Abstract: A technique for estimating a set of parameter values for a lumped parameter model of a loudspeaker. The technique includes determining, via a neural network model, a first set of parameter values for the LPM of the loudspeaker based on an audio input signal and a first measured response of a loudspeaker that corresponds to the audio input signal. The technique further includes generating a first LPM response based on the first set of parameter values and comparing the first LPM response to the first measured response of the loudspeaker to determine a first error value. The technique further includes generating, via the neural network model, a second set of parameter values for the LPM of the loudspeaker based on the first error value.

Abstract: An audio speaker system for a home theater including a number of microphones, a number of speakers, each speaker located at a different location in a room, and a processor electrically connected to the plurality of microphones and wirelessly connected to the plurality of speakers. The processor is configured to generate an audio signal to send to each speaker of the plurality of speakers, output audio from each speaker of the plurality of speakers based on the audio signal, receive the audio at each microphone from each speaker of the plurality of speakers, determine a location of each speaker relative to the plurality of microphones based on the received audio at each microphone, and assign an audio channel to each speaker based on the determined location.

Abstract: A personal assistant device configured to determine a location of the personal assistant device and apply settings specific to the location may include at least one speaker configured to emit a stimulus noise, at least one microphone configured to acquire a room sample based on the stimulus noise, the room sample including a sample room impulse response, and a memory configured to maintain a plurality of room profiles, each room profile including a room location, a stored room impulse response, and a room specific response. A processor may be configured to receive the room sample, compare the sample room impulse response with at least one of the stored room impulse responses, determine whether the sample room impulse response matches one of the stored room impulse responses, apply the room specific response associated with the room profile of the matched stored room impulse response.

Abstract: An audio speaker system for a home theater including a number of microphones, a number of speakers, each speaker located at a different location in a room, and a processor electrically connected to the plurality of microphones and wirelessly connected to the plurality of speakers. The processor is configured to generate an audio signal to send to each speaker of the plurality of speakers, output audio from each speaker of the plurality of speakers based on the audio signal, receive the audio at each microphone from each speaker of the plurality of speakers, determine a location of each speaker relative to the plurality of microphones based on the received audio at each microphone, and assign an audio channel to each speaker based on the determined location.

Abstract: An audio processor receives ambient audio input and performs time frequency analysis. A controller receives a first description of a first step of a project, generates a first sound signature according to the time frequency analysis of the ambient audio input during a timeframe corresponding to performance of the first step, adds the first step to a project script including the first description and the first signature for matching to future audio input to determine whether the first step is being performed, receives a second description of a second step of the project, generates a second sound signature based on the time frequency analysis of the ambient audio input during a timeframe corresponding to performance of the second step, and adds the second step to the project script including the second description and the second signature for matching to future audio input to determine whether the second step is performed.

Abstract: A personal assistant device configured to determine a location of the personal assistant device and apply settings specific to the location may include at least one speaker configured to emit a stimulus noise, at least one microphone configured to acquire a room sample based on the stimulus noise, the room sample including a sample room impulse response, and a memory configured to maintain a plurality of room profiles, each room profile including a room location, a stored room impulse response, and a room specific response. A processor may be configured to receive the room sample, compare the sample room impulse response with at least one of the stored room impulse responses, determine whether the sample room impulse response matches one of the stored room impulse responses, apply the room specific response associated with the room profile of the matched stored room impulse response.

Abstract: An audio processor receives ambient audio input and performs time frequency analysis. A controller receives a first description of a first step of a project, generates a first sound signature according to the time frequency analysis of the ambient audio input during a timeframe corresponding to performance of the first step, adds the first step to a project script including the first description and the first signature for matching to future audio input to determine whether the first step is being performed, receives a second description of a second step of the project, generates a second sound signature based on the time frequency analysis of the ambient audio input during a timeframe corresponding to performance of the second step, and adds the second step to the project script including the second description and the second signature for matching to future audio input to determine whether the second step is performed.

Abstract: A non-transitory storage maintains a project script including a sequence of steps, each step including a description of the step and a sound signature indicative of ambient sounds that occur during performance of the step. An audio processor is programmed to receive ambient audio input and perform a time frequency analysis of the ambient audio input. A controller is programmed to provide a description of a next step of the project script upon completion of a current step identified responsive to the time frequency analysis of the ambient audio input matching a sound signature corresponding to the next step of the project script.

Abstract: One or more embodiments set forth an audio presence detection system, with a memory that includes an acoustic presence detection application, and a processor that executes the acoustic presence detection application. The audio presence detection system receives a first input signal associated with a first speaker, and receives a second input signal associated with a first microphone. The audio presence detection system generates, via an adaptive filter, a first estimation signal based on at least the first input signal and an impulse response associated with a room related to the first speaker and the first microphone. The audio presence detection system computes a first error signal based on the second input signal and the first estimation signal. The audio presence detection system determines that an object is present within a space based on a magnitude associated with the first error signal relative to a first threshold level.

Abstract: One or more embodiments set forth an audio presence detection system, with a memory that includes an acoustic presence detection application, and a processor that executes the acoustic presence detection application. The audio presence detection system receives a first input signal associated with a first speaker, and receives a second input signal associated with a first microphone. The audio presence detection system generates, via an adaptive filter, a first estimation signal based on at least the first input signal and an impulse response associated with a room related to the first speaker and the first microphone. The audio presence detection system computes a first error signal based on the second input signal and the first estimation signal. The audio presence detection system determines that an object is present within a space based on a magnitude associated with the first error signal relative to a first threshold level.

Abstract: A technique for estimating a set of parameter values for a lumped parameter model of a loudspeaker. The technique includes determining, via a neural network model, a first set of parameter values for the LPM of the loudspeaker based on an audio input signal and a first measured response of a loudspeaker that corresponds to the audio input signal. The technique further includes generating a first LPM response based on the first set of parameter values and comparing the first LPM response to the first measured response of the loudspeaker to determine a first error value. The technique further includes generating, via the neural network model, a second set of parameter values for the LPM of the loudspeaker based on the first error value.