Abstract: An augmented reality (AR) device, such as AR glasses, may include a microphone array. The sensitivity of the microphone array can be directed to a target by beamforming, which includes combining the audio of each microphone of the array in a particular way based on a location of the target. The present disclosure describes systems and methods to determine the location of the target based on a gaze of a user and beamform the audio accordingly. This eye-tracked beamforming (i.e., foveated beamforming) can be used by AR applications to enhance sounds from a gaze direction and to suppress sounds from other directions. Additionally, the gaze information can be used to help visualize the results of an AR application, such as speech-to-text.

Abstract: A device with a microphone and a condensation collection apparatus to prevent migration of condensation to the microphone is provided. The device comprises a microphone; a board having an acoustic port therethrough, the microphone positioned to accept sound through the acoustic port; a moisture-resistant, acoustically transparent membrane over the acoustic port; an outer membrane that receives the sound for the microphone, the outer membrane being non-permeable to at least moisture; and a condensation collection apparatus between the outer membrane and the acoustically transparent membrane. The condensation collection apparatus comprises: an aperture through which the sound from the outer membrane passes; and one or more condensation collection features, at an outer-membrane facing side of the condensation collection apparatus, configured to: collect condensation that migrates from an inner side of the outer membrane; and prevent migration of the condensation, that is collected, through the aperture.

Abstract: A signal processing circuit includes an input buffer circuit and a direct-(DC) voltage detector circuit. The input buffer circuit is coupled to a pin. The pin is configured to receive an input signal. The DC voltage detector circuit is coupled to the pin and the input buffer circuit. The DC voltage detector circuit is configured to detect the input signal to generate a mode signal and generate a bias of the input buffer circuit according to the mode signal.

Abstract: A goods processing apparatus includes a controller including a program memory, a security module, a first communication interface that is configured to, in cooperation with the security module, securely communicate with a remote server, and an acoustic output device electrically connected with the controller and configured to output audio files or sound files. The security module and the first communication interface can be electrically connected with the controller. The program memory may store a program to control the acoustic output via the acoustic output device. The program can facilitate external commands being transmitted from the remote server, or from one or more other internet sources, to the controller. Via security measures, operational security of the goods processing apparatus is prevented from being negatively affected, or harmful code is prevented from being transmitted to controller.

Abstract: The light-emitting device includes a main body, a light-emitting module, and a press part located on the main body and configured to control on or off of the light-emitting module. The main body is provided with an accommodation space having the light-emitting module arranged therein. The main body includes a light guide, and light emitted by the light-emitting module is emitted outside of the main body through the light guide. The light guide includes a light exit surface and a light entrance surface. The light entrance surface is located on the circumferential inner sidewall of the accommodation space, and the light exit surface is located on the circumferential outer sidewall of the main body, and light emitted by the light-emitting module is emitted outside along a side of the main body.

Abstract: A process for preserving chain of custody for digital evidence captured at a portable device. The portable device transmits a request to upload the digital evidence to the cloud server via an intermediary storage device. The request includes digitally signed evidence metadata with data integrity code and authentication credentials. The portable device receives a response indicating approval to upload the digital evidence to the cloud server via the intermediary storage device. The portable device transmits the digital evidence to the intermediary storage device for uploading to the cloud server, and further transmits a request for approval to delete the digital evidence from the portable device. The portable device deletes the digital evidence only after receiving a response from the cloud server indicating an approval to delete the digital evidence from the portable device.

Abstract: An acoustic apparatus according to each of the embodiments includes a reception unit, an operation unit, and a control unit. The reception unit is configured to receive a packet to which voice data and a signal for azimuth estimate are added. The operation unit is configured to operate a signal angle of the packet by using the signal for azimuth estimate. The control unit is configured to control information related to a sound image of the voice data according to the signal angle.

