Abstract: In general, in one aspect, a hearing aid has an ANR circuit and an ear tip that acoustically occludes the ear. Such a hearing aid provides greater gain to sounds than would be stable in the same hearing aid with a vented ear tip. The ear tip and the ANR circuit in combination attenuate sounds reaching the ear canal through the hearing aid to a first level. The hearing aid detects sounds arriving at a microphone, amplifies those sounds, and provides the amplified sounds to the ear canal at a second level and later in time than the same sounds arrive at the ear canal through the ear tip. The first level is at least 14 dB greater than the second level, such that the amplified sounds do not interact with the passive sounds to result in spectral combing.

Abstract: In general, in one aspect, a hearing aid has an ANR circuit and an ear tip that acoustically occludes the ear. Such a hearing aid provides greater gain to sounds than would be stable in the same hearing aid with a vented ear tip. The ear tip and the ANR circuit in combination attenuate sounds reaching the ear canal through the hearing aid to a first level. The hearing aid detects sounds arriving at a microphone, amplifies those sounds, and provides the amplified sounds to the ear canal at a second level and later in time than the same sounds arrive at the ear canal through the ear tip. The first level is at least 14 dB greater than the second level, such that the amplified sounds do not interact with the passive sounds to result in spectral combing.

Abstract: Various implementations include audio devices and methods for noise reduction control in wearable audio devices and/or vehicle audio systems. Certain implementations include a method of controlling a noise cancelation (NC) setting at a vehicle audio system and an active noise reduction (ANR) setting at a non-occluding wearable audio device, the method comprising: adjusting at least one of the NC setting at the vehicle audio system or the ANR setting at the non-occluding wearable audio device in response to detecting the presence of the non-occluding wearable audio device in the vehicle.

Abstract: Various implementations include audio devices and methods for noise reduction control in wearable audio devices and/or vehicle audio systems. Certain implementations include a non-occluding wearable audio device having: at least one electro-acoustic transducer; at least one microphone; and a control system coupled with the at least one electro-acoustic transducer and the at least one microphone, the control system programmed to: adjust an active noise reduction (ANR) setting for audio output to the at least one electro-acoustic transducer in response to detecting use of the non-occluding wearable audio device in a vehicle.

Abstract: Various implementations include audio devices and methods for noise reduction control in wearable audio devices and/or vehicle audio systems. Certain implementations include a non-occluding wearable audio device having: at least one electro-acoustic transducer; at least one microphone; and a control system coupled with the at least one electro-acoustic transducer and the at least one microphone, the control system programmed to: adjust an active noise reduction (ANR) setting for audio output to the at least one electro-acoustic transducer in response to detecting use of the non-occluding wearable audio device in a vehicle.

Abstract: Various implementations include systems for processing audio signals. In particular implementations, a system for processing audio signals includes: an accessory device that includes a first processor for running a machine learning model on an input signal, where the machine learning model includes a classifier configured to generate metadata associated with the input signal; and a wearable audio device configured for wireless communication with the accessory device, the wearable audio device including a second processor that utilizes the metadata from the accessory device to process a source audio signal and output a processed audio signal.

Abstract: Various implementations include conversation assistance audio devices with settings that are adjustable based upon user feedback. In some cases, a computer-implemented method of personalizing a conversation assistance audio device includes: receiving a command from a user for assistance with audio settings in the conversation assistance audio device; applying a baseline set of audio settings to the conversation assistance audio device in response to receiving the user command for assistance; receiving a user command to change the baseline set of audio settings; and applying a modified set of audio settings to the conversation assistance audio device in response to receiving the user command to change the baseline set of audio settings, wherein the modified set of audio settings are applied based upon usage of the conversation assistance audio device and a population model of usage of similar conversation assistance audio devices.

Abstract: A headset includes an acoustic structure, a first microphone located outside the acoustic structure, a second microphone located inside the acoustic structure, and an output driver configured to receive an antinoise signal based on a combination of input from the first and second microphones. A voice signal of a user of the headset is generated using input from the first and second microphones. The first microphone could be a feed-forward microphone that provides input to a feed-forward filter to produce a filtered feed-forward signal for producing the antinoise signal. The second microphone could be a feedback microphone that provides input to a feedback filter to produce a filtered feedback signal for producing the antinoise signal.

Abstract: Various implementations include systems for processing audio signals. In particular implementations, a process includes receiving an audio signal, wherein the audio signal includes a speech component of the user and a noise component; filtering the audio signal with a self-speech filter that utilizes an intrinsic user vector to filter out the speech component, wherein the intrinsic user vector is determined based on a voice input of the user; and outputting a filtered audio signal in which the speech component of the user has been substantially removed from the audio signal.

