System and Method for Controlling the Operation of a Device by Voice Commands

• US 20090043580A1
• Filed: 07/24/2008
• Published: 02/12/2009
• Est. Priority Date: 09/25/2003
• Status: Active Grant

• Current Assignee: Sensory Incorporated
• Original Assignee: Sensory Incorporated
• Inventors: Mozer, Forrest S., Mozer, Todd F., Adams, Erich B.
• Granted Patent: US 7,774,204 B2
• Time in Patent Office: Days
• US Class Current: 704/251
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

The present invention includes a speech recognition system comprising a light element, a power control switch, the power control switch varying the power delivered to the light element, a controller, a microphone, a speech recognizer coupled to the microphone for recognizing speech input signals and transmitting recognition results to the controller, and a speech synthesizer coupled to the controller for generating synthesized speech, wherein the controller varies the power to the light element in accordance with the recognition results received from the speech recognizer. Embodiments of the invention may alternatively include a low power wake up circuit. In another embodiment, the present invention is a method of controlling a device by voice commands.

Claims

1. A speech recognition system comprising:

a light element;

a power control switch coupled between the light element and an AC power supply, the power control switch varying the power delivered to the light element;

a controller coupled to the power control switch;

a first auxiliary sensing device having an output coupled to the controller;

a microphone;

a speech recognizer coupled to the microphone for recognizing speech input signals and transmitting recognition results to the controller; and

a speech synthesizer coupled to the controller for generating synthesized speech,

wherein the controller varies the power to the light element in accordance with the recognition results received from the speech recognizer and the output of the auxiliary sensing device.

2. The speech recognition system of claim 1 wherein the first auxiliary sensing device is a light sensor.

3. The speech recognition system of claim 2 wherein the controller dims the light element when the light sensor output is below a threshold.

4. The speech recognition system of claim 2 wherein the light element is switched from an on state to a dimmed state in response to voice commands when the light sensor output is below a threshold.

5. The speech recognition system of claim 1 further comprising a display.

6. The speech recognition system of claim 5 wherein the display comprises a plurality of light emitting diodes.

7. The speech recognition system of claim 1 wherein the controller is programmed with an algorithm comprising:

generating a first dialog;

generating a second dialog in response to receiving a trigger word from a user if the trigger word is in a first recognition set;

executing one of a plurality of predefined algorithms in response to receiving a command word from a user if the command word is in a second recognition set, the plurality of predefined algorithms including varying the power to a light element, generating a simulated dialog with a user or activating a plurality of light emitting diodes.

8. The speech recognition system of claim 1 wherein the controller is a microcontroller.

9. The speech recognition system of claim 1 wherein the controller is a microprocessor.

10. The speech recognition system of claim 1 wherein the speech recognition system is a lamp, the lamp further comprising a lamp attachment movably attached to the lamp by a magnet.

11. A speech recognition system comprising:

a microphone;

a first low power audio channel coupled to the microphone;

a second audio channel coupled to the microphone; and

a processor having signal lines coupled to the first and second audio channels,

wherein the processor turns on the first low power audio channel and turns off the second audio channel during a low power mode of operation, and the processor turns on the second audio channel when the first low power audio channel receives an input signal above a first threshold.

12. The speech recognition system of claim 11 wherein the first low power audio channel comprises a comparator.

13. The speech recognition system of claim 11 further comprising a microphone power control circuit.

14. The speech recognition system of claim 11 wherein the processor enters a low power sleep state during the low power mode.

15. The speech recognition system of claim 11 wherein the second audio channel is a high resolution audio channel.

16. The speech recognition system of claim 12 wherein the second audio channel comprises an analog-to-digital converter.

17. A method of controlling a device by voice commands comprising:

storing a plurality of speech synthesis dialogs;

generating a first dialog of the plurality of speech synthesis dialogs using a speech synthesizer;

receiving a trigger word from a user;

generating a second dialog of the plurality of speech synthesis dialogs using a speech synthesizer if the trigger word is in a first recognition set;

receiving a command word from a user; and

executing one of a plurality of predefined algorithms if the command word is in a second recognition set, the plurality of predefined algorithms including varying the power to a light element.

18. The method of claim 17 further comprising automatically dimming a light element.

19. The method of claim 17 wherein the plurality of predefined algorithms further includes generating a simulated dialog with a user.

20. The method of claim 17 wherein the plurality of predefined algorithms includes activating a plurality of light emitting diodes.

21. The method of claim 17 wherein varying power to a light element comprises toggling the light element between an on state and a dim state or off state.

22. The method of claim 17 wherein if the trigger word is in the first recognition set the system enters a ready state for receiving a command word, and wherein the simulated dialog comprises:

generating a third dialog from a second plurality of speech synthesis dialogs; and

returning to the ready state for receiving a command word.