Abstract: A microphone assembly includes an acoustic sensor and a voice activity detector on an integrated circuit coupled to an external-device interface. The acoustic sensor produces an electrical signal representative of acoustic energy detected by the sensor. A filter bank separates data representative of the acoustic energy into a plurality of frequency bands. A power tracker obtains a power estimate for at least one band, including a first estimate based on relatively fast changes in a power metric of the data and a second estimate based on relatively slow changes in a power metric of the data. The presence of voice activity in the electrical signal is based upon the power estimate.

Abstract: Systems and methods for providing ambient awareness are provided. An example method includes receiving an acoustic signal representing at least one captured ambient sound and determining that at least one triggering event has occurred based at least on the acoustic signal, a user profile, and a user context. In response to the determination, the method proceeds to modify, based on the at least one triggering event, the acoustic signal which represents the at least one captured ambient sound. The modified acoustic signal is provided to at least one ear canal of a user. In an exemplary embodiment, ambient sounds are selectively passed through automatically to a user based on certain triggering events, allowing a user to be able to hear sounds outside of headset while the user is wearing the headset. The triggering events may be selected by the user, for example, using a smartphone application.

Abstract: Approaches are provided for an apparatus that includes an input buffer, an analog-to-digital converter coupled to the input buffer, a decompress module coupled to the analog to digital converter, and a gain control module coupled to the input buffer and the decompress module. The input buffer has a first adjustable gain and operating in the analog domain. The analog-to-digital converter converts the input analog data received from the input buffer into digital data. The decompress module operates in the digital domain, and is configured to decompress the digital data received from the analog-to-digital converter. The decompress module has a second adjustable gain and produces an output digital signal. The gain control module determines when to compensate for changes in characteristics the input analog data by selectively controlling the first gain of the input buffer in the analog domain and the second gain of the decompress module in the digital domain.

Abstract: Systems and methods for multiplying a sparse matrix by a vector using a single instruction multiple data (SIMD) architecture are provided. An example method includes sorting rows of the sparse matrix by a number of non-zero elements in the rows to generate sorted rows. The sorted rows are split to generate groups of the sorted rows. The number of rows in each group of the sorted rows is equal to the number of rows updated in parallel. The method allows for packing the sorted rows in each of the groups to generate packed rows. Each of the packed rows within the same group has the same length. Per clock cycle, C elements of the packed rows and data for selecting elements of the vector are provided to computational units in the SIMD architecture, where C is the number of computational units.

Abstract: Systems and methods for controlling adaptivity of noise cancellation are presented. One or more audio signals are received by one or more corresponding microphones. The one or more signals may be decomposed into frequency sub-bands. Noise cancellation consistent with identified adaptation constraints is performed on the one or more audio signals. The one or more audio signals may then be reconstructed from the frequency sub-bands and outputted via an output device.

Abstract: An analog signal is received from an acoustic transducer. The analog signal is converted into digital data. A determination is made as to whether acoustic activity exists within the digital data. The digital data is stored in a temporary memory storage device and a count is maintained of an amount of digital data in the temporary memory storage device. When the count exceeds a predetermined threshold, at least some of the digital data is transmitted from the temporary memory storage device to a processor.

Abstract: Systems and apparatuses for a MEMS device. The MEMS device includes a diaphragm and a backplate spaced a distance from the diaphragm forming an air gap therebetween. The backplate includes a first surface facing toward the diaphragm and an opposing second surface facing away from the diaphragm. The first surface and the opposing second surface of the backplate cooperatively define a plurality of through-holes that extend through the backplate allowing air from the air gap to flow therethrough. Each of the plurality of through-holes include a first aperture disposed along the first surface, a second aperture disposed along the opposing second surface, and a sidewall extending between the first surface and the opposing second surface. The first aperture and the second aperture have different dimensions.

Abstract: Systems and methods for stereo separation and directional suppression are provided. An example method includes receiving a first audio signal, representing sound captured by a first microphone associated with a first location, and a second audio signal, representing sound captured by a second microphone associated with a second location. The microphones comprise omni-directional microphones. The distance between the first and second microphones is limited by the size of a mobile device. A first channel signal of a stereo signal is generated by forming, based on the first and second audio signals, a first beam at the first location. A second channel signal of the stereo signal is generated by forming, based on the first and second audio signals, a second beam at the second location. First and second directions, associated respectively with the first and second beams, are fixed relative to a line between the first and second locations.

Abstract: Methods and systems for providing consistency in noise reduction during speech and non-speech periods are provided. First and second signals are received. The first signal includes at least a voice component. The second signal includes at least the voice component modified by human tissue of a user. First and second weights may be assigned per subband to the first and second signals, respectively. The first and second signals are processed to obtain respective first and second full-band power estimates. During periods when the user's speech is not present, the first weight and the second weight are adjusted based at least partially on the first full-band power estimate and the second full-band power estimate. The first and second signals are blended based on the adjusted weights to generate an enhanced voice signal. The second signal may be aligned with the first signal prior to the blending.

Abstract: A processing apparatus including one or more processors and memory determines a first context of a first user at a first location in a physical space based on sensor measurements from one or more sensors of a set of one or more devices coupled to the first user and detects movement of the first user to a second location in the physical space based on sensor measurements from one or more sensors of the devices. The processing apparatus determines a second context of the first user at the second location based on sensor measurements from one or more sensors of the devices and generates, based on the first context, the second context, and the movement of the user from the first location to the second location, a first mapping of the physical space that includes information corresponding to a spatial relationship between the first context and the second context.

