Neural network-based parameter estimation of loudspeakers
AssigneeHarman International Industries, Incorporated
InventorsAjay Iyer, Meenakshi Barjatia
Life of this patent
Estimating the term…
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.
Claims20
One or more non-transitory computer-readable storage media including instructions that, when executed by one or more processors, configure the one or more processors to estimate a set of parameter values for a lumped parameter model (LPM) of a loudspeaker, by performing steps of:
- determining, via a neural network model, a first set of parameter values for the LPM of the loudspeaker from an audio input signal and a first measured response of a loudspeaker that corresponds to the audio input signal;
- generating, via the LPM, a first LPM response from the audio input signal and the first set of parameter values;
- comparing the first LPM response to the first measured response of the loudspeaker to determine a first error value;
- and
- generating, via the neural network model, a second set of parameter values for the LPM of the loudspeaker based on the first error value.
A method for estimating a set of parameter values for a lumped parameter model (LPM) of a loudspeaker, the method comprising:
- determining, via a neural network model, a first set of parameter values for the LPM of the loudspeaker from an audio input signal and a first measured response of a loudspeaker that corresponds to the audio input signal;
- generating, via the LPM, a first LPM response from the audio input signal and the first set of parameter values;
- comparing the first LPM response to the first measured response of the loudspeaker to determine a first error value;
- training the neural network model based on the first error value, the audio input signal, and at least one measured response of the loudspeaker;
- and
- generating, via the trained neural network model, a second set of parameter values for the LPM of the loudspeaker.
A system for estimating a set of parameter values for a lumped parameter model (LPM) of a loudspeaker, the system comprising:
- a memory storing a loudspeaker parameter estimation application;
- and
- one or more processors that are coupled to the memory and, when executing the loudspeaker parameter estimation application, are configured to:
- determine, via a neural network model, a first set of parameter values for the LPM of the loudspeaker from an audio input signal and a first measured response of a loudspeaker that corresponds to the audio input signal;
- generate, via the LPM, a first LPM response from the audio input signal and the first set of parameter values;
- train the neural network model based on the first LPM response and the first measured response of the loudspeaker;
- and
- generate, via the trained neural network model, a second set of parameter values for the LPM of the loudspeaker.
Dependencies are inferred from the claim text.