Interactive speech recognition device and system for hands-free building control

• US 8,340,975 B1
• Filed: 10/04/2011
• Issued: 12/25/2012
• Est. Priority Date: 10/04/2011
• Status: Active Grant

• Current Assignee: Theodore Alfred Rosenberger
• Original Assignee: Theodore Alfred Rosenberger
• Inventors: Rosenberger, Theodore Alfred
• Primary Examiner(s): Desir, Pierre-Louis
• Assistant Examiner(s): BAKER, MATTHEW H
• Application Number:
  US13/252,849
• Time in Patent Office: 448 Days
• Field of Search: 704270-275
• US Class Current: 704/275
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A self-contained wireless interactive speech recognition control device and system that integrates with automated systems and appliances to provide totally hands-free speech control capabilities for a given space. Preferably, each device comprises a programmable microcontroller having embedded speech recognition and audio output capabilities, a microphone, a speaker and a wireless communication system through which a plurality of devices can communicate with each other and with one or more system controllers or automated mechanisms. The device may be enclosed in a stand-alone housing or within a standard electrical wall box. Several devices may be installed in close proximity to one another to ensure hands-free coverage throughout the space. When two or more devices are triggered simultaneously by the same speech command, real time coordination ensures that only one device will respond to the command.

Claims

1. An interactive, self-contained, speech recognition control device that is adapted for use in an automated building control system in which a plurality of functionally identical devices are positioned at different locations throughout a building space to enable a system user to control the actions of the system, via speech commands only, from various locations within the building space, as well as to enable such device to audibly interact with the system user, said device comprising a housing operatively supporting:

(a) a microphone for converting spoken words, emanating from a system user located within said building space, to corresponding electrical signals;

(b) a programmable microcontroller, operatively coupled to the microphone and comprising embedded software and circuitry serving to;

(i) continuously monitor said electrical signals in order to recognize when a trigger phrase from an expected vocabulary has likely been spoken,

(ii) produce a weighted signal having a value representing the quality of a just-recognized trigger phrase, and

(iii) in the event the value of said weighted signal exceeds the respective values of all weighted signals produced by other devices located within said building space that have simultaneously recognized the same trigger phrase, produce audible user interactions and system control signals by which a desired effect, reflective of speech commands uttered by the system user and recognized by said device, is achieved within the building space by automated mechanisms that respond to said system control signals;

(c) a transmitter operatively coupled to said microcontroller for selectively transmitting said weighted signal and said system control signals into said building space;

(d) a receiver, operatively coupled to said microcontroller, for receiving (i) weighted signals emanating from one or more other functionally identical interactive speech recognition control devices within said building space, and/or (ii) coordination signal derived from said weighted signals by an independent coordinating controller; and

(e) audio output circuitry through which said microcontroller can transmit audible sounds to interact with and provide indications of the system status to the system user.

2. The device as defined by claim 1 wherein said weighted signal incorporates one or more quantifiable measures representing the detected loudness of said trigger phrase and/or the estimated probability that said trigger phrase was correctly recognized by the embedded software of the microcontroller.

3. The device as defined by claim 1 wherein, upon said weighted signal being compared with all other weighted signals received from said other devices in said building space, if it is determined that the quality of a just-recognized trigger phrase received by said device is poorer than the quality of the same trigger phrase recognized simultaneously by said other devices, said device will immediately terminate further handling of said just-recognized trigger phrase.

4. The device as defined by claim 1 wherein, upon said weighted signal being compared with all other weighted signals produced by said other devices in said building space at the same time, if it is determined that the quality of a just-recognized trigger phrase received by said device is better than the quality of the same trigger phrase recognized simultaneously by said other devices, said device will proceed to respond to the system user.

5. The device as defined by claim 1 wherein the comparison of said weighted signals is performed collectively by said device and all other like devices within said building space that have simultaneously received and recognized the same trigger phrase.

6. The device as defined by claim 1 wherein the comparison of weighted signals is made by an independent coordinating controller to which said interactive speech recognition control device is operatively coupled in a multi-device system.

7. The device as defined by claim 1 wherein said comparison of weighted signals is made between the weighted signal produced by said device and a weighted signal produced by at least one other device within said space with which said device is paired.

8. The device as defined by claim 1 wherein said transmitter and receiver components transmit and receive said weighted signals and system control signals via radio-frequency (RF) signals.

9. The device as defined by claim 1 wherein said transmitter and receiver components transmit and receive said weighted signals and system control signals via a power line communication system.

10. The device as defined by claim 1 wherein said housing is adapted to be received by a standard electrical wall box.

11. The device as defined by claim 10 wherein said device further comprises electrical load control circuitry, mounted within said housing, for controlling and/or dimming electrical loads, lighting loads and power outlets, said electrical load control circuitry being operatively coupled to and controlled by said microcontroller.