Abstract: A vehicle system includes a controller that is configured to (a) store a plurality of passenger profiles regarding passengers of a vehicle where each of the plurality of passenger profiles include pre-stored identifying characteristics of a respective passenger associated therewith, (b) acquire passenger identifying data regarding a present passenger in the vehicle, (c) identify a respective passenger profile associated with the present passenger from the plurality of passenger profiles based on the passenger identifying data corresponding with the pre-stored identifying characteristics of the respective passenger profile, (d) control a speaker positioned within the vehicle based at least in part on the respective passenger profile to emit noise-canceling sound waves to generate a noise suppression zone to suppress sound waves perceived by the present passenger, (e) acquire movement data regarding movement of the present passenger within the vehicle, and (f) dynamically adjust the noise suppression zone based

Abstract: A bipolar output charge pump circuit having a network of switching paths for selectively connecting an input node and a reference node for connection to an input voltage, a first pair of output nodes and a second pair of output nodes, and two pairs of flying capacitor nodes, and a controller for controlling the switching of the network of switching paths. The controller is operable to control the network of switching paths when in use with two flying capacitors connected to the two pairs of flying capacitor nodes, to provide a first bipolar output voltage at the first pair of output nodes and a second bipolar output voltage at the second pair of bipolar output nodes.

Abstract: Disclosed herein are example techniques to facilitate calibrating a portable playback device. An example implementation involves determining that a playback device is to perform an equalization calibration of the playback device and initiating the equalization calibration. Initiating the equalization calibration involves (i) outputting audio content, (ii) capturing audio data representing reflections of the audio content within an area in which the playback device is located, (iii) determining an acoustic response of the area in which the playback device is located, (iv) selecting a stored acoustic response from the acoustic response database that is most similar to the determined acoustic response of the area in which the playback device is located, and (v) applying to the audio content, via the playback device, a set of stored audio calibration settings associated with the selected stored acoustic area response.

Abstract: A signal processing apparatus that processes a plurality of audio signals obtained by acquiring a sound in a target area by performing sound acquisition by a plurality of sound acquisition units, comprising: a specification unit configured to specify a position of a sound source in the target area and positions and directivities of the plurality of sound acquisition units; and a selection unit configured to select, among the plurality of audio signals based on the sound acquisition by the plurality of sound acquisition units, an audio signal to be played back based on a degree of misalignment of the directivity of each of the plurality of sound acquisition units with respect to the specified position of the sound source.

Abstract: A method for determining an actual position of a microphone, comprising: sequentially emitting a first sound signal via a first speaker positioned and a second sound signal via a second speaker positioned; measuring a first elapsed time between the emission of the first sound signal and a detection of the first sound signal by the microphone, and a second elapsed time between the emission of the second sound signal and a detection of the second sound signal by the microphone; determining a first distance between the first speaker and the microphone using the first elapsed time, and a second distance between the second speaker and the microphone using the second elapsed time; determining the actual position of the microphone using the first and second distances and the positions of the first and second speaker; and outputting the actual position.

Abstract: The present application discloses a method and device for processing multimedia information, an electronic equipment, and a computer-readable storage medium. The method for processing multimedia information includes: detecting whether multimedia configuration parameters have changed during a process of recording multimedia information; and recording the multimedia information based on the changed multimedia configuration parameters when detecting that the multimedia configuration parameters have changed. According to the embodiments of the present application, multimedia configuration parameters of the special effects such as stickers, make-up, filters, and mixing can be added during the recording of multimedia information, which improves the user experience.

Abstract: In a general aspect, a discharge circuit for discharging a voltage from a USB connector pin can include a discharge load configured to discharge the voltage from the pin. The discharge circuit can also include a first control circuit configured to adjust a magnitude of the discharge load during discharging, such that power consumption is less than or equal to a discharge power limit, and a discharge time is less than or equal to a discharge time limit. The discharge circuit can further include a second control circuit configured to detect whether the voltage of the pin is changed based on a first reference voltage during discharging and adjust the magnitude of the discharge load in response to the change in the voltage of the pin, such that a slew rate of the voltage is less than or equal to a slew rate limit.

Abstract: Apparatuses, systems, devices, and methods for a face mask for facilitating conversations are disclosed. A face mask includes a microphone located on an inside of the face mask, a processor located on the inside of the face mask and connected to the microphone, and a memory located on the inside of the face mask that stores code executable by the processor. The code is executable by the processor to capture, using the microphone, audio spoken by a user wearing the face mask, determine a mode that the face mask is in for transmitting the captured audio to a destination, and transmit the captured audio to the destination based on the determined mode.

Abstract: Systems and methods are disclosed in which a playback device transmits a first sound signal including a predetermined waveform. In one example, the playback device receives a second sound signal including at least one reflection of the first sound signal. The second sound signal is processed to determine a location of a person relative to the playback device, and a characteristic of audio reproduction by the playback device is selected, based on the determined location of the person.

Abstract: A differential microphone array includes a plurality of microphones situated on a substantially planar platform and a processing device, communicatively coupled to the plurality of microphones, to receive a plurality of electronic signals generated by the plurality of microphones responsive to a sound source and execute a minimum-norm beamformer to calculate an estimate of the sound source based on the plurality of electronic signals, wherein the minimum-norm beamformer is determined subject to a constraint that an approximation of a beampattern associated with the differential microphone array substantially matches a target beampattern.

Abstract: A flexible method to provide a variety of value-added coatings to a piece of jewelry or a group of jewelries is disclosed. Atomic Layer Deposition (ALD) and Molecular Layer Deposition (MLD) technique is implemented to deposit a layer of conformal coating on intended jewelry surfaces, including both exterior and interior surfaces, to enhance a vast majority of process-driven or end of use driven properties. The coating compositions include dielectrics material, metals, organic materials or organic-inorganic hybrid materials. The method steps of forming a layer of coating are straightforward and can be tailed to different purposes.

Abstract: Described herein are systems and methods for compressing or otherwise reducing the memory requirements for storing and computing the model parameters in recurrent neural language models. Embodiments include space compression methodologies that share the structured parameters at the input embedding layer, the output embedding layers, or both of a recurrent neural language model to significantly reduce the size of model parameters, but still compactly represent the original input and output embedding layers. Embodiments of the methodology are easy to implement and tune. Experiments on several data sets show that embodiments achieved similar perplexity and BLEU score results while only using a fraction of the parameters.

Abstract: The present disclosure relates to a differential input circuit, an amplifier circuit, and a display device. The differential input circuit comprises: a first power module, a second power module, a first shunt module, a second shunt module, a first output module, and a second output module. The first power module is controlled to output a first signal, a second signal, and a third signal through a first bias signal, and the second power module receives the first signal, and outputs a fourth signal and a fifth signal through a differential input signal. The first shunt module, the second shunt module, the first output module, and the second output module are controlled by the differential input signal so that the first output module and the second output module output signals under the control of the differential input signal.

Abstract: A sound pickup method obtains a correlation between a first sound pickup signal of a directional first microphone and a second sound pickup signal of a non-directional second microphone, and performs level control of the first sound pickup signal or the second sound pickup signal according to a calculation result of the correlation.

Abstract: An augmented reality eyewear device to operate augmented reality applications and provides a wide-angle field view, is disclosed. The eyewear device comprises a frame which is associated with a processor, a sensor assembly, a camera assembly, and a user interface control assembly coupled to the processor. The sensor assembly coupled to the processor comprises at least two inertial measurement unit (IMU) sensor to transmit raw IMU data of at least one IMU sensor and an android connected IMU data of at least one IMU sensor. The camera assembly coupled to the processor comprises at least two wide angle cameras synchronized with one another is configured to transmit camera feed data from the camera assembly to the processor. The processor is configured to dually synchronize raw IMU Data and android connected IMU data with the camera feed data providing a seamless display of 3D content of the augmented reality applications.

