# US 12,651,604 B2 · Device and method for AI-based noise suppression > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,651,604 B2 - Document ID: US12651604B2 - Status: Granted - Kind: B2 - Application number: 18/589,574 - Filed: 2024-02-28 - Published: 2025-08-28 - Granted: 2026-06-09 - Earliest claimed: 2024-02-28 - Assignees: Motorola Solutions, Inc. - Applicants: Motorola Solutions, Inc. - Inventors: Adam Gilboa; Leonid Nikolaev; Jesus F Corretjer; Oren Afriat; Amit Aroch; Yulia Louzon - Web page: https://patentgrep.com/patent/US12651604B2 ## CPC - G10L 21/0208: Noise filtering - G10L 21/0232: Processing in the frequency domain - G10K 11/17827: {Desired external signals, e.g. pass-through audio such as music or speech} - G10L 2021/02166: {Microphone arrays; Beamforming} - G10L 2021/02168: {the estimation exclusively taking place during speech pauses} - H04R 3/005: {for combining the signals of two or more microphones (specially adapted for hearing aids H04R25/407)} - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - G10K: SOUND-PRODUCING DEVICES; METHODS OR DEVICES FOR PROTECTING AGAINST, OR FOR DAMPING, NOISE OR OTHER ACOUSTIC WAVES IN GENERAL; ACOUSTICS NOT OTHERWISE PROVIDED FOR - 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 A device, system and method for AI-based noise suppression is provided. The device is configured to perform during a first period of time: applying one or more AI algorithms to an audio data; applying noise suppression to the audio data to generate a noise-suppressed audio data; and providing the noise-suppressed audio data to an output device. The device is further configured to perform during a second period of time, the second period of time following the first period of time: applying the one or more AI algorithms to the audio data to generate an AI-based noise-suppressed audio data; and providing the AI-based noise-suppressed audio data to the output device. ## Claims ### Claim 1 A device comprising: a microphone; an output device; a noise suppression engine configured to: receive audio data from the microphone; apply noise suppression to the audio data to generate a noise-suppressed audio data; an Artificial Intelligence (AI) noise suppression engine configured to: receive the audio data from the microphone or the noise suppression engine; apply one or more AI algorithms to the audio data to generate an AI-based noise-suppressed audio data; the device further configured to: perform during a first period of time: applying the one or more AI algorithms to the audio data; applying the noise suppression to the audio data to generate the noise-suppressed audio data; and providing the noise-suppressed audio data to the output device; and perform during a second period of time, the second period of time following the first period of time: applying, by the AI noise suppression engine, the one or more AI algorithms to the audio data to generate the AI-based noise-suppressed audio data; and providing, by the AI noise suppression engine, the AI-based noise-suppressed audio data to the output device. ### Claim 2 (depends on 1) The device of claim 1, further configured to trigger providing the AI-based noise-suppressed audio data to the output device based on reaching convergence by the one or more AI algorithms. ### Claim 3 (depends on 1) The device of claim 1, further configured to trigger providing the AI-based noise-suppressed audio data to the output device based on a relative comparison of noise suppression performance. ### Claim 4 (depends on 1) The device of claim 1, further comprising a switch configured to trigger providing the AI-based noise-suppressed audio data to the output device. ### Claim 5 (depends on 4) The device of claim 4, wherein the switch is configured to trigger providing the AI-based noise-suppressed audio data to the output device based on a predefined period of time. ### Claim 6 (depends on 5) The device of claim 5, wherein the predefined period of time is a convergence time determined for the one or more AI algorithms. ### Claim 7 (depends on 4) The device of claim 4, wherein the switch is configured to trigger providing the AI-based noise-suppressed audio data to the output device based on a reception of a convergence notification. ### Claim 8 (depends on 4) The device of claim 4, further comprising: a performance comparison engine configured to: determine that the AI noise suppression engine provides relatively better noise suppression performance than the noise suppression engine; and provide a performance comparison notification, wherein the switch is configured to trigger providing the AI-based noise-suppressed audio data to the output device based on a reception of the performance comparison notification. ### Claim 9 (depends on 1) The device of claim 1, further configured to trigger providing the AI-based noise-suppressed audio data to the