Abstract: