Abstract: Systems, methods, devices and non-transitory, computer-readable storage mediums are disclosed for location-tracking wireless devices. In an embodiment, a method performed by an electronic device comprises: playing, or initiating the playing of, a sound through a loudspeaker of an accessory device via a communication link. The sound is played at a specified frequency that utilizes a frequency response of the loudspeaker (or loudspeaker plus speaker enclosure). The sound is received through two or more microphones of the electronic device and filtered by one or more filters. The one or more filters are configured to pass the sound at or around the specified frequency and to reduce masking of the sound by ambient noise. The filtered sound is associated with direction data generated from sensor data provided by one or more inertial sensors of the electronic device. In another embodiment, the specified frequency is higher than the maximum human hearing range.

Abstract: A method performing automatic gain control (AGC) using an accelerometer in a headset starts with an accelerometer-based voice activity detector (VADa) generating a VADa output based on (i) acoustic signals received from at least one microphone included in a pair of earbuds and (ii) data output by at least one accelerometer that is included in the pair of earbuds. The at least one accelerometer detects vibration of the user's vocal chords. The headset includes the pair of earbuds. An AGC controller then performs automatic gain control (AGC) on the acoustic signals from the at least one microphone based on the VADa output. Other embodiments are also described.

Abstract: Digital signal processing techniques for automatically reducing audible noise from a sound recording that contains speech. A noise suppression system uses two types of noise estimators, including a more aggressive one and less aggressive one. Decisions are made on how to select or combine their outputs into a usable noise estimate in a different speech and noise conditions. A 2-channel noise estimator is described. Other embodiments are also described and claimed.

Abstract: An assistive apparatus, and a method of providing an accessibility switch output by the assistive apparatus, is described. The assistive apparatus may include an accelerometer to be worn in an ear canal of a user, and a display having a graphical user interface. The accelerometer may generate an input signal representing an input command made by the user, and more particularly, the generated input command may represent one or more hums transmitted from vocal cords of the user to the accelerometer in the ear canal via bone conduction. The assistive apparatus may provide an accessibility switch output in response to the input signals representing the input command. For example, the accessibility switch output may cause a selection of a user interface element of the graphical user interface. Other embodiments are also described and claimed.

Abstract: Method of improving voice quality using a wireless headset with untethered earbuds starts by receiving first acoustic signal from first microphone included in first untethered earbud and receiving second acoustic signal from second microphone included in second untethered earbud. First inertial sensor output is received from first inertial sensor included in first earbud and second inertial sensor output is received from second inertial sensor included in second earbud. First earbud processes first noise/wind level captured by first microphone, first acoustic signal and first inertial sensor output and second earbud processes second noise/wind level captured by second microphone, second acoustic signal, and second inertial sensor output. First and second noise/wind levels and first and second inertial sensor outputs are communicated between the earbuds. First earbud transmits first acoustic signal and first inertial sensor output when first noise and wind level is lower than second noise/wind level.

Abstract: Method for improving noise suppression for ASR starts with a microphone receiving an audio signal including speech signal and noise signal. In each frame for frequency band of audio signal, a noise estimator detects ambient noise level and generates noise estimate value based on estimated ambient noise level, variable noise suppression target controller generates suppression target value using noise estimate value and logistic function, a gain value calculator generates a gain value based on suppression target value and noise estimate value, and combiner enhances the audio signal by the gain value to generate a clean audio signal in each frame for all frequency bands. Logistic function models desired noise suppression level that varies based on ambient noise level. Variable level of noise suppression includes low attenuation for low noise levels and progressively higher attenuation for higher noise level. Other embodiments are also described.

Abstract: An audio system has a housing in which are integrated a number of microphones. A programmed processor accesses the microphone signals and produces a number of acoustic pick up beams based groups of microphones, an estimation of voice activity and an estimation of noise characteristics on each beam. Two or more beams including a voice beam that is used to pick up a desired voice and a noise beam that is used to provide information to estimate ambient noise are adaptively selected from among the plurality of beams, based on thresholds for voice separation and thresholds for noise-matching. Other embodiments are also described and claimed.

Abstract: A method of performing automatic speech recognition (ASR) using end-pointing markers generated using accelerometer-based voice activity detector starts with a voice activity detector (VAD) generating an accelerometer VAD output (VADa) based on data output by at least one accelerometer that is included in at least one earbud. The at least one accelerometer to detect vibration of the user's vocal chords. A voice processor detects a speech signal based on acoustic signals from at least one microphone. An end-pointer generates the end-pointing markers based on the VADa output and an ASR engine performs ASR on the speech signal based on the end-pointing markers. Other embodiments are also described.

Abstract: A method performing automatic gain control (AGC) using an accelerometer in a headset starts with an accelerometer-based voice activity detector (VADa) generating a VADa output based on (i) acoustic signals received from at least one microphone included in a pair of earbuds and (ii) data output by at least one accelerometer that is included in the pair of earbuds. The at least one accelerometer detects vibration of the user's vocal chords. The headset includes the pair of earbuds. An AGC controller then performs automatic gain control (AGC) on the acoustic signals from the at least one microphone based on the VADa output. Other embodiments are also described.

Abstract: An electronic device that can be worn by a user can include a processing unit and one or more sensors operatively connected to the processing unit. The processing unit can be adapted to determine an installation position of the electronic device based on one or more signals received from at least one sensor.