Abstract: The invention discloses a method for noise reduction in a binaural hearing aid, said binaural hearing aid comprising a first local unit and a second local unit, wherein the method comprises the following steps: generating a first main signal and a first auxiliary signal in the first local unit from an environment sound, and a second main signal in the second local unit from the environment sound, estimating a direction of arrival of a useful sound signal in the environment sound, assigning a first frequency range and a second frequency range, generating a first range beamformer signal in the first frequency range from the first main signal, the first auxiliary signal and the second main signal by imposing at least one spatial condition related to the estimated direction of arrival on the directional characteristic of the first range beamformer signal, generating a second range beamformer signal in the second frequency range from the first main signal and the second main signal by imposing at least one spatial

Abstract: The sound pick-up apparatus has a first area sound pick-up unit configured to acquire, on a basis of an input signal from a microphone array unit capable of forming microphone arrays with three or more different directionalities, area sound pick-up outputs based on two or more patterns of combinations of the microphone arrays, and a second area sound pick-up unit configured to output, as an area sound pick-up result, a result obtained by integrating the area sound pick-up outputs of the respective patterns which are acquired by the first area sound pick-up unit.

Abstract: An acoustic processing apparatus includes a detection unit configured to detect a change in a state of a microphone, and a determination unit configured to determine a parameter to be used in acoustic signal generation by a generation unit configured to generate an acoustic signal based on one or more of a plurality of channels of sound collection signals acquired based on sound collection by a plurality of microphones, wherein in a case where a change in at least any of states of the plurality of microphones is detected by the detection unit, the determination unit determines the parameter based on the states of the plurality of microphones after the change.

Abstract: Embodiments generally relate to a device comprising at least one signal input component for receiving a bone conducted signal from a bone conducted signal sensor of an earbud; memory storing executable code; and a processor configured to access the memory and execute the executable code. Executing the executable code causes the processor to: receive the bone conducted signal; determine at least one speech metric for the received bone conducted signal, wherein the speech metric is based on the input level of the bone conducted signal and a noise estimate for the bone conducted signal; based at least in part on comparing the speech metric to a speech metric threshold, update a speech certainty indicator indicative of a level of certainty of a presence of speech in the bone conducted signal; update at least one signal attenuation factor based on the speech certainty indicator; and generate an updated speech level estimate output by applying the signal attenuation factor to a speech level estimate.

Abstract: Presented herein is an audio endpoint for telecommunication operations with increased echo rejection. According to one example, the audio endpoint includes a housing body, an upper speaker assembly, a lower speaker assembly, and at least one microphone assembly. The upper speaker assembly is disposed near a top portion of the housing body and has an effective frequency range above a first frequency. The lower speaker assembly is disposed near a bottom portion of the housing body and has an effective frequency range below a second frequency. The microphone assembly includes a first microphone element and a second microphone element. The first microphone element is above the second microphone element so that they are vertically aligned. The first microphone element has an effective frequency range below the first frequency and the second microphone element has an effective frequency range above the second frequency.

Abstract: The present disclosure provides a microphone including a main body, where an audio signal is generated in the main body based on the sound level and some other properties received, and an amplifier disposed in the main body, where the amplifier is adapted to amplify the audio signal, with the amplifier able to be configured with multiple gain levels. The present disclosure further provides a method for processing audio signals including: acquiring an audio signal; selecting a gain from multiple gain levels of an amplifier based on a property of the acquired audio signal, where the amplifier is built in a main body of a microphone; and modifying the digital representation after analog to digital conversion of the acquired audio signal according to the selected gain.

Abstract: An electronic apparatus includes a housing in which an opening is formed, a microphone disposed inside the housing and configured to collect sound from the opening, a light emitter disposed inside the housing and configured to emit light from the opening, and a buffer member configured to block the opening. The buffer member has a base portion, a first portion facing the microphone, and a second portion facing the light emitter. The first portion is a cut portion of the base portion. The second portion is a portion protruding from the base portion.

Abstract: To provide an information processing apparatus, an information processing method, and a program capable of aurally producing distance in a virtual three-dimensional space by using the space for a connection to a communication partner, and realizing more comfortable communication. An information processing apparatus including: a reception unit configured to receive data from a communication destination; and a reproduction control unit configured to perform control such that sound data of a space of the communication destination is reproduced from a sound output unit in a space of a communication source with an output value in accordance with separation distance between the communication destination and the communication source disposed in a virtual three-dimensional space, the output value being different for each sound source type.

Abstract: Described herein are an apparatus, a computer program product, and a method for switching between rendering modes based on location data. The method can comprise based on location data indicative of a location of a user in an environment, causing rendering of audio content, via headphones worn by the user, to be switched from a first rendering mode, in which the audio content is rendered such that at least a component of the audio appears to originate from a first location that is fixed relative to the user, to a second rendering mode, in which the audio content is rendered such that at least the component of the audio content appears to originate from a second location that is fixed relative to the environment of the user. The method can further comprise causing rendering of additional audio content for the user via the headphones.

Abstract: Apparatus configured to, based on visual and audio content captured of a scene comprising at least one audio source and the content including at least two audio tracks, each audio track comprising audio captured by a respective one of at least two audio capture devices located at different locations in the scene, and audio-capture-direction information indicative of at least the direction towards each of the audio capture devices; provide for display of a user selectable audio-capture-location graphic for each of the audio tracks, wherein each audio-capture-location graphic is associated with one of the audio tracks and visually associated with the audio source wherein the form or position of the audio-capture-location graphics is indicative of the direction towards the audio source capture device and wherein based on selection of one of the audio-capture-location graphics, provide for audible presentation of the audio track associated therewith.

Abstract: A smart microphone system is disclosed that includes a control microphone subsystem and a smart microphone receiver subsystem. The control microphone subsystem may include a microphone; a wireless transmitter that receives audio signals from the microphone and is configured to wirelessly communicate the audio signals; and a button that switches between a virtual assistant state and audio output state. The smart microphone receiver subsystem may include a wireless receiver that receives audio signals from the wireless transmitter; an audio output that outputs the audio signals from the wireless receiver when the button is in the audio output state; and a virtual assistant that receives the audio signals from the wireless receiver when the button is in the virtual assistant enable state.

Abstract: A connection assembly for connection to an audio device includes a connector module including a connector configured for electronic connection to a mating connector of the audio device and a releasable latch configured for retaining the connector module to the audio device, an actuator engageable with the connector module and being moveable to release the latch for removal of the connector module from the audio device, and locking structure configured to selectively resist movement of the actuator to release the latch.

Abstract: Described herein is a MEMS acoustic transducer device provided with a micromechanical detection structure that detects acoustic-pressure waves and supplies a transduced electrical quantity, and with an integrated circuit operatively coupled to the micromechanical detection structure and having a reading module that generates at output an audio signal as a function of the transduced electrical quantity. The integrated circuit is further provided with a recognition module, which recognizes a of sound activity event associated to the transduced electrical quantity. The MEMS acoustic transducer has an output that supplies at output a data signal that carries information regarding recognition of the sound activity event.

Abstract: Systems and methods for training and using an image classifier are provided. A plurality of points can be generated from respective patches of images annotated as either a first type or a second type. The points corresponding to the images of the second type can be clustered into two clusters. A first cluster of the two clusters can be identified as closer to the points corresponding to the images annotated as the first type. The points in the first cluster can be assigned to a class positive, the points in the second cluster can be assigned to a class negative, and the points corresponding to the images annotated as the first type can be assigned to an anchor class. A plurality of triplets can be generated based on the points in the various classes. Parameters of an image classifier can be adjusted based on a loss function of the triplets.

