Voice control input for portable capture devices

• US 6,289,140 B1
• Filed: 12/23/1998
• Issued: 09/11/2001
• Est. Priority Date: 02/19/1998
• Status: Expired due to Term

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Company (HP Inc.)
• Inventors: Oliver, Thomas C
• Primary Examiner(s): Couso, Jose L.
• Assistant Examiner(s): Do, Anh Hong
• Application Number:
  US09/219,970
• Time in Patent Office: 993 Days
• Field of Search: 382/313, 375/133, 370/320, 370/335, 707/200, 707/104, 348/143, 348/154, 348/155, 704/275, 704/270.1, 379/88.1, 600/443
• US Class Current: 382/313
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 19/00 Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis in musical instruments G10H
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: H04M 3/42204 Arrangements at the exchange for service or number selection by voice at the terminal H04M1/27
• CPC Class Codes: H04N 1/00127 Connection or combination of a still picture apparatus with another apparatus, e.g. for storage, processing or transmission of still picture signals or of information associated with a still picture
• CPC Class Codes: H04N 1/00204 with a digital computer or a digital computer system, e.g. an internet server programmed control between transmitter and receiver or between image input and image output device H04N1/32561
• CPC Class Codes: H04N 1/00326 with a data reading, recognizing or recording apparatus, e.g. with a bar-code apparatus arrangements for the associated working of recording or reproducing apparatus with related apparatus G11B31/00
• CPC Class Codes: H04N 1/32122 in a separate device, e.g. in a memory or on a display separate from image data
• CPC Class Codes: H04N 1/32128 attached to the image data, e.g. file header, transmitted message header, information on the same page or in the same computer file as the image for information embedded in the image H04N1/32144
• CPC Class Codes: H04N 2201/0081 Image reader H04N2201/0091 - H04N2201/0094 take precedence
• CPC Class Codes: H04N 2201/3222 of processing required or performed, e.g. forwarding, urgent or confidential handling
• CPC Class Codes: H04N 2201/3264 of sound signals
• CPC Class Codes: H04N 2201/3274 Storage or retrieval of prestored additional information
• CPC Class Codes: H04N 2201/3278 Transmission

Abstract

A portable capture device, such as a hand held document scanner or digital camera, that receives voice commands for operation control is disclosed. Commands such as “scan”, “save”, “delete”, “left”, “zoom in”, and “send” are illustrative, where the capture device will perform the predetermined functions associated with the command names. In one embodiment, the portable capture device trains itself to recognize the user'"'"'s spoken commands through voice analysis software. The voice analysis software may be located within the capture device, or on a host computer system and accessed by the capture device while tethered to the host computer system. The capture device has an audio input/output system under the control of a controller. Upon receiving a voice control input command, the controller saves the digitized voice input in dynamic memory. The controller then compares the command received with the commands stored in a command recognition table held in static memory.

Claims

1. A voice control input method for a capture device, said method comprising the steps of:

(a0) using a separate host computer system for training said capture device to accept voice commands, comprising the steps of

(a0a) loading voice analysis software into a memory in said host computer system, wherein sad host computer system is separate from said capture device,

(a0b) connecting said capture device to said host computer system,

(a0c) selecting a predetermined function, with said voice analysis software, for training and voice analysis of at least one word for invoking said predetermined function,

(a0d) capturing a plurality of voice inputs of said at least one word in said voice pickup component of said capture device,

(a0e) processing said plurality of voice inputs into a plurality of digital signals in said capture device,

(a0f) sending said plurality of digital signals from said capture device to said host computer system,

(a0g) analyzing said plurality of digital signals with said voice analysis software,

(a0h) developing said at least one recognition pattern from said analysis of said plurality of digital signals with said voice analysis software,

(a0i) storing said at least one recognition pattern in said memory in said host computer system, and