12. An automated building control system comprising:

a plurality of automated mechanisms that respond to predetermined system control signals to achieve a desired effect within a building space; and

a plurality of functionally identical, interactive, self-contained, speech recognition control devices that are configured to be positioned at different locations throughout said building space to enable a system user to control the operation of said automated building control system, via speech commands only, from various locations within said building space, each of said control devices including a housing operatively supporting;

(a) a microphone for converting spoken words, emanating from a system user located within said building space, to corresponding electrical signals;

(b) a programmable microcontroller, operatively coupled to the microphone and comprising embedded software and circuitry serving to;

(i) continuously monitor said electrical signals in order to recognize when a trigger phrase from an expected vocabulary has likely been spoken,

(ii) produce a weighted signal having a value representing the quality of a just-recognized trigger phrase, and

(iii) in the event the value of said weighted signal exceeds the respective values of all weighted signals produced by other devices located within said building space that have simultaneously recognized the same trigger phrase, produce audible user interactions and system control signals by which a desired effect, reflective of the speech commands uttered by the system user and recognized by said device, is achieved within the building space by automated mechanisms that respond to said system control signals;

(c) a transmitter operatively coupled to said microcontroller for selectively transmitting said weighted signal and said system control signals into said building space;

(d) a receiver, operatively coupled to said microcontroller, for receiving (i) weighted signals emanating from one or more other functionally identical interactive speech recognition control devices within said building space, and/or (ii) coordination signal derived from said weighted signals by an independent coordinating controller; and

(e) audio output circuitry through which said microcontroller can transmit audible sounds to interact with and provide indications of the system status to the system user;

each of the respective microcontrollers of said control devices operating to compare the respective values of weighted signals received from said other control devices with the value of the weighted signal it has produced to determine whether said microcontroller will produce any subsequent user interactions and said system control signals for transmission into said building space.

13. The system as defined by claim 12 wherein said weighted signal incorporates one or more quantifiable measures representing the detected loudness of said trigger phrase and/or the estimated probability that said trigger phrase was correctly recognized by the embedded software of the microcontroller.

14. The system as defined by claim 12 wherein, upon comparing said weighted signals, if a microcontroller determines that the value of the weighted signal it has produced is lower than the value of any one of the weighted signals received from said other control devices, said microcontroller will immediately terminate further handling of said trigger phrase.

15. The system as defined by claim 12 wherein, upon comparing said weighted signals, if a microcontroller determines that the value of the weighted signal it has produced is higher than the value of all other weighted signals it has received from said other control devices, said microcontroller will proceed to handle said trigger phrase by interacting with the system user and producing said system control signals.

16. The system as defined by claim 12 wherein the comparison of said weighted signals is performed collectively by all control devices within said building space that have simultaneously received and recognized the same trigger phrase.

17. The system as defined by claim 12 wherein said control signals are transmitted directly to said automated mechanisms.

18. The system as defined by claim 12 further comprising a system controller operatively coupled with each of said control devices and with each of said automated mechanisms, said system controller being configured to effect desired changes by said automated mechanisms in response to system control signals produced by any one of said control devices.

19. An automated building control system comprising:

a plurality of automated mechanisms that respond to predetermined system control signals to achieve a desired effect within a building space;

a plurality of functionally identical, interactive, self-contained, speech recognition control devices that are configured to be positioned at different locations throughout said building space to enable a system user to control the operation of said automated building control system, via speech commands only, from various locations within said building space, each of said devices including a housing operatively supporting;

(a) a microphone for converting spoken words, emanating from a system user located within said building space, to corresponding electrical signals;

(b) a programmable microcontroller, operatively coupled to the microphone and comprising embedded software and circuitry serving to;

(i) continuously monitor said electrical signals in order to recognize when a trigger phrase from an expected vocabulary has likely been spoken,

(ii) produce a weighted signal having a value representing the quality of a just-recognized trigger phrase, and

(iii) in the event the value of said weighted signal exceeds the respective values of all weighted signals produced by other devices located within said building space that have simultaneously recognized the same trigger phrase, produce audible user interactions and system control signals by which a desired effect, reflective of the speech commands uttered by the system user and recognized by said device, is achieved within the building space by automated mechanisms that respond to said system control signals;

(c) a transmitter operatively coupled to said microcontroller for selectively transmitting said weighted signal and said system control signals into said building space;

(d) a receiver, operatively coupled to said microcontroller, for receiving (i) weighted signals emanating from one or more other functionally identical interactive speech recognition control devices within said building space, and/or (ii) coordination signal derived from said weighted signals by an independent coordinating controller; and

(e) audio output circuitry through which said microcontroller can transmit audible sounds to interact with and provide indications of the system status to the system user; and

(c) a coordinating controller being positioned within said building space and adapted to receive and compare the respective weighted signals produced by a plurality of control devices that have simultaneously recognized a given trigger phrase to determine which one of said plurality of control devices will control subsequent handling of said given trigger phrase, said coordinating controller being configured to transmit a signal to one or more of said control devices to implement that determination.

20. The system as defined by claim 19 wherein each of said control devices operates to await a predetermined time period after transmitting said weighted signal into said building space to receive said signal from said coordinating controller, and thereafter, return from a trigger phrase processing mode to a listening mode, and wherein said coordinating controller, upon determining which one of said plurality of control devices is to subsequently handle said given trigger phrase, transmits a signal, during said time period, to said one control device instructing it to proceed in responding to said given trigger phrase.

21. The system as defined by claim 19 wherein each of said control devices, after awaiting a predetermined time period after transmitting said weighted signal into said building space, proceeds to process said speech trigger phrase, and wherein said coordinating controller, upon determining which one of said plurality of control devices is to subsequently handle said given trigger phrase, transmits a signal to each of the other of said control devices, during said time period, instructing each not to proceed in handling said given trigger phrase.

22. The system as defined by claim 19 wherein said weighted signal incorporates one or more quantifiable measures representing the detected trigger phrase loudness and/or the estimated probability that the trigger phrase was correctly recognized by the embedded software of the microcontroller.

23. The system as defined by claim 19 wherein said control signals are transmitted directly to said automated mechanisms.

24. The system as defined by claim 19 further comprising a system controller operatively coupled with each of said control devices and with each of said automated mechanisms, said system controller being configured to effect desired changes by said automated mechanisms in response to system control signals produced by any one of said control devices.