Abstract: One embodiment provides a method comprising obtaining, via a microphone of a hearable device, one or more measurements of a first individual transfer function from a transducer of the hearable device to a first sound pressure at the microphone. At least a portion of the hearable device is within proximity of an ear canal of an individual ear. The method further comprises determining, based on the one or more measurements of the first individual transfer function, a second individual transfer function from the first sound pressure to a second sound pressure at an eardrum within the ear canal. The method further comprises applying, based in part on the second individual transfer function, personalized equalization (PEQ) within the audio full range (low, mid and high frequencies) to an audio signal for reproduction via the hearable device.

Abstract: In one embodiment, a method includes determining human directivity index (DI) pattern data corresponding to a location of a listener, based on vocalization recorded by a microphone at each of a plurality of loudspeakers. The method further includes extracting a set of DI features from the DI pattern data; providing the set of DI features to a trained machine-learning model; and determining, by the trained machine-learning model and based on the set of DI features, a placement of each of the plurality of loudspeakers relative to the listener.

Abstract: One embodiment provides a computer-implemented method that includes acquiring, via at least one microphone, sound pressure data from a loudspeaker in a room. The sound pressure data is input into an artificial intelligence (AI) model. The AI model automatically estimates, without user interaction, at least one of energy average (EA) in a listening area or total sound power (TSP) produced by the loudspeaker. The AI model is trained prior to automatically estimating the at least one of the EA in the listening area or the TSP produced by the loudspeaker.

Abstract: One embodiment provides a method of automatic spatial calibration. The method comprises estimating one or more distances from one or more loudspeakers to a listening area based on a machine learning model and one or more propagation delays from the one or more loudspeakers to the listening area. The method further comprises estimating one or more incidence angles of the one or more loudspeakers relative to the listening area based on the one or more propagation delays. The method further comprises applying spatial perception correction to audio reproduced by the one or more loudspeakers based on the one or more distances and the one or more incidence angles. The spatial perception correction comprises delay and gain compensation that corrects misplacement of any of the one or more loudspeakers relative to the listening area.

Abstract: One embodiment provides a method of automatic loudspeaker directivity adaptation. The method comprises measuring one or more room impulse responses (RIRs) from one or more loudspeakers to one or more microphones of the one or more loudspeakers, estimating reverberation time and clarity based on the one or more RIRs, and estimating one or more positions of the one or more loudspeakers based on the one or more RIRs. The method further comprises automatically adapting directivity of the one or more loudspeakers based on the reverberation time estimated, the clarity estimated, and the one or more positions estimated.

Abstract: One embodiment provides a method of automatic spatial calibration. The method comprises estimating one or more distances from one or more loudspeakers to a listening area based on a machine learning model and one or more propagation delays from the one or more loudspeakers to the listening area. The method further comprises estimating one or more incidence angles of the one or more loudspeakers relative to the listening area based on the one or more propagation delays. The method further comprises applying spatial perception correction to audio reproduced by the one or more loudspeakers based on the one or more distances and the one or more incidence angles. The spatial perception correction comprises delay and gain compensation that corrects misplacement of any of the one or more loudspeakers relative to the listening area.

Abstract: One embodiment provides a computer-implemented method that includes acquiring, via at least one microphone, sound pressure data from a loudspeaker in a room. The sound pressure data is input into an artificial intelligence (AI) model. The AI model automatically estimates, without user interaction, at least one of energy average (EA) in a listening area or total sound power (TSP) produced by the loudspeaker. The AI model is trained prior to automatically estimating the at least one of the EA in the listening area or the TSP produced by the loudspeaker.

Abstract: One embodiment provides a method of automatic spatial calibration. The method comprises estimating one or more distances from one or more loudspeakers to a listening area based on a machine learning model and one or more propagation delays from the one or more loudspeakers to the listening area. The method further comprises estimating one or more incidence angles of the one or more loudspeakers relative to the listening area based on the one or more propagation delays. The method further comprises applying spatial perception correction to audio reproduced by the one or more loudspeakers based on the one or more distances and the one or more incidence angles. The spatial perception correction comprises delay and gain compensation that corrects misplacement of any of the one or more loudspeakers relative to the listening area.

Abstract: One embodiment provides a method of automatic spatial calibration. The method comprises estimating one or more distances from one or more loudspeakers to a listening area based on a machine learning model and one or more propagation delays from the one or more loudspeakers to the listening area. The method further comprises estimating one or more incidence angles of the one or more loudspeakers relative to the listening area based on the one or more propagation delays. The method further comprises applying spatial perception correction to audio reproduced by the one or more loudspeakers based on the one or more distances and the one or more incidence angles. The spatial perception correction comprises delay and gain compensation that corrects misplacement of any of the one or more loudspeakers relative to the listening area.

