# US 12,764,478 B2 · Method, apparatus and system for low latency audio enhancement > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,764,478 B2 - Document ID: US12764478B2 - Status: Granted - Kind: B2 - Application number: 18/963,074 - Filed: 2024-11-27 - Published: 2025-06-26 - Granted: 2026-10-13 - Earliest claimed: 2022-01-24 - Assignees: Fortell Research Inc. - Applicants: Fortell Research Inc. - Inventors: Igor Lovchinsky; Jonathan Macoskey; Philip Meyers, IV; Andrew J. Casper; Nicholas Morris - Web page: https://patentgrep.com/patent/US12764478B2 ## CPC - H04R 25/507: {implemented by neural network or fuzzy logic} - H04R 25/554: {using a wireless connection, e.g. between microphone and amplifier or using Tcoils} - H04R 2225/43: Signal processing in hearing aids to enhance the speech intelligibility - 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 According to some embodiments, an ear-worn device, e.g., a hearing aid, is provided that operates to enhance audio signals detected by the ear-worn device. In some embodiments, the ear-worn device includes a microphone, a processing circuit coupled to the microphone, and an output signal generator coupled to the processing circuit. In some embodiments, a method for enhancing audio signals includes: detecting an audio signal with the microphone; as the audio signal is being detected, dividing the audio signal into a plurality of segments; enhancing the detected audio signal with the processing circuit of the hearing aid; and outputting the enhanced audio signal with the output signal generator. In some embodiments, enhancing the detected audio signal includes processing one or more of the segments of the detected audio signal with a neural network engine (NNE) of the processing circuit to obtain an output for enhancing the detected audio signal. ## Claims ### Claim 1 A method for enhancing audio signals with a hearing aid, the hearing aid comprising a microphone, a processing circuit coupled to the microphone, and an output signal generator coupled to the processing circuit, the method comprising: detecting an audio signal with the microphone of the hearing aid; as the audio signal is being detected, dividing, with the processing circuit of the hearing aid, the audio signal into a plurality of overlapping segments, the plurality of overlapping segments comprising a first segment and a second segment, the first segment and the second segment sharing an overlapping portion, wherein the first segment is detected with the microphone before the second segment is detected with the microphone; after detecting the first segment, processing the first segment with a neural network engine (NNE) of the processing circuit to obtain a first output for enhancing the first segment including the overlapping portion; after detecting the second segment, processing the second segment with the NNE of the processing circuit to obtain a second output for enhancing the second segment including the overlapping portion; enhancing the overlapping portion based on the first output for enhancing the first segment and the second output for enhancing the second segment; transmitting the enhanced overlapping portion to the output signal generator for playback; and beginning playback of the enhanced overlapping portion with the output signal generator. ### Claim 2 (depends on 1) The method of claim 1, wherein the first segment further comprises a non-overlapping portion, the method further comprising: enhancing the non-overlapping portion based on the first output for enhancing the first segment; and before enhancing the overlapping portion, beginning playback of the enhanced non-overlapping portion with the output signal generator. ### Claim 3 (depends on 1) The method of claim 1, wherein the second segment further comprises a non-overlapping portion, and wherein the method further comprises: enhancing the non-overlapping portion of the second segment based on the second output for enhancing the second segment; and after completing playback of the enhanced overlapping portion, beginning playback of the enhanced non-overlapping portion of the second segment with the output signal generator. ### Claim 4 (depends on 1) The method of claim 1, wherein processing the first segment with the NNE of the processing circuit to obtain the first output comprises isolating a first speech component of the overlapping portion from a first noise component of the overlapping portion, and wherein processing the second segment with the NNE comprises isolating a second speech component of the overlapping portion from a second noise component of the overlapping portion. ### Claim 5 (depends on 1) The method of claim 1, wherein enhancing the overlapping portion comprises enhancing the overlapping portion with a digital signal processing (DSP) circuit of the processing circuit of the hearing aid. ### Claim 6 (depends on 1) The method of claim 1, wherein enhancing the overlapping portion based on the first output for enhancing the first segment and the second output for enhancing the second segment comprises enhancing the overlapping portion based on an average or a weighted average of the first and second outputs. ### Claim 7 (depends on 1) The method of claim 1, wherein processing the first segment with the NNE of the processing circuit to obtain the first output comprises generating a first mask for the first segment including the overlapping portion, and wherein processing the second segment with the