# US 12,016,098 B1 · System and method for user presence detection based on audio events > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,016,098 B1 - Document ID: US12016098B1 - Status: Granted - Kind: B1 - Application number: 17/020,290 - Filed: 2020-09-14 - Granted: 2024-06-18 - Earliest claimed: 2019-09-12 - Assignees: Renesas Electronics America Inc. - Applicants: Reality Analytics, Inc. - Inventors: Jeffrey Sieracki; Xavier Gutierrez - Web page: https://patentgrep.com/patent/US12016098B1 ## CPC - H05B 47/12: by detecting audible sound - G05B 19/048: Monitoring; Safety - G08B 13/1672: {using sonic detecting means, e.g. a microphone operating in the audio frequency range} - G08B 21/0469: {Presence detectors to detect unsafe condition, e.g. infrared sensor, microphone (G08B21/0476 takes precedence)} - G10L 25/03: characterised by the type of extracted parameters - G10L 25/51: for comparison or discrimination - G05B 2219/2642: Domotique, domestic, home control, automation, smart house - H05B: ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL - G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G) - G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract A system and method are provided for detecting the presence of animate users, such as people, within a monitored environment, based on audio events. A transducer captures sound signals generated within the monitored environment, which a capture channel converts to form a digital stream. A feature extractor detects predetermined signal features of the digital stream over predetermined extraction periods, and an event classifier uses values of these features to generate a series of detection events reflective of likely sources of sounds in the captured sound signals. Then, an event buffer maintains an aggregate count of detection events generated by the event classifier, and a status generator generates the user presence indicator according to the aggregate count of detection events. A response system triggers one of more functions responsive to one or user presence indicators, thereby responding to the presence or absence of the animate users. ## Claims ### Claim 1 A system for detecting the presence of animate users within a monitored environment, the system comprising: at least one transducer configured to capture vibration signals generated within the monitored environment; a capture channel coupled to the transducer, the capture channel receiving and converting the signals captured by the transducer to form a digital stream; and a processor configured to generate a user presence indicator for the monitored environment, the processor including: a feature extractor executing to detect at least one predetermined signal feature of the digital stream over a predetermined extraction period; at least one event classifier executing to generate a series of detection events responsive to the predetermined signal features of the predetermined extraction period; at least one event buffer having a predetermined event buffer length defining a buffer period, the event buffer executing to maintain, for a built-in delay period associated with said at least one event buffer, an aggregate count of detection events generated by the event classifier; and a status generator executing to generate the user presence indicator according to the aggregate count of detection events, said user presence indicator having an inertia corresponding to said built-in delay period, wherein said status generator maintains the user presence indicator for said built-in delay period; wherein the user presence indicator is provided for triggering one or more functions of a response system. ### Claim 2 (depends on 1) The system of claim 1, wherein each detection event is assigned a source weight corresponding to one of a plurality of source categories, the processor includes a plurality of event buffers each maintaining an aggregate count of detection events having a designated source weight, and the status generator generates the user presence indicator according to a combination of weighted aggregate counts of the event buffers. ### Claim 3 (depends on 2) The system of claim 2, wherein the plurality of source categories includes vocal human activity, non-vocal human activity, and non-human activity. ### Claim 4 (depends on 1) The system of claim 1, wherein the feature extractor generates feature vectors representing a plurality of feature values, each feature value representing a measurement of one of the predetermined signal features, the event classifier generating each detection event according to at least one generated feature vector. ### Claim 5 (depends on 1) The system of claim 1, wherein the feature extractor includes a spectrogram-type extractor configured to execute processes including Fourier transformation of time-spaced portions of the digital stream within the predetermined extraction period. ### Claim 6 (depends on 1) The system of claim 1, wherein the event classifier generates the detection events according at least in part to a root-mean-square (RMS) energy value of the digital stream during the extraction period. ### Claim 7 (depends on 1) The system of claim 1, wherein the event classifier generates the detection events according at least in part to a crest value of the digital stream during the extraction period. ### Claim 8 (depends on 1) The system of claim 1, wherein the status generator generates the user presence indicator over a period shorter than the event buffer length. ### Claim 9 (depends on 1) The system of claim 1, wherein each detection event is assigned a weight in the aggregate count according at least in part to an accuracy of the event classifier generating the detection event. ### Claim 10 (depends on 1) The system of claim 1, wherein each detection event is assigned a weight in the aggregate count according at least in part to a predetermined likelihood that the detection event indicates a user presence. ### Claim 11 (depends on 1) The system of claim 1, wherein the user presence indicator includes a binary value. ### Claim 12 (depends on 1) The system of claim 1, wherein the user presence indicator includes a probability value. ### Claim 13 (depends on 1) The system of claim 1, wherein the response system controls lighting within the monitored environment, the response system including one or more light sources, and the triggered functions including active and inactive lighting states. ### Claim 14 (depends on 1) The system of claim 1, wherein the response system includes an alarm system.