# US 11,443,760 B2 · Active sound control > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,760 B2 - Document ID: US11443760B2 - Status: Granted - Kind: B2 - Application number: 17/107,031 - Filed: 2020-11-30 - Published: 2021-11-11 - Granted: 2022-09-13 - Earliest claimed: 2020-05-08 - Assignees: DTEN, Inc. - Applicants: DTEN, Inc. - Inventors: Wei Liu; Jin Guo; Sally Tung; Yuchen Zhou; Jinxin Dong - Web page: https://patentgrep.com/patent/US11443760B2 ## CPC - 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) - H04R 3/005: {for combining the signals of two or more microphones (specially adapted for hearing aids H04R25/407)} - G10L 25/27: characterised by the analysis technique - H04R 3/04: for correcting frequency response - G10L 17/00: Speaker identification or verification techniques - G10L 17/26: Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices - G10L 21/0208: Noise filtering - H03G 3/32: the control being dependent upon ambient noise level or sound level - H04R 2430/01: Aspects of volume control, not necessarily automatic, in sound systems - 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) - H03G: CONTROL OF AMPLIFICATION ## Abstract A system automatically controls an electronic device's audio by detecting an active sound source presence within an auditory detection space. The system transitions the electronic device to selectively output a desired sound when the active sound source presence is detected and detects sound in the auditory detection space. The system enhances sound and transforms it into electrical signals. The system converts the electrical signals into a digital signal and identifies active sound segments in the digital signals. The system attenuates noise components in the digital signals and locates the physical location of the active sound source. It adjusts an output automatically by muting a second sound source in a second detection space. ## Claims ### Claim 1 A computer implemented method of controlling an electronic device's audio output, comprising: detecting an active sound source presence within an auditory detection space; transitioning the electronic device to selectively transmitting a desired sound when the active sound source presence is detected; detecting a sound segment from the active sound source in the auditory detection space and enhancing the sound segment when transformed into electrical signals; converting the electrical signals into a digital signals; identifying active sound segments within the digital signals; attenuating noise components within in the active sound segments; identifying a physical location of the active sound source; and adjusting an output automatically by muting a second active sound source in the auditory detection space in response to the identifying of the physical location of the active sound source. ### Claim 2 (depends on 1) The computer implemented method of claim 1 where the active sound presence is detected through a cross-correlation and a phase transform across a pair of microphones. ### Claim 3 (depends on 1) The computer implemented method of claim 1 where the auditory detection space comprises an interactive space and the sound source is generated by detecting energy distributions. ### Claim 4 (depends on 3) The computer implemented method of claim 3 where the auditory detection space comprises an interactive space and the sound source is generated by a plurality of reverberation effects. ### Claim 5 (depends on 3) The computer implemented method of claim 3 where the detection of the active sound source comprises an analysis of a plurality of physical regions monitored by a plurality of microphone pairs. ### Claim 6 (depends on 5) The computer implemented method of claim 5 where the analysis identifies a speech source and occurs continuously thereby tracking a plurality of changing speech sources. ### Claim 7 (depends on 6) The computer implemented method of claim 6 where the changing speech sources identifies the speech source is further identified and the changing speech sources tracked through a triangulation in three dimensions and a processing of a plurality of video images. ### Claim 8 (depends on 7) The computer implemented method of claim 7 where the processing of the plurality of video images is executed by a machine learning algorithm. ### Claim 9 (depends on 1) The computer implemented method of claim 1 further comprising modeling a plurality of temporal spaces of the noise components and the attenuating of the noise components is based on the modeling. ### Claim 10 (depends on 1) The computer implemented method of claim 1 where the noise components within in the active sound segments comprise noise components that occur near the active sound segments. ### Claim 11 (depends on 1) The computer implemented method of claim 1 further comprising averaging a portions of the active sound segment to render an average spectrum, comparing the average spectrum to average spectrum templates that comprise aural profiles, and identifying the sound source. ### Claim 12 (depends on 1) The computer implemented method of claim 1 where the device comprises a video teleconferencing system. ### Claim 13 A method of controlling video teleconferencing device's audio output, comprising: detecting an active sound source presence within an auditory detection space; transitioning the video teleconferencing device to selectively transmitting a desired sound when the active sound source presence is detected; detecting a sound segment from the active sound source in the auditory detection space and enhancing the sound segment when transformed into electrical signals; converting the electrical signals into a digital signals; identifying active sound segments within the digital signals; attenuating noise components within in the active sound segments; identifying a physical location of the active sound source; and adjusting an output automatically by muting a second active sound source in the auditory detection space in response to the identifying of the physical location of the active sound source. ### Claim 14 (depends on 13) The method of claim 13 where the active sound presence is detected through a cross-correlation and a phase transform across a pair of microphones. ### Claim 15 (depends on 13) The method of claim 13 where the auditory detection space comprises an interactive space and the sound source is generated by detecting energy distributions. ### Claim 16 (depends on 15) The method of claim 15 where the auditory detection space comprises an interactive space and the sound source is generated by a plurality of reverberation effects. ### Claim 17 (depends on 15) The method of claim 15 where the detection of the active sound source comprises an analysis of a plurality of physical regions monitored by a plurality of microphone pairs. ### Claim 18 (depends on 17) The method of claim 17 where the analysis identifies a speech source and occurs continuously thereby tracking a plurality of changing speech sources. ### Claim 19 (depends on 18) The method of claim 18 where the changing speech sources identifies the speech source is further identified and the changing speech sources tracked through a triangulation in three dimensions and a processing of a plurality of video images. ### Claim 20 (depends on 13) The method of claim 13 further comprising modeling a plurality of temporal spaces of the noise components and the attenuating of the noise components is based on the modeling.