Abstract: Method of improving voice quality using a wireless headset with untethered earbuds starts by receiving first acoustic signal from first microphone included in first untethered earbud and receiving second acoustic signal from second microphone included in second untethered earbud. First inertial sensor output is received from first inertial sensor included in first earbud and second inertial sensor output is received from second inertial sensor included in second earbud. First earbud processes first noise/wind level captured by first microphone, first acoustic signal and first inertial sensor output and second earbud processes second noise/wind level captured by second microphone, second acoustic signal, and second inertial sensor output. First and second noise/wind levels and first and second inertial sensor outputs are communicated between the earbuds. First earbud transmits first acoustic signal and first inertial sensor output when first noise and wind level is lower than second noise/wind level.

Abstract: A wearable device that attaches to a body part of a user via an attachment member operates in at least a connected and a disconnected state. One or more sensors located in the wearable device and/or the attachment member detect the user's body part when present. Such detection may only be performed when the attachment member is in a connected configuration and may be used to switch the wearable device between the connected and disconnected states. In this way, the wearable device operates in the connected state when worn by a user and in the disconnected state when not worn by the user.

Abstract: Method of improving voice quality using a wireless headset with untethered earbuds starts by receiving first acoustic signal from first microphone included in first untethered earbud and receiving second acoustic signal from second microphone included in second untethered earbud. First inertial sensor output is received from first inertial sensor included in first earbud and second inertial sensor output is received from second inertial sensor included in second earbud. First earbud processes first noise/wind level captured by first microphone, first acoustic signal and first inertial sensor output and second earbud processes second noise/wind level captured by second microphone, second acoustic signal, and second inertial sensor output. First and second noise/wind levels and first and second inertial sensor outputs are communicated between the earbuds. First earbud transmits first acoustic signal and first inertial sensor output when first noise and wind level is lower than second noise/wind level.

Abstract: Embodiments of the invention determine whether speaker earbuds of a headset are positioned in a user's ears. The headset may be a “Y” shaped headset with two earbuds having speakers and a plug for insertion into a jack of the audio device. Multiple microphones are located on wired lengths to the earbuds and a common wire between the lengths and the plug, to receive speech from the user's mouth. Each earbud may have a front and rear microphone, and an accelerometer. Embodiments can detect user speech vibrations at one or more of the microphones, and in the accelerometers in the earbuds. Based on these detections, it can be determined whether one or both of the earbuds are in user's ears. To provide more accurate beamforming, when only one of the earbuds is in the user's ears, only the microphones leading to that earbud are selected for beamforming input.

Abstract: An electronic device that can be worn on a limb of a user can include a processing device and one or more position sensing devices operatively connected to the processing device. The processing device can be adapted to determine which limb of the user is wearing the electronic device based on one or more signals received from at least one position sensing device.

Abstract: Digital signal processing for microphone partial occlusion detection is described. In one embodiment, an electronic system for audio noise processing and for noise reduction, using a plurality of microphones, includes a first noise estimator to process a first audio signal from a first one of the microphones, and generate a first noise estimate. The electronic system also includes a second noise estimator to process the first audio signal, and a second audio signal from a second one of the microphones, in parallel with the first noise estimator, and generate a second noise estimate. A microphone partial occlusion detector determines a low frequency band separation of the first and second audio signals and a high frequency band separation of the first and second audio signals to generate a microphone partial occlusion function that indicates whether one of the microphones is partially occluded.

Abstract: A method of detecting a user's voice activity in a headset with a microphone array is described herein. The method starts with a voice activity detector (VAD) generating a VAD output based on acoustic signals received from microphones included in a pair of earbuds and the microphone array included on a headset wire and data output by an accelerometer that is included in the pair of earbuds. A noise suppressor may then receive the acoustic signals from the microphone array and the VAD output and suppress the noise included in the acoustic signals received from the microphone array based on the VAD output. The method may also include steering one or more beamformers based on the VAD output. Other embodiments are also described.

Abstract: A wearable device configured to acquire and process electrocardiographic measurements, detect lead inversion and correct the acquired measurements for lead inversion is provided. In one example, the wearable device can detect lead inversion by first assessing whether the P-wave of a given electrocardiographic measurement has a negative amplitude, and if the P-wave is found to be negative, the device can determine if the magnitude of the R-wave is smaller than the maximum of the magnitudes of the S-wave and the Q-wave. In another example, the device can be put through an enrollment procedure in which electrocardiographic measurements are taken with the device being worn at known locations on the body. Once the enrollment procedure is completed, when the device is being used, any electrocardiographic results obtained can be compared against the measurements taken during the enrollment phase, and the location of the device on the body can be determined.

Abstract: A method of improving voice quality in a mobile device starts by receiving acoustic signals from microphones included in earbuds and the microphone array included on a headset wire. The headset may include the pair of earbuds and the headset wire. An output from an accelerometer that is included in the pair of earbuds is then received. The accelerometer may detect vibration of the user's vocal chords filtered by the vocal tract based on vibrations in bones and tissue of the user's head. A spectral mixer included in the mobile device may then perform spectral mixing of the scaled output from the accelerometer with the acoustic signals from the microphone array to generate a mixed signal. Performing spectral mixing includes scaling the output from the inertial sensor by a scaling factor based on a power ratio between the acoustic signals from the microphone array and the output from the inertial sensor. Other embodiments are also described.

Abstract: Method for improving noise suppression for ASR starts with a microphone receiving an audio signal including speech signal and noise signal. In each frame for frequency band of audio signal, a noise estimator detects ambient noise level and generates noise estimate value based on estimated ambient noise level, variable noise suppression target controller generates suppression target value using noise estimate value and logistic function, a gain value calculator generates a gain value based on suppression target value and noise estimate value, and combiner enhances the audio signal by the gain value to generate a clean audio signal in each frame for all frequency bands. Logistic function models desired noise suppression level that varies based on ambient noise level. Variable level of noise suppression includes low attenuation for low noise levels and progressively higher attenuation for higher noise level. Other embodiments are also described.