# US 2019/0172464 A1 · System and method for determining recipient of spoken command in a control system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0172464 A1 - Document ID: US20190172464A1 - Status: Published application - Kind: A1 - Application number: 16/272,252 - Filed: 2019-02-11 - Published: 2019-06-06 - Earliest claimed: 2015-09-10 - Assignees: Crestron Electronics, Inc. - Inventors: Fred Bargetzi; Ara Seferian; Josh Stene; Mark LaBosco - Web page: https://patentgrep.com/patent/US20190172464A1 ## CPC - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback} - G10L 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications - G10L 21/0208: Noise filtering - G10L 2015/223: {Execution procedure of a spoken command} - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Disclosed is an apparatus and method for determining which controllable device an audible command is directed towards, the method comprising: receiving at each of two or more controlling devices the audible command signal, the audible command being directed to control at least one of two or more controllable devices controlled by a respective one of the two or more controlling devices; digitizing each of the received audible command signals; attaching a unique identifier to each digitized audible command so as to uniquely correlate it to a respective controlling device; determining a magnitude of each of the digitized audible command; determining a digitized audible command with the greatest magnitude, and further determining to which controlling device the audible command is directed to on the basis of the unique identifier associated with the digitized audible command with the greatest magnitude; performing speech recognition on the digitized audible command with the greatest magnitude; and forwarding a command to the controlling device corresponding to the digitized audible command with the greatest magnitude, the command corresponding to the audible command that can be implemented on the controllable device controlled by the controlling device. ## Claims ### Claim 1 An acoustic sensor network comprising: four or more controllable devices, at least two of which are located in a first room and at least two of which are located in a second room; two or more controlling devices, each of the two or more controlling devices comprising at least one respective microphone, and an analog to digital converter, a first controlling device being located in the first room, and a second controlling device being located in the second room, and wherein the first controlling device located in the first room is adapted to control the at least two controllable devices located in the first room, and the second controlling device located in the second room is adapted to control the at least two controllable devices located in the second room, and further wherein each of the first and second controlling devices are further adapted to receive an audible command through the at least one respective microphone, the received audible command being directed to control one of the two or more controllable devices controlled by the respective controlling device, and wherein each of the analog-to-digital converters are adapted to digitize the received audible command; a first occupancy sensor located in the first room; a second occupancy sensor located in the second room; and a central controller adapted to receive the digitized audible command and perform speech recognition to determine which type of controllable device the digitized audible command is directed towards, and wherein the central controller is further adapted to receive an output from each of the first and second occupancy sensors, wherein the output reports an occupied state of the respective room, and further wherein the central controller is adapted to determine that an occupancy sensor reading associated with a respective controlling device, within a predefined period of time before the audible command was received, indicates a recently occupied room, and apply the audible command to the controllable device in the room that was recently occupied. ### Claim 2 (depends on 1) The acoustic sensor network according to claim 1, wherein each of the two or more controlling devices are further adapted to attach a unique identifier to each of the digitized audible commands so as to uniquely correlate it to a respective controlling device and transmit the same, and wherein the central controller is further adapted to receive each of the transmitted digitized audible commands, determine a magnitude of each of the digitized audible commands, determine a digitized audible command with the greatest magnitude, and further determine to which controlling device the audible command is directed to on the basis of the unique identifier associated with the digitized audible command with the greatest magnitude. ### Claim 3 (depends on 2) The acoustic sensor network according to claim 2, wherein the central controller is further adapted to forward the digitized audible command with the greatest magnitude to the controlling device on the basis of the unique identifier, and wherein the controlling device is further adapted to forward the digitized audible command to the controllable device. ### Claim 4 (depends on 2) The acoustic sensor network according to claim 2, wherein each of the controlling devices are further adapted to attach a time-date stamp to the digitized audible commands, and wherein the central controller is further adapted to verify that the time-date stamp of