Harman International Industries, Inc.

Owlet Baby Care, Inc.

University of Utah Research Foundation

Ajay Sundaram Iyer

Richard Allen Kreifeldt

Douglas J Button

Jeffrey L Hutchings

James M Kirsch

V John Mathews

Alison Jeanette Carlile

Shreyas Srikanth Payal

Russell H Lambert

Branden Sheffield

Zack Bomsta

Meenakshi Barjatia

Sean Kerman

Kurt Gibbons Workman

Daniela Natalia Turner

Ali Carlile

Paul Allen

Ethan Lawrence

Ryan Workman

Bruce Olney

Daniela Turner

A system for monitoring fetal health data and mother health data comprises a belly-covering garment that is configured to at least partially cover a belly and to hold one or more sensor modules directly adjacent to the belly. One or more sensor modules disposed within the belly-covering garment. The one or more sensor modules comprise a pulse-oximeter sensor that gathers pulse oximetry data from the mother through contact with the belly. The one or more sensor modules also comprise an accelerometer sensor that gathers movement data from the mother. Additionally, the one or more sensor modules comprise a fetal sensor that gathers health data from a fetus within the belly.

Fetal health data monitoring

A first digital signal processor (DSP) associated with a first user outputs audio to the first user via first headphones, and captures speech from the first user via a first microphone. Similarly, a second DSP associated with a second user outputs audio to the second user via second headphones, and captures speech from the second user via a second microphone. The first DSP is coupled to the second DSP in order to allow the first and second users to share music and communicate with one another. The first user may speak into the first microphone, and the first and second DSPs may then interoperate to output that speech to the second user without substantially disrupting audio output to the second user. Each of the first and second users may also select between first and second audio sources that may be coupled to the first and second DSPs, respectively.

Techniques for sharing stereo sound between multiple users

An abdominal electrocardiogram processing system for determining a fetal heart rate of a fetus in a pregnant woman obtains a combined electrocardiogram measurement of a maternal heart rate and a fetal heart rate. The system then transforms the combined electrocardiogram measurement into a wavelet domain to create a combined electrocardiogram measurement wavelet transform. The system can then remove the maternal heart rate from the combined electrocardiogram measurement wavelet transform. The system then identifies a fetal heart rate from the compensated combined electrocardiogram measurement wavelet transform.

Fetal heart rate extraction within a processor constrained environment

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.

Neural network-based parameter estimation of loudspeakers

A technique for controlling a loudspeaker system with an artificial neural network includes filtering, with a deconvolution filter, a measured system response of a loudspeaker and a reverberant environment in which the loudspeaker is disposed to generate a filtered response, wherein the measured system response corresponds to an audio input signal applied to the loudspeaker while the loudspeaker is disposed in the reverberant environment. The techniques further include generating, via a neural network model, an initial neural network output based on the audio input signal, comparing the initial neural network output to the filtered response to determine an error value, and generating, via the neural network model, an updated neural network output based on the audio input signal and the error value.

Neural network-based loudspeaker modeling with a deconvolution filter

In an audio system, an audio signal is preprocessed to provide an input signal to a fast detector and a slow detector, the input signal comprising alert signals and ambient sounds. The slow detector determines the ambient sound level of the input signal which is output to an alert signal detector. The alert signal detector uses the ambient sound level to compute an adaptive threshold level using an adaptive threshold function. The fast detector determines the envelope level of the input signal which is output to the alert signal detector. The alert signal detector compares the envelope level to the adaptive threshold level to determine if an alert signal is present in the input signal. The adaptive threshold level varies depending on the ambient sound level of the input signal and the alert signal detection of the audio system automatically adapts to changing acoustic environments having different ambient sound levels.

Approach for detecting alert signals in changing environments

Fabric electrode assembly

An audio processing system for a listening device includes an input device, a voice activity detector and a ratio-based attenuator. The input device is configured to receive a first audio signal emanating from an environment and including a signal of interest. The voice activity detector is configured to generate a control signal in response to the first audio signal. The ratio-based attenuator is configured to receive the control signal and determine whether the signal level of the first audio signal exceeds the signal level of an audio signal received from an audio playback device by at least a target difference. If so, then the audio level of the playback audio signal is maintained. Otherwise, the audio level of the playback audio signal is adjusted, where, at the adjusted value, the first signal level exceeds the playback signal level by at least the target difference.

Approach for partially preserving music in the presence of intelligible speech

An audio system is described that corrects for linear and nonlinear distortions. The system can include a physical loudspeaker system responsive to an audio input signal, an adaptive circuit, e.g., with a recurrent neural network, to correct for non-linear distortions from the loudspeaker.

Adaptive correction of loudspeaker using recurrent neural network

Digital filters for processing an input audio signal for extending the audio capabilities and reducing distortion of a loudspeaker. Such extension may include a general sound pressure level (SPL) extension or a more targeted low frequency (LF) extension. This may be accomplished by modifying an original frequency response of the loudspeaker to achieve a particular extension, and applying a digital linear filter based on the modified frequency response to the audio signal. A nonlinear digital filter may also be applied to the audio signal reduce nonlinear distortions of the loudspeaker. The nonlinear digital filter may be based on an inverse of an electro-mechanical model of the loudspeaker. In this manner, a loudspeaker may be driven close to its maximum theoretical power capability without increasing distortion in the loudspeaker output.

Digital signal processor for audio extensions and correction of nonlinear distortions in loudspeakers

A dynamic processor for compressing an incoming audio signal is provided. The processor includes an adaptive detector, an adaptive module, and an amplifier. The adaptive detector includes a first adaptive filter and is configured to apply a transfer function to the incoming audio signal to generate a detector output signal. The adaptive module includes a second adaptive filter and is configured to generate a control signal based on the detector output signal. The amplifier is configured to receive the control signal from the adaptive module and to generate a compressed audio signal based on the control signal.

Adaptive detector and auto mode for dynamics processor

A corrector is configured to transform audio signals to compensate for unwanted distortion characteristics of a loudspeaker. A tuning filter is configured to transform audio signals to incorporate desired distortion characteristics associated with a target loudspeaker. By chaining together the tuning filter and the corrector, an audio signal can be modified so that the loudspeaker, when outputting the audio signal, has response characteristics of the target loudspeaker.

Techniques for tuning the distortion response of a loudspeaker

In one embodiment, a pre-correcting engine generates a pre-corrected signal that may be used to mitigate air path distortions in sounds generated by loudspeaker systems that include loudspeakers coupled to waveguides. In operation, the pre-correcting engine virtually propagates a target signal in a reverse direction from the output of the waveguide to the output of a driver. Notably, the pre-correcting engine implements a propagation distortion compensation model that, when applied to the target signal, corrects for the effects of air path distortions on the target signal. The pre-correcting engine then transmits the pre-corrected signal to the driver. As the driver drives the waveguide based on the pre-corrected signal, effects of the pre-corrected distortions negate effects of air path distortions and the loudspeaker system generates high-fidelity sounds. By contrast, conventional loudspeaker systems that drive the waveguide based on the target signal typically generate lower fidelity sounds that include air path distortions.

Growing community of inventors

Sandy, UT, United States of America

Ajay Sundaram Iyer