# US 2021/0279634 A1 · Personalized and adaptive learning audio filtering > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0279634 A1 - Document ID: US20210279634A1 - Status: Published application - Kind: A1 - Application number: 16/809,648 - Filed: 2020-03-05 - Published: 2021-09-09 - Earliest claimed: 2020-03-05 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Elaheh ShafieiBavani; Fatemeh Jalali; Mahtab Mirmomeni; Ying Xu - Web page: https://patentgrep.com/patent/US20210279634A1 ## CPC - G06N 20/00: Machine learning - H04R 3/04: for correcting frequency response - A61B 5/7225: {Details of analogue processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation (input circuits for detecting, measuring, or recording bioelectric or biomagnetic signals A61B5/30; specific diagnostic methods using bioelectric or biomagnetic signals A61B5/316)} - A61B 5/725: {using specific filters therefor, e.g. Kalman or adaptive filters (specific diagnostics methods using using bioelectric or biomagnetic signals A61B5/316)} - A61B 5/7267: {involving training the classification device} - G06F 3/015: {Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection} - G06V 20/46: {Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames} - G10L 21/0208: Noise filtering - G10L 25/57: for processing of video signals - G10L 25/66: for extracting parameters related to health condition (detecting or measuring for diagnostic purposes A61B5/00) - A61B 5/0022: {Monitoring a patient using a global network, e.g. telephone networks, internet} - G06F 2218/00: Aspects of pattern recognition specially adapted for signal processing - G10L 21/0272: Voice signal separating - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - 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) - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract Aspects of the invention include a method including collecting, by a processor, physiological data from a user in an environment and a sound waveform from the user's environment. The method detects and labels as a potential annoyance, by the processor, a set of potential annoyance data based on the collected physiological data and the sound waveform. The method decomposes, by the processor, the sound waveform into a first sound waveform segment associated with the set of potential annoyance data and a second sound waveform segment not associated with the set of potential annoyance data. The method predicts, by the processor, that the potential annoyance is an actual annoyance. The method filters and modifies, by the processor, the first sound waveform segment associated with the actual annoyance and provides, by the processor, the second sound waveform segment not associated with the actual annoyance to the user. ## Claims ### Claim 1 A computer-implemented method comprising: collecting, by a processor, physiological data from a user in an environment and a sound waveform from the user's environment; detecting and labeling as a potential annoyance, by the processor, a set of potential annoyance data based on the collected physiological data and the sound waveform; decomposing, by the processor, the sound waveform into a first sound waveform segment associated with the set of potential annoyance data and a second sound waveform segment not associated with the set of potential annoyance data; predicting, by the processor, that the set of potential annoyance data is an actual annoyance; filtering and modifying, by the processor, the first sound waveform segment associated with the actual annoyance; and providing, by the processor, the second sound waveform segment not associated with the actual annoyance to the user. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein predicting, by the processor, that the set of potential annoyance data is an actual annoyance is performed using machine learning. ### Claim 3 (depends on 2) The computer-implemented method of claim 2, wherein training data for the machine learning includes an input and output pair where the input is the first sound waveform segment and the output is the potential annoyance label. ### Claim 4 (depends on 2) The computer-implemented method of claim 2, wherein machine learning is repeated periodically. ### Claim 5 (depends on 1) The computer-implemented method of claim 1 further comprising collecting, by the processor, a video input feed of the user and using the video input feed when detecting and labeling a potential annoyance. ### Claim 6 (depends on 1) The computer implemented method of claim 1, wherein detecting and labeling as a potential annoyance, by the processor, the set of potential annoyance data from the collected physiological data and the sound waveform comprises finding patterns of abnormal changes in the physiological data. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein decomposing, by the processor, the sound waveform into a first sound waveform segment associated with the set of potential annoyance data and a second sound waveform segment not associated with the set of potential annoyance data comprises decomposing using a non-negative matrix factor 2-D deconvolution algorithm. ### Claim 8 A system comprising: a memory having computer readable instructions; and one or more processors for executing the computer readable instructions, the computer readable instructions controlling the one or more processors to perform operations comprising: collecting physiological data from a user in an environment and a sound waveform from the user's environment; detecting and labeling as a potential annoyance a set of potential annoyance data based on the collected physiological data and the sound waveform; decomposing the sound waveform into a first sound waveform segment associated with the set of potential annoyance data and a second sound waveform segment not associated with the set of potential annoyance data; predicting that the set of potential annoyance data is an actual annoyance; filtering and modifying the first sound waveform segment associated with the actual annoyance; and providing the second sound waveform segment not associated with the actual annoyance to the user. ### Claim 9 (depends on 8) The system of claim 8, wherein predicting that the set of potential annoyance data is an actual annoyance is performed using machine learning. ### Claim 10 (depends on 9) The system of claim 9, wherein training data for the machine learning includes an input and output pair where the input is the first sound waveform segment and the output is the potential annoyance label. ### Claim 11 (depends on 10) The system of claim 10, wherein machine learning is repeated periodically. ### Claim 12 (depends on 8) The system of claim 8, further comprising collecting a video input feed of the user and using the video input feed when detecting and labeling a potential annoyance. ### Claim 13 (depends on 8) The system of claim 8, wherein detecting and labeling as a potential annoyance the set of potential annoyance data from the collected physiological data and the sound waveform comprises finding patterns of abnormal changes in the physiological data. ### Claim 14 (depends on 8) The system of claim 8, wherein decomposing the sound waveform into a first sound waveform segment associated with the set of potential annoyance data and a second sound waveform segment not associated with the set of potential annoyance data comprises decomposing using a non-negative matrix factor 2-D deconvolution algorithm. ### Claim 15 A computer program product comprising one or more computer readable storage media having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform operations comprising: collecting physiological data from a user in an environment and a sound waveform from the user's environment; detecting and labeling as a potential annoyance a set of potential annoyance data from the collected physiological data and the sound waveform; decomposing the sound waveform into a first sound waveform segment associated with the set of potential annoyance data and a second sound waveform segment not associated with the set of potential annoyance data; predicting that the set of potential annoyance data is an actual annoyance; filtering and modifying the first sound waveform segment associated with the actual annoyance; and providing the second sound waveform segment not associated with the actual annoyance to the user. ### Claim 16 (depends on 15) The computer program product of claim 15, wherein predicting that the set of potential annoyance data is an actual annoyance is performed using machine learning. ### Claim 17 (depends on 16) The computer program product of claim 16, wherein training data for the machine learning includes an input and output pair where the input is the first sound waveform segment and the output is the potential annoyance label. ### Claim 18 (depends on 15) The computer program product of claim 15, further comprising collecting a video input feed of the user and using the video input feed when detecting and labeling a potential annoyance. ### Claim 19 (depends on 15) The computer program product of claim 15, wherein detecting and labeling as a potential annoyance the set of potential annoyance data from the collected physiological data and the sound waveform comprises finding patterns of abnormal changes in the physiological data. ### Claim 20 (depends on 15) The computer program product of claim 15, wherein decomposing the sound waveform into a first sound waveform segment associated with the set of potential annoyance data and a second sound waveform segment not associated with the set of potential annoyance data comprises decomposing using a non-negative matrix factor 2-D deconvolution algorithm.