Abstract: The present disclosure relates to a circuit and system for audio pickup and play, and a method for switching audio pickup and play. The circuit includes a microphone array for collecting a first audio signal, a first wireless audio transceiver for receiving a second audio signal from a remote wireless microphone, an audio processor, a first audio player, a controller for outputting a first control signal and a second control signal, an audio input switcher for inputting the first audio signal or the second audio signal into the audio processor based on the first control signal. The audio processor is configured for processing the received first audio signal and second audio signal and outputting an audio play signal. The circuit includes an audio output switcher for outputting the audio play signal to the first audio player or the first wireless audio transceiver based on the second control signal.

Abstract: A microphone array configurable to connect via an Ethernet connection with an audio processor includes a plurality of MEMS microphones (7101-7121), a plurality of sigma-delta modulators (7201-7221), a processor and storage (90), and an Ethernet physical interface (80) operating at a network data transmission rate. Each sigma-delta modulator converts the analog output of a corresponding microphone into a bit stream at an audio sampling rate. The processor and storage performs a data-interleaving operation (92) to combine the bit streams from the sigma-delta modulators into a microphone audio frame serial bit stream (34), and loads the microphone audio frame serial bit stream into a FIFO memory (94) at a FIFO serial data load rate.

Abstract: Some embodiments of the invention include a throwable microphone device. The throwable microphone device may comprise a housing. The throwable microphone device may include a microphone, a communication unit, a motion sensor, an orientation sensor, and a processor disposed within the housing. In some embodiments, the microphone may receive sound waves and generate a corresponding electrical audio signal. The communication unit may wirelessly transmit at least a portion of the electrical audio signals. The motion sensor may detect changes in acceleration of the throwable microphone device. The orientation sensor may detect changes in orientation of the throwable microphone device. The processor may be electrically coupled with the microphone, the communication unit, the motion sensor, and the orientation sensor. The processor may mute the throwable microphone device in response to data from the motion sensor and may also unmute the throwable microphone device in response to data from the orientation sensor.

Abstract: A voice activity detection unit is configured to receive at least two electric input signals in a number of frequency bands and a number of time instances, k and m being frequency band and time indices, respectively, (k, m) defining a specific time-frequency tile of said electric input signal. The voice activity detection unit is configured to provide a resulting voice activity detection estimate comprising one or more parameters indicative of whether or not a given time-frequency tile contains or to what extent it comprises a target speech signal. The voice activity detection unit comprises a) a first detector for analyzing the time-frequency representation of the electric input signals and identifying spectro-spatial characteristics of said electric input signals, and b) and is configured for providing said resulting voice activity detection estimate in dependence of said spectro-spatial characteristics. The invention may be used in hearing aids, table microphones, speakerphones, etc.

Abstract: Various embodiments set forth techniques for directional sound modification. In one aspect, a system includes a plurality of audio sensors configured to acquire sound from an environment and at least one processor coupled to the plurality of audio sensors. The at least one processor is configured to determine a direction within the environment, generate an audio signal based on sound acquired from the direction within the environment, and transmit the audio signal to at least one audio output device to generate audio output. The audio output combines with sound from the direction within the environment to produce a modified sound.

Abstract: A device for measuring wind noise comprises at least a first microphone and a processor. A first signal and a second signal are obtained from the at least one microphone, the first and second signals reflecting a common acoustic input, and the first and second signals being at least one of temporally distinct and spatially distinct. The first signal is processed to determine a first distribution of the samples of the first signal. The second signal is processed to determine a second distribution of the samples of the second signal. From a difference between the first distribution and the second distribution a scalar non-binary metric reflecting an intensity of wind noise present in the first and second signals is derived, and output.

Abstract: Stereoscopic 360° video recording devices are adapted to facilitate capture of stereoscopic 360° images. According to one example, a stereoscopic 360° video recording device may include an enclosure with three sides of equal length in a triangular configuration. Six digital camera slots may be included within the enclosure, with each of the three sides including two digital camera slots. A fan may be coupled to a surface of the enclosure to facilitate cooling of digital cameras retained within the enclosure. A digital video camera may be secured within each of the digital camera slots, wherein each digital video camera includes a predefined interaxial distance from a respective digital video camera on its left and a respective digital video camera on its right. Other aspects, embodiments, and features are also included.

