to claim 34 wherein a plurality of voice command voice inputs are processed in creating said first voice macro command.

37. The voice controlled capture device system according to claim 34 wherein a plurality of voice macro commands are created.

38. The voice controlled capture device system according to claim 30 wherein said capture device user interface accesses at least one digital signal from said voice macro command file instead of said at least one command number, and further wherein said at least one digital signal is converted into a second recognition pattern, and said second recognition pattern is compared to at least one stored recognition pattern stored in said voice command recognition table, and when said second recognition pattern matches one of said at least one stored recognition patterns stored in said voice command recognition table, a voice command file linked to said one of said at least one stored recognition patterns is retrieved, and at least one instruction from said first voice command file is sent to said controller, wherein said controller executes said at least one instruction.