NNE of the processing circuit to obtain the second output comprises generating a second mask for the second segment including the overlapping portion. ### Claim 8 (depends on 7) The method of claim 7, wherein enhancing the overlapping portion based on the first output for enhancing the first segment and the second output for enhancing the second segment comprises: combining the first mask for the first segment and the second mask for the second segment to obtain a combined mask for the overlapping portion; and applying the combined mask to the overlapping portion to generate the enhanced overlapping portion. ### Claim 9 (depends on 8) The method of claim 8, wherein combining the first mask for the first segment and the second mask for the second segment comprises determining an average or weighted average of the first and second masks. ### Claim 10 (depends on 1) The method of claim 1, wherein the NNE is a recurrent NNE. ### Claim 11 A hearing aid comprising: a microphone configured to detect an audio signal; a processing circuit coupled to the microphone and comprising a neural network engine (NNE), wherein the processing circuit is configured to: as the audio signal is being detected with the microphone, divide the audio signal into a plurality of overlapping segments, the plurality of overlapping segments comprising a first segment and a second segment, the first segment and the second segment sharing an overlapping portion, wherein the first segment is detected with the microphone before the second segment is detected with the microphone; after the first segment is detected, process the first segment with the NNE to obtain a first output for enhancing the first segment including the overlapping portion; after the second segment is detected, process the second segment with the NNE to obtain a second output for enhancing the second segment including the overlapping portion; enhance the overlapping portion based on the first output for enhancing the overlapping portion and the second output for enhancing the second segment including the overlapping portion; and transmit the enhanced overlapping portion to an output signal generator for playback; and the output signal generator coupled to the processing circuit and configured to playback the enhanced overlapping portion. ### Claim 12 (depends on 11) The hearing aid of claim 11, wherein: the first segment further comprises a non-overlapping portion, the processing circuit is further configured to enhance the non-overlapping portion based on the first output for enhancing the first segment, and the output signal generator is further configured to begin playback of the enhanced non-overlapping portion before the enhancing of the overlapping portion with the processing circuit. ### Claim 13 (depends on 11) The hearing aid of claim 11, wherein: the second segment further comprises a non-overlapping portion, the processing circuit is further configured to enhance the non-overlapping portion of the second segment based on the second output for enhancing the second segment, and the output signal generator is configured to begin playback of the enhanced non-overlapping portion of the second segment after completing playback of the enhanced overlapping portion. ### Claim 14 (depends on 11) The hearing aid of claim 11, wherein processing the first segment with the NNE to obtain the first output comprises isolating a first speech component of the overlapping portion from a first noise component of the overlapping portion, and wherein processing the second segment with the NNE comprises isolating a second speech component of the overlapping portion from a second noise component of the overlapping portion. ### Claim 15 (depends on 11) The hearing aid of claim 11, wherein the processing circuit further comprises a digital signal processing (DSP) circuit, wherein enhancing the overlapping portion comprises enhancing the overlapping portion with the DSP circuit. ### Claim 16 (depends on 11) The hearing aid of claim 11, wherein enhancing the overlapping portion based on the first output for enhancing the first segment and the second output for enhancing the second segment comprises enhancing the overlapping portion based on an average or a weighted average of the first and second outputs. ### Claim 17 (depends on 11) The hearing aid of claim 11, wherein processing the first segment with the NNE to obtain the first output comprises generating a first mask for the first segment including the overlapping portion, and wherein processing the second segment with the NNE to obtain the second output comprises generating a second mask for the second segment including the overlapping portion. ### Claim 18 (depends on 17) The hearing aid of claim 17, wherein enhancing the overlapping portion based on the first output for enhancing the first segment and the second output for enhancing the second segment comprises: combining the first mask for the first segment and the second mask for the second segment to obtain a combined mask for the overlapping portion; and applying the combined mask to the overlapping portion to generate the enhanced overlapping portion. ### Claim 19 (depends on 18) The hearing aid of claim 18, wherein combining the first mask for the first segment and the second mask for the second segment comprises determining an average or weighted average of the first and second masks. ### Claim 20 (depends on 11) The hearing aid of claim 11, wherein the NNE is a recurrent NNE.