Abstract: An acoustic processing apparatus includes a detection unit configured to detect a change in a state of a microphone, and a determination unit configured to determine a parameter to be used in acoustic signal generation by a generation unit configured to generate an acoustic signal based on one or more of a plurality of channels of sound collection signals acquired based on sound collection by a plurality of microphones, wherein in a case where a change in at least any of states of the plurality of microphones is detected by the detection unit, the determination unit determines the parameter based on the states of the plurality of microphones after the change.

Abstract: A method for operating a hearing device includes generating first and second input signals from a sound signal by using respective first and second input transducers, providing a first angle and an angular range and, with respect to frequency bands, based on the first and second input signals and first angle, forming an attenuation directional signal having relative attenuation at least for a second angle in the angular range about the first angle and thereby setting and an overlay parameter. A gain directional signal is formed based on the first and second input signals and the overlay parameter and/or second angle, having relative gain for the second angle. An angled directional signal is generated from the attenuation directional signal and the gain directional signal. An output signal is generated based on the angled directional signal. A hearing device and a binaural hearing device system are also provided.

Abstract: Embodiments of the present invention provide a method for locating a sound emitting position and a terminal device. The method includes: collecting K first sound signals, where K is an integer greater than or equal to 2; extracting M second sound signals from the K first sound signals according to N position parameters corresponding to N different positions, where M is less than or equal to N, and N is an integer greater than or equal to 2; and determining a position corresponding to each second sound signal.

Abstract: A spherical content capture system captures spherical video and audio content. In one embodiment, captured metadata or video/audio processing is used to identify content relevant to a particular user based on time and location information. The platform can then generate an output video from one or more shared spherical content files relevant to the user. The output video may include a non-spherical reduced field of view such as those commonly associated with conventional camera systems. Particularly, relevant sub-frames having a reduced field of view may be extracted from each frame of spherical video to generate an output video that tracks a particular individual or object of interest. For each sub-frame, a corresponding portion of an audio track is generated that includes a directional audio signal having a directionality based on the selected sub-frame.

Abstract: A microphone has: a printed circuit board provided with a first sound hole; a microphone element mounted on a first surface of the printed circuit board so as to cover the first sound hole; a microphone casing provided with a second sound hole opposite to the first sound hole, and housing the printed circuit board so that the second sound hole; and a bush provided with a third sound hole, and having a first contact surface and a second contact surface. The third sound hole is disposed between the first and second sound holes to be communicated with the holes. The first contact surface is in contact with a second surface of the printed circuit board at a first end of the third sound hole. The second contact surface is in contact with an inner surface of the microphone casing at a second end of the third sound hole.

Abstract: Various techniques are provided to perform enhanced automatic speech recognition. For example, a subband analysis may be performed that transforms time-domain signals of multiple audio channels in subband signals. An adaptive configurable transformation may also be performed to produce single or multichannel-based features whose values are correlated to an Ideal Binary Mask (IBM). An unsupervised Gaussian Mixture Model (GMM) model fitting the distribution of the features and producing posterior probabilities may also be performed, and the posteriors may be combined to produce deep neural network (DNN) feature vectors. A DNN may be provided that predicts oracle spectral gains from the input feature vectors. Spectral processing may be performed to produce an estimate of the target source time-frequency magnitudes from the mixtures and the output of the DNN. Subband synthesis may be performed to transform signals back to time-domain.

Abstract: Various implementations include microphone arrays and related speaker systems. In one implementation, a microphone array is mounted in a housing having a primary X axis, a primary Y axis perpendicular to the primary X axis, and a primary Z axis perpendicular to the primary X axis and the primary Y axis. The microphone array can include a set of microphones positioned in a single plane perpendicular to the primary Z axis, and axially asymmetric with respect to both the primary X axis and the primary Y axis.