Abstract: A noise cancelling headset includes an earpiece, the earpiece including a feedback microphone, a feed-forward microphone, and an output driver. A first feedback filter receives an input from at least the first feedback microphone and produces a first filtered feedback signal. A first feed-forward filter receives an input from at least the first feed-forward microphone and produces a first filtered feed-forward signal. A first summer combines the first filtered feedback signal and the first filtered feed-forward signal and produces a first output signal. An output interface provides the first output signal as an output from the headset.

Abstract: Various implementations include systems for processing audio signals. In particular implementations, a system includes at least one microphone configured to capture acoustic signals; a wearable hearing assist device configured to amplify captured acoustic signals from the at least one microphone and output amplified audio signals to a transducer; a voice activity detector (VAD) configured to detect voice signals of a user from the captured acoustic signals; and a voice suppression system configured to suppress the voice signals of the user from the amplified audio signals being output to the transducer.

Abstract: In general, in one aspect, a hearing aid has an ANR circuit and an ear tip that acoustically occludes the ear. Such a hearing aid provides greater gain to sounds than would be stable in the same hearing aid with a vented ear tip. The ear tip and the ANR circuit in combination attenuate sounds reaching the ear canal through the hearing aid to a first level. The hearing aid detects sounds arriving at a microphone, amplifies those sounds, and provides the amplified sounds to the ear canal at a second level and later in time than the same sounds arrive at the ear canal through the ear tip. The first level is at least 14 dB greater than the second level, such that the amplified sounds do not interact with the passive sounds to result in spectral combing.

Abstract: In general, in one aspect, a hearing aid has an ANR circuit and an ear tip that acoustically occludes the ear. Such a hearing aid provides greater gain to sounds than would be stable in the same hearing aid with a vented ear tip. The ear tip and the ANR circuit in combination attenuate sounds reaching the ear canal through the hearing aid to a first level. The hearing aid detects sounds arriving at a microphone, amplifies those sounds, and provides the amplified sounds to the ear canal at a second level and later in time than the same sounds arrive at the ear canal through the ear tip. The first level is at least 14 dB greater than the second level, such that the amplified sounds do not interact with the passive sounds to result in spectral combing.

Abstract: Various implementations include systems for processing audio signals. In particular implementations, a process includes receiving an audio signal, wherein the audio signal includes a speech component of the user and a noise component; filtering the audio signal with a self-speech filter that utilizes an intrinsic user vector to filter out the speech component, wherein the intrinsic user vector is determined based on a voice input of the user; and outputting a filtered audio signal in which the speech component of the user has been substantially removed from the audio signal.

Abstract: Various implementations include systems for processing audio signals. In particular implementations, a system for processing audio signals includes: an accessory device that includes a first processor for running a machine learning model on an input signal, where the machine learning model includes a classifier configured to generate metadata associated with the input signal; and a wearable audio device configured for wireless communication with the accessory device, the wearable audio device including a second processor that utilizes the metadata from the accessory device to process a source audio signal and output a processed audio signal.

Abstract: Various implementations include systems for processing audio signals. In particular implementations, a system for processing audio signals includes: a wearable audio device having a transducer and a communication system; and an accessory device configured to wirelessly communicate with the wearable audio device, the accessory device having a processor configured to process a source audio signal according to a method that includes: source separating the source audio signal; and providing a source separated audio signal to the wearable audio device for transduction.

Abstract: Various implementations include systems for processing audio signals. In particular implementations, a system includes at least one microphone configured to capture acoustic signals; a wearable hearing assist device configured to amplify captured acoustic signals from the at least one microphone and output amplified audio signals to a transducer; a voice activity detector (VAD) configured to detect voice signals of a user from the captured acoustic signals; and a voice suppression system configured to suppress the voice signals of the user from the amplified audio signals being output to the transducer.

Abstract: Various implementations include systems for processing audio signals. In particular implementations, a system for processing audio signals includes: a wearable audio device having a transducer and a communication system; and an accessory device configured to wirelessly communicate with the wearable audio device, the accessory device having a processor configured to process a source audio signal according to a method that includes: source separating the source audio signal; and providing a source separated audio signal to the wearable audio device for transduction.

Abstract: Various implementations include control mechanisms for conversation assistance audio devices. In some cases, an interface with a representation of the conversation assistance audio device in space is used to control audio functions in the device. In other cases, directionality of the device is controlled based upon the user's visual focus direction. In additional cases, the operating mode of the device is adjustable based upon the signature of a nearby acoustic signal.

Abstract: A noise cancelling headset includes an earpiece, the earpiece including a feedback microphone, a feed-forward microphone, and an output driver. A first feedback filter receives an input from at least the first feedback microphone and produces a first filtered feedback signal. A first feed-forward filter receives an input from at least the first feed-forward microphone and produces a first filtered feed-forward signal. A first summer combines the first filtered feedback signal and the first filtered feed-forward signal and produces a first output signal. An output interface provides the first output signal as an output from the headset.