Abstract: A method of operating an acoustic system includes detecting an ultrasonic sound signal and pattern matching the received ultrasonic sound signal to determine when the received ultrasonic sound signal is a desired ultrasonic sound signal. The method includes sending a signal to at least one electronic component when the received ultrasonic sound signal is the desired ultrasonic sound signal. The method includes operating the microphone in a lower power state when the received ultrasonic sound signal is not the desired ultrasonic sound signal.

Abstract: Systems and methods for multi-sourced noise suppression are provided. An example system may receive streams of audio data including a voice signal and noise, the voice signal including a spoken word. The streams of audio data are provided by distributed audio devices. The system can assign weights to the audio streams based at least partially on quality of the audio streams. The weights of audio streams can be determined based on signal-to-noise ratios (SNRs). The system may further process, based on the weights, the audio stream to generate cleaned speech. Each audio device comprises microphone(s) and can be associated with the Internet of Things (IoT), such that the audio devices are Internet of Things devices. The processing can include noise suppression and reduction and echo cancellation. The cleaned speech can be provided to a remote device for further processing which may include Automatic Speech Recognition (ASR).

Abstract: An apparatus includes a microphone and a gasket. The microphone includes a base having an inner surface and an outer surface. The inner surface is generally parallel with the outer surface. The base has a port extending from the outer surface to the inner surface. The microphone includes a micro electro mechanical system (MEMS) transducer coupled to the inner surface of the base over the port. The microphone has a cover coupled to the base and the cover encloses the MEMS transducer. The gasket is coupled to the outer surface of the base and forms a channel. The channel has a first end and a second end. The first end communicates with the port of the microphone, and the second end of the channel is generally aligned with an edge of the base.

Abstract: A surface-mountable MEMS microphone comprising a MEMS microphone die and an application-specific integrated circuit (ASIC) mounted inside a surface-mountable package housing, and fully enclosed therein. The surface-mountable package is a single, self-contained housing that provides an electrical interface to external circuitry for the enclosed MEMS microphone die and the ASIC, and provides electrical, physical, and environmental protection for the MEMS microphone die and the ASIC. The surface-mountable package allows external acoustic energy to enter the package interior via one or more acoustic ports and impinge on the diaphragm of the MEMS microphone die. The cover of the surface-mountable package comprises an acoustic port with ingress protection to limit dust and particle intrusion. The ingress protection can be a formed member that is part of the cover of the surface-mountable package having various shapes, an internal shield, or a combination of both a formed member and internal shield.

Abstract: A microphone includes a microphone base that has a first surface and a second surface. The microphone also includes a microelectromechanical system (MEMS) device coupled to the first surface of the microphone base. The microphone also includes a cover coupled to the first surface of the microphone base, such that the cover divides the first surface into a covered portion where the cover encloses the MEMS device, and a non-covered portion extending away from the cover. The microphone also includes one or more pads on the uncovered portion of the first surface of the base. The microphone also includes a port extending through the base from the first surface to the second surface.

Abstract: Systems and methods for active noise reduction and occlusion reduction based on seal quality of an in-the-ear (ITE) module inserted into a user's ear canal are provided. An example method includes receiving one or more acoustic signals. Each of the acoustic signals represents at least one captured sound having at least one of a voice component and an unwanted noise. The voice component may include the user's own voice. A quality of a seal of an ear canal is determined based at least partially on the acoustic signals. If the quality of the seal exceeds a predetermined threshold value, an occlusion reduction is performed on the acoustic signals to improve the voice component. If the quality of the seal is below a predetermined threshold value, active noise reduction is performed on the acoustic signals to reduce the unwanted noise.

Abstract: Method and systems for modeling user possession of a mobile device for a user authentication framework are provided. The method includes analyzing sensor data representing information captured from sensor(s) associated with at least one of a plurality of devices, the plurality including the user's mobile device. The method allows for determining, based on the analyzed sensor data, a probability that the user maintains possession of the user's mobile device; and configuring the probability for use in determining whether to require authentication. The determination may include configuring a probabilistic model that includes a first state indicating that the user possesses the mobile device and a second state indicating that the user does not; classifying motions of the mobile device by types, the motions being determined based on the sensor data; and updating probabilities of the two states in response to determining that at least one of the motions has occurred.

Abstract: Systems and methods for performing personalized operations of a mobile device are provided. An example method includes determining a user-defined signature has been received. The user-defined signature can include a combination of an acoustic input and non-acoustic input. The method can further include performing, in response to the determination, operations of the mobile device, the operations being associated with the user-defined signature. Exemplary acoustic input includes a voice sound with at least one spoken keyword. The spoken keyword is used to identify the operations. Exemplary non-acoustic input includes motions of the mobile device detected by an accelerometer, a gyroscope, and a magnetometer. Exemplary motions include vibrations of the mobile device, tapping the mobile device, rotations of the mobile device, movements of the mobile device as to draw a figure in a space.

Abstract: A surface mount package for a micro-electro-mechanical system (MEMS) microphone die is disclosed. The surface mount package features a substrate with metal pads for surface mounting the package to a device's printed circuit board and for making electrical connections between the microphone package and the device's circuit board. The surface mount microphone package has a cover, and the MEMS microphone die is substrate-mounted and acoustically coupled to an acoustic port provided in the surface mount package. The substrate and the cover are joined together to form the MEMS microphone, and the substrate and cover cooperate to form an acoustic chamber for the substrate-mounted MEMS microphone die.

Abstract: An apparatus includes a microelectromechanical system (MEMS) device having a diaphragm and a back plate; a clipping circuit coupled to the MEMS device, wherein the clipping circuit is configured to clip an output signal of the MEMS device so that the maximum signal drawn by a buffer is substantially constant over a temperature range; and an integrated circuit coupled to the clipping circuit, the integrated circuit including the buffer.