(a0j) transferring said at least one recognition pattern in said memory in said host computer system to said command recognition table in said static memory in said capture device, wherein said at least one recognition pattern is linked to said first set of instructions stored in said command recognition table for performing said predetermined function;

(a) capturing a first voice control input command with a voice pickup component in said capture device;

(b) converting said first voice control input command into a first analog signal;

(c) converting said first analog signal into a first digital signal;

(d) converting said first digital signal into a first recognition pattern;

(e) comparing said first recognition pattern to at least one recognition pattern stored in a command recognition table in a static memory in said capture device; and

(f) when said first recognition pattern matches said at least one recognition pattern stored in said command recognition table, executing a first set of instructions linked to said at least one recognition pattern.

2. The voice control input method for a capture device according to claim 1 wherein said capture device is a scanner device.

3. The voice control input method for a capture device according to claim 1 wherein said capture device is a digital camera.

4. The voice control input method for a capture device according to claim 1 wherein step (b) further comprises the step (b1), and step (c) further comprises the steps (c1) through (c3):

(b1) inputting, to an analog-to-digital converter in said capture device, said first analog signal;

(c1) converting said first analog signal, in said analog-to-digital converter, to said first digital signal;

(c2) transferring said first digital signal from said analog-to-digital converter to a controller in said capture device; and

(c3) storing, by said controller, said first digital signal in a dynamic memory in said capture device.

5. The voice control input method for a capture device according to claim 1 wherein step (d) further comprises the step (d1):

(d1) performing a plurality of frequency domain transforms on said first digital signal stored in a dynamic memory in said capture device, generating said first recognition pattern, wherein said first recognition pattern is a spectral transform of said first digital signal.

6. The voice control input method for a capture device according to claim 1 wherein said at least one word is language independent.

7. The voice control input method for a capture device according to claim 1 further comprising the steps of:

(a0k) repeating steps (a0c) through (a0j) for a plurality of predetermined functions, wherein a plurality of recognition patterns are developed from a plurality of said plurality of voice inputs for a plurality of said at least one words, and further wherein said plurality of recognition patterns are stored in said command recognition table in said static memory in said capture device, wherein each of said plurality of recognition patterns are linked to one of a plurality of predetermined sets of instructions stored in said command recognition table for performing one of said plurality of predetermined functions.

8. The voice control input method for a capture device according to claim 1 wherein step (a0a) is replaced by the new step (a0a), steps (a0b), (a0f), and (a0i) are eliminated, and step (a0j) is replaced by the new step (a0j):

(a0a) accessing voice analysis software in said static memory in said capture device; and

(a0j) storing said at least one recognition pattern in said command recognition table in said static memory in said capture device, wherein said at least one recognition pattern is linked to said first set of instructions stored in said command recognition table for performing said predetermined function.

9. The voice control input method for a capture device according to claim 8 wherein said at least one word is language independent.

10. The voice control input method for a capture device according to claim 8 further comprising the steps of:

(a0k) repeating steps (a0c) through (a0j) for a plurality of predetermined functions, wherein a plurality of recognition patterns are developed from a plurality of said plurality of voice inputs for a plurality of said at least one words, and further wherein said plurality of recognition patterns are stored in said command recognition table in said static memory in said capture device, wherein each of said plurality of recognition patterns are linked to one of a plurality of predetermined sets of instructions stored in said command recognition table for performing one of said plurality of predetermined functions.

11. The voice control input method for a capture device according to claim 1 wherein said first recognition pattern, representing a password command, matches said at least one recognition pattern stored in said command recognition table, and further wherein said first set of instructions executed in step (f) further comprises the following step (f1):

(f1) enabling said capture device to receive and process additional voice control input commands.