the digitized audible command with the greatest magnitude is the same or earlier than the time-date stamp of any other digitized received audible command signal. ### Claim 5 (depends on 4) The acoustic sensor network according to claim 4, wherein the central controller is further adapted to apply additional processing to determine which controlling device the received audible command is directed to if the time-date stamp of the digitized audible command signal with the greatest magnitude is later than the time-date stamp any other digitized audible command. ### Claim 6 (depends on 5) The acoustic sensor network according to claim 5, wherein the central controller is further adapted to check one or more of a proximity sensor reading and motion detector reading, each of which is associated with respective controlling devices to determine which controlling device the received audible command is directed towards. ### Claim 7 (depends on 6) The acoustic sensor network according to claim 6, wherein the central controller is further adapted to determine that the proximity sensor reading associated with a respective controlling device matches the received audible command in order to determine that the received audible command should be applied to the controllable device controlled by the respective controlling device. ### Claim 8 (depends on 6) The acoustic sensor network according to claim 6, wherein the central controller is further adapted to determine that the motion detector reading associated with a respective controlling device matches the received audible command in order to determine that the received audible command should be applied to the controllable device controlled by the respective controlling device. ### Claim 9 (depends on 2) The acoustic sensor network according to claim 2, wherein each of the respective controlling devices are further adapted to attach the time-date stamp to the digitized audible command received at the respective controlling device through use of a time-date stamp generator using a time synch protocol. ### Claim 10 (depends on 2) The acoustic sensor network according to claim 2, wherein the central controller is further adapted to generate a test signal to determine a travel time from each of the plurality of controlling devices to the central controller, modify the time-date stamp of each received digitized audible command signal according to the travel time from a respective controlling device to the central processor, and use the modified time-date stamp to assist in determining to which controlling device the audible command signal is directed to. ### Claim 11 (depends on 1) The acoustic sensor network according to claim 1, wherein the controlling device further comprises: a time-date stamp generator adapted to generate the time-date stamp; and at least two microphones, each of which digitizes the received audible command, and wherein, the controlling device is further adapted to average all of the time-date stamps generated at the controlling device and attach the averaged time-date stamps to each of the plurality of digitized audible commands prior to transmitting the same. ### Claim 12 (depends on 1) The acoustic sensor network according to claim 1, wherein the controlling device further comprises: a noise reduction processing circuit. ### Claim 13 (depends on 12) The acoustic sensor network according to claim 12, wherein the noise reduction processing circuit is adapted to filter the received audible command in an analog domain to attenuate a first bandwidth of noise energy. ### Claim 14 (depends on 12) The acoustic sensor network according to claim 12, wherein the noise reduction processing circuit is adapted to use one or more of acoustic echo cancellation filtering, direction of arrival filtering, and directionally adaptive beam forming filtering, to filter the digitized audible command in a digital domain to attenuate noise energy and to amplify audible command energy. ### Claim 15 (depends on 14) The acoustic sensor network according to claim 14, wherein the noise energy comprises: noise energy generated by one or more of a fan motor, music, air conditioning noise, audio generated by multi-media presentations, and non-command words. ### Claim 16 (depends on 1) The acoustic sensor network according to claim 1, further comprising: at least one additional spatially separated microphone, adapted to receive the audible command, and associated with one of the at least two controlling devices; an analog to digital converter associated with the at least one spatially separated microphone, and adapted to digitize the received audible command; a time-date stamp generator adapted to add a time-date stamp to the additional digitized audible command, and further adapted to add a unique identifier to the additional digitized audible command, the unique identifier corresponding to the associated one of the controlling devices, and further wherein the central controller uses the at least one additional digitized audible command to assist in determining to which controlling device the audible command is directed to. ### Claim 17 (depends on 1) The acoustic sensor network according to claim 1, wherein the controllable devices include one or more of a sensor, lighting control device, shade device, audio/video device, environmental control device, security device, household appliance, control device, and industrial device. ### Claim 18 (depends on 1) The acoustic sensor network according to claim 1, wherein the controlling device comprises: a keypad.