# US 12,223,975 B2 · Method to remove talker interference to noise estimator > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,223,975 B2 - Document ID: US12223975B2 - Status: Granted - Kind: B2 - Application number: 17/633,782 - Filed: 2020-09-15 - Published: 2022-10-13 - Granted: 2025-02-11 - Earliest claimed: 2019-10-01 - Assignees: Google Inc. - Applicants: Google LLC - Inventors: Jae Lee; Priya Kasirajan; Leng Ooi - Web page: https://patentgrep.com/patent/US12223975B2 ## CPC - G10L 21/0232: Processing in the frequency domain - H04R 1/1016: {Earpieces of the intra-aural type} - G10L 21/0216: characterised by the method used for estimating noise - H04R 1/1083: {Reduction of ambient noise (active noise reduction per se G10K11/175; protective devices for the ear, e.g. providing acoustic protection A61F11/06)} - G10L 25/78: Detection of presence or absence of voice signals (switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10) - G10L 2021/02087: {the noise being separate speech, e.g. cocktail party} - G10L 2021/02165: {Two microphones, one receiving mainly the noise signal and the other one mainly the speech signal} - G10L 2021/02166: {Microphone arrays; Beamforming} - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - H04R: LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS (producing sounds with frequency not determined by supply frequency G10K) ## Abstract The present disclosure provides systems and method for determining a background noise level. The device may receive audio from two or more microphones. The audio may include a first signal and a second signal, such that each microphone receives its own signal. The time, loudness, frequency of the first and second signals may be compared to determine the source of the audio, such as whether the audio is the user's voice or background noise. Based on the source of the audio, the audio may be suppressed to reduce false estimations when calculating the background noise level. ## Claims ### Claim 1 A method for determining a background noise level, the method comprising: receiving, by one or more processors, a first audio signal from a first microphone and a second audio signal from a second microphone; receiving, by the one or more processors, an accelerometer signal from one or more accelerometers, the accelerometer signal comprising at least one frequency; classifying, by the one or more processors and based on the at least one frequency, a type of activity of the user, the type of activity selected from among a plurality of types of activities, each of the plurality of types of activities corresponding with a frequency range; comparing, by the one or more processors, the first audio signal and the second audio signal; determining, by the one or more processors and based on the comparison, whether the source of the received first audio signal is a speech of a user or a background noise; determining, by the one or more processors and based on the classified type of activity, whether the user is talking; and responsive to a determination that the user is talking, suppressing, by the one or more processors, the first audio signal from the first microphone, the suppressed first audio signal configured to create an effect of receiving the first audio signal through a beamformer microphone that is beamformed in a direction away from or toward a mouth of the user. ### Claim 2 (depends on 1) The method of claim 1, further comprising: determining, by the one or more processors, a first time that the first audio signal was received from the first microphone; determining, by the one or more processors, a second time that the second audio signal was received from the second microphone; and determining, using the one or more processors, that the first time occurs before the second time, wherein determining whether the user is talking is further based on the determination that the first time occurs before the second time. ### Claim 3 (depends on 1) The method of claim 1, further comprising, based on the determination that the source of the received first audio signal is the speech of the user: detecting, by the one or more processors, the speech of the user in the suppressed first audio signal; and nullifying, using the one or more processors, the speech of the user from the suppressed first audio signal. ### Claim 4 (depends on 1) The method of claim 1, wherein the first microphone is located adjacent a first edge of a device and the second microphone is located adjacent a second edge of the device opposite the first edge. ### Claim 5 (depends on 1) The method of claim 1, wherein each of the first and second microphones has an omnidirectional beam pattern. ### Claim 6 (depends on 1) The method of claim 1, further comprising calculating, based on the received first audio signal, the received second audio signal, and the suppressed first audio signal, the background noise level. ### Claim 7 A device comprising: one or more accelerometers; a first microphone; a second microphone; and one or more processors in communication with the first microphone, the second microphone, and the one or more accelerometers, the one or more processors configured to: receive a first audio signal from the first microphone and a second audio signal from the second microphone; receive an accelerometer signal from the one or more accelerometers, the accelerometer signal comprising at least one frequency; classify, based on the at least one frequency, a type of activity of the user, the type of activity selected from among a plurality of types of activities, each of the plurality of types of activities corresponding with a frequency range; compare the first audio signal and the second audio signal; determine, based on the classified type of activity, whether a user is talking; determine, based on the comparison, whether a source of the first audio signal is a speech of the user; and responsive to a determination that the user is talking, suppress the first audio signal from the first microphone, the