output device at a time during a non-speech section of the noise-suppressed audio data. ### Claim 10 (depends on 4) The device of claim 4, wherein the switch is implemented by the noise suppression engine. ### Claim 11 (depends on 1) The device of claim 1, further configured to: provide the audio data to the noise suppression engine if a noise level of the audio data is below a predefined noise level threshold; and to provide the audio data to the AI noise suppression engine if the noise level of the audio data is equal to or above the predefined noise level threshold. ### Claim 12 (depends on 1) The device of claim 1, further comprising: a baseband processor configured to implement the noise suppression engine; and an audio processor configured to implement the AI noise suppression engine in parallel with the baseband processor implementing the noise suppression engine, the baseband processor and the audio processor in communication with each other. ### Claim 13 (depends on 1) The device of claim 1, further comprising: a baseband processor configured to implement the noise suppression engine and the AI noise suppression engine in parallel. ### Claim 14 (depends on 1) The device of claim 1, wherein the microphone and the noise suppression engine are integrated into an audio accessory. ### Claim 15 A system comprising a device and an audio accessory, wherein the audio accessory comprises: an accessory microphone; and an accessory noise suppression engine configured to: receive an accessory audio data from the accessory microphone; and apply a noise suppression to the accessory audio data to generate a noise-suppressed accessory audio data; and wherein the device comprises: an output device; and an Artificial Intelligence (AI) noise suppression engine configured to: receive the accessory audio data or the noise-suppressed accessory audio data; and apply one or more AI algorithms to the accessory audio data or the noise-suppressed accessory audio data to generate an AI-based noise-suppressed accessory audio data; the system further configured to: perform during a first period of time: applying the noise suppression to the accessory audio data to generate the noise-suppressed accessory audio data; applying the one or more AI algorithms to the accessory audio data or the noise-suppressed accessory audio data; and providing the noise-suppressed accessory audio data to the output device; and perform during a second period of time, the second period of time following the first period of time: applying, by the AI noise suppression engine, the one or more AI algorithms to the accessory audio data or the noise-suppressed accessory audio data to generate the AI-based noise-suppressed accessory audio data; and providing, by the AI noise suppression engine, the AI-based noise-suppressed accessory audio data to the output device. ### Claim 16 A method comprising: receiving, at a noise suppression engine, audio data from a microphone; receiving, at an Artificial Intelligence (AI) noise suppression engine, the audio data from the microphone or the noise suppression engine; performing during a first period of time: applying one or more AI algorithms to the audio data; applying a noise suppression to the audio data to generate a noise-suppressed audio data; and providing the noise-suppressed audio data to an output device; and performing during a second period of time, the second period of time following the first period of time: applying, by the AI noise suppression engine, the one or more AI algorithms to the audio data to generate an AI-based noise-suppressed audio data; and providing, by the AI noise suppression engine, the AI-based noise-suppressed audio data to the output device. ### Claim 17 (depends on 16) The method of claim 16, further comprising triggering of providing the AI-based noise-suppressed audio data to the output device based on the one or more of: reaching convergence by the one or more AI algorithms, a relative comparison of noise suppression performance, a predefined period of time, a reception of a convergence notification, a reception of a performance comparison notification, a noise level of the audio data. ### Claim 18 (depends on 16) The method of claim 16, further comprising triggering of providing the AI-based noise-suppressed audio data to the output device at a time during a non-speech section of the noise-suppressed audio data. ### Claim 19 (depends on 16) The method of claim 16, further comprising: implementing the noise suppression engine at a baseband processor; and implementing the AI noise suppression engine at an audio processor in parallel with the baseband processor implementing the noise suppression engine. ### Claim 20 (depends on 16) The method of claim 16, further comprising: implementing the noise suppression engine and the AI noise suppression engine in parallel at a baseband processor.