Abstract: One embodiment provides a computer-implemented method that includes acquiring, via at least one microphone, sound pressure data at one or more discrete frequencies obtained from a frequency response of a loudspeaker in a room. The sound pressure data is input into an artificial intelligence (AI) model that analyses and processes information, and that incorporates a relationship between the frequency response and at least one of an energy average (EA) in a listening area or a total sound power (TSP) produced by the loudspeaker. The AI model automatically estimates, without user interaction, the at least one of the EA in the listening area or the TSP produced by the loudspeaker.

Abstract: One embodiment provides a computer-implemented method that includes acquiring, via at least one microphone, sound pressure data at one or more discrete frequencies obtained from a frequency response of a loudspeaker in a room. The sound pressure data is input into an artificial intelligence (AI) model that analyses and processes information, and that incorporates a relationship between the frequency response and at least one of an energy average (EA) in a listening area or a total sound power (TSP) produced by the loudspeaker. The AI model automatically estimates, without user interaction, the at least one of the EA in the listening area or the TSP produced by the loudspeaker.

Abstract: One embodiment provides a method of personalized headphone equalization system for a headphone. The method comprises obtaining a measurement of sound pressure level at a microphone mounted in a near field of a headphone driver of the headphone and inside a cavity formed by the headphone and a user's ear. The method further comprises providing personalized equalization (EQ) of output reproduced via a headphone driver by performing EQ correction of the output based on the measurement of sound pressure level and a pre-determined target frequency response for the headphone, resulting in an equalized output that is adapted to individual characteristics of the user's ear.

Abstract: A method includes detecting, by a speaker system including a microphone, one or more boundaries within a proximity to the speaker system. The speaker system adjusts an output of the speaker system based on the one or more detected boundaries. A sound quality of the speaker system is improved based on adjusting the output.

Abstract: One embodiment provides a method of personalized headphone equalization system for a headphone. The method comprises obtaining a measurement of sound pressure level at a microphone mounted in a near field of a headphone driver of the headphone and inside a cavity formed by the headphone and a user's ear. The method further comprises providing personalized equalization (EQ) of output reproduced via a headphone driver by performing EQ correction of the output based on the measurement of sound pressure level and a pre-determined target frequency response for the headphone, resulting in an equalized output that is adapted to individual characteristics of the user's ear.

Abstract: A method includes detecting, by a speaker system including a microphone, one or more boundaries within a proximity to the speaker system. The speaker system adjusts an output of the speaker system based on the one or more detected boundaries. A sound quality of the speaker system is improved based on adjusting the output.

Abstract: One embodiment provides a method comprising determining an actual elevation of a sound source. The actual elevation is indicative of a first location at which the sound source is physically located relative to a first listening reference point. The method further comprises determining a desired elevation for a portion of an audio signal. The desired elevation is indicative of a second location at which the portion of the audio signal is perceived to be physically located relative to the first listening reference point. The desired elevation is different from the actual elevation. The method further comprises, based on the actual elevation, the desired elevation and the first listening reference point, modifying the audio signal, such that the portion of the audio signal is perceived to be physically located at the desired elevation during reproduction of the audio signal via the sound source.

Abstract: One embodiment provides a device comprising a speaker driver, a microphone configured to obtain a measurement of a near-field sound pressure of the speaker driver, and a controller. The controller is configured to determine a velocity of a diaphragm of the speaker driver, and automatically calibrate sound power levels of audio reproduced by the speaker driver based on the velocity and the measurement of the near-field sound pressure to automatically adjust the sound power levels to an acoustic environment of the device.

Abstract: One embodiment provides a method comprising determining an actual elevation of a sound source. The actual elevation is indicative of a first location at which the sound source is physically located relative to a first listening reference point. The method further comprises determining a desired elevation for a portion of an audio signal. The desired elevation is indicative of a second location at which the portion of the audio signal is perceived to be physically located relative to the first listening reference point. The desired elevation is different from the actual elevation. The method further comprises, based on the actual elevation, the desired elevation and the first listening reference point, modifying the audio signal, such that the portion of the audio signal is perceived to be physically located at the desired elevation during reproduction of the audio signal via the sound source.

Abstract: One embodiment provides a method comprising determining an actual elevation of a sound source. The actual elevation is indicative of a first location at which the sound source is physically located relative to a first listening reference point. The method further comprises determining a desired elevation for a portion of an audio signal. The desired elevation is indicative of a second location at which the portion of the audio signal is perceived to be physically located relative to the first listening reference point. The desired elevation is different from the actual elevation. The method further comprises, based on the actual elevation, the desired elevation and the first listening reference point, modifying the audio signal, such that the portion of the audio signal is perceived to be physically located at the desired elevation during reproduction of the audio signal via the sound source.

Abstract: One embodiment provides a sound apparatus comprising a plurality of driver units arranged linearly in an end-fire array, and for each driver unit, a corresponding digital filter for individual digital signal processing of signals received by the driver unit.