suppressed first audio signal configured to create an effect of receiving the audio through a beamformer microphone that is beamformed in a direction away from or toward a mouth of the user. ### Claim 8 (depends on 7) The device of claim 7, wherein the one or more processors are further configured to: determine a first time that the first audio signal was received from the first microphone; determine a second time that the second audio signal was received from the second microphone; and determine that the first time occurs before the second time, wherein when determining whether the user is talking is further based on the determination that the first time occurs before the second time. ### Claim 9 (depends on 7) The device of claim 7, wherein the one or more processors are further configured to, based on the determination that the source of the first audio signal is the speech of the user: detect the speech of the user in the suppressed first audio signal; and nullify the speech of the user from the suppressed first audio signal. ### Claim 10 (depends on 7) The device of claim 7, wherein the first microphone is located at a first end of the device and the second microphone is located at a second end of the device opposite the first end. ### Claim 11 (depends on 7) The device of claim 7, wherein the first and second microphones each have an omnidirectional beam pattern. ### Claim 12 (depends on 7) The device of claim 7, wherein the one or more processors are further configured to calculate, based on the received first audio signal, the received second audio signal, and the suppressed first audio signal, the background noise level. ### Claim 13 A non-transitory computer-readable medium storing instructions, which when executed by one or more processors, cause the one or more processors to: receive a first audio signal from a first microphone and a second audio signal from a second microphone; receive an accelerometer signal from one or more accelerometers, the accelerometer signal comprising at least one frequency; classify, based on the at least one frequency, a type of activity of the user, the type of activity selected from among a plurality of types of activities, each of the plurality of types of activities corresponding with a frequency range; compare the first audio signal and the second audio signal; determine, based on the classified type of activity, whether a user is talking; determine, based on the comparison, whether a source of the first audio signal is a speech of the user; and responsive to a determination that the user is talking, suppress the first audio signal from the first microphone, the suppressed first audio signal configured to create an effect of receiving the audio through a beamformer microphone that is beamformed in a direction away from or toward a mouth of the user. ### Claim 14 (depends on 13) The non-transitory computer-readable medium of claim 13, wherein the instructions further cause the one or more processors to: determine, when a user is talking, a speech of the user; detect the speech of the user in the suppressed first audio signal; and nullify the speech of the user from the suppressed first audio signal. ### Claim 15 (depends on 1) The method of claim 1, wherein configuring the suppressed first audio signal to create the effect of receiving the audio through a beamformer microphone that is beamformed in a direction away from or toward a mouth of the user comprises generating, using the one or more processors, a cardioid beam pattern based on the first audio signal. ### Claim 16 (depends on 1) The method of claim 1, wherein configuring the suppressed first audio signal to create the effect of receiving the audio through a beamformer microphone that is beamformed in a direction away from or toward a mouth of the user comprises generating, using the one or more processors, a hypercardioid beam pattern based on the first audio signal. ### Claim 17 (depends on 13) The non-transitory computer-readable medium of claim 13, wherein the instructions further cause one or more processors to: determine a first time that the first audio signal was received from the first microphone; determine a second time that the second audio signal was received from the second microphone; and determine that the first time occurs before the second time, wherein when determining whether the user is talking is further based on the determination that the first time occurs before the second time. ### Claim 18 (depends on 13) The non-transitory computer-readable medium of claim 13, wherein the first and second microphones each have an omnidirectional beam pattern. ### Claim 19 (depends on 13) The non-transitory computer-readable medium of claim 13, wherein the instructions further cause one or more processors to calculate, based on the received first audio signal, the received second audio signal, and the suppressed first audio signal, the background noise level. ### Claim 20 (depends on 1) The method of claim 1, wherein the plurality of types of activities includes talking, walking, typing, and driving. ### Claim 21 (depends on 1) The method of claim 1, wherein the accelerometer signal is a first accelerometer signal received at a first time, the method further comprising: receiving, by the one or more processors, a second accelerometer signal from the one or more accelerometers at a second time, the second time being before the first time and the second accelerometer signal comprising at least one frequency; classifying, by the one or more processors and based on the at least one frequency of the second accelerometer signal, a second type of activity of the user, the second type of activity selected from among the plurality of types of activities; determining, by the one or more processors and based on the classified second type of activity, that the user is not talking; and responsive to the determination that the user is not talking, monitoring, by the one or more processors, for additional accelerometer signals.