12. The voice control input method for a capture device according to claim 1 wherein said first recognition pattern, representing a voice annotation command, matches said at least one recognition pattern stored in said command recognition table, and further wherein said first set of instructions executed in step (f) further comprises the following steps (f1) through (f8):

(f1) until a predetermined period of absence of voice input has occurred, performing steps (f2) through (f6);

(f2) capturing a stream of voice input with said voice pickup component in said capture device;

(f3) converting said stream of voice input into a second analog signal;

(f4) inputting, to an analog-to-digital converter in said capture device, said second analog signal;

(f5) converting said second analog signal, in said analog-to-digital converter, to a second digital signal;

(f6) transferring said second digital signal from said analog-to-digital converter to a controller in said capture device;

(f7) storing, by said controller, said second digital signal in said static memory in said capture device as a voice annotation file; and

(f8) connecting said voice annotation file to a data file stored in said static memory.

13. The voice control input method for a capture device according to claim 1 further comprising the steps of:

(g) receiving button down input in a controller from an annotation control button on said capture device;

(h) until button up input is received in said controller from said annotation control button, performing steps (i) through (m);

(i) capturing a stream of voice input with said voice pickup component;

(j) converting said stream of voice input into a second analog signal;

(k) inputting, to an analog-to-digital converter in said capture device, said second analog signal;

(l) converting said second analog signal, in said analog-to-digital converter, to a second digital signal;

(m) transferring said second digital signal from said analog-to-digital converter to a controller in said capture device;

(n) receiving said button up input in said controller from said annotation control button on said capture device;

(o) storing, by said controller, said second digital signal in said static memory in said capture device as a voice annotation file; and

(p) connecting said voice annotation file to a data file stored in said static memory.

14. A capture device with voice control input comprising:

a voice pickup component for capturing a first voice control input command and for outputting said first voice control input command as a first analog signal;

an analog-to-digital converter, connected to said voice pickup component, for 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 converting said first digital signal into a first recognition pattern;

a dynamic memory, connected to said controller, for storing said first digital signal and said first recognition pattern;

a static memory, connected to said controller, for storing at least one recognition pattern in a command recognition table, and for storing in said command recognition table a first set of instructions for performing a predetermined function, wherein said first set of instructions are linked to said at least one recognition pattern;

a host connection connected to said controller; and

a host computer system, separate from said capture device, wherein said host connection of said capture device is connected to a communications interface of said host computer system, allowing communication to occur between said capture device and said host computer system, and further wherein a plurality of voice inputs of at least one word to be used for invoking said predetermined function are captured by said voice pickup component, processed in said capture device into a plurality of digital signals which are transferred from said host connection to said communications interface in said host computer system, and further wherein said plurality of digital signals are analyzed with voice analysis software loaded into a memory in said host computer system, generating said at least one recognition pattern for said at least one word from said plurality of digital signals, and said at least one recognition pattern is transferred from said communications interface to said host connection of said capture device and stored in said command recognition table in said static memory in said capture device;

wherein, said controller compares said first recognition pattern with said at least one recognition pattern in said command recognition table stored in said static memory, and further wherein, when said first recognition pattern and said at least one recognition pattern match, said controller executes said first set of instructions linked to said at least one recognition pattern for performing said predetermined function.

15. The capture device with voice control input according to claim 14 wherein said capture device is a scanner device.

16. The capture device with voice control input according to claim 14 wherein said capture device is a digital camera.

17. The capture device with voice control input according to claim 14 wherein said controller converts said first digital signal into said first recognition pattern by performing a plurality of frequency domain transforms on said first digital signal, generating said first recognition pattern, wherein said first recognition pattern is a spectral transform of said first digital signal.

18. The capture device with voice control input according to claim 14 further comprising:

an annotation control button connected to said controller, wherein when button down input from said annotation control button is received by said controller, and until button up input from said annotation control button is received by said controller, a stream of voice input, captured by said voice pickup component between said button down input and said button up input, is converted to a second analog signal, and said second analog signal is converted to a second digital signal by said analog-to-digital converter, and stored as a voice annotation file in said static memory in said capture device, and connected to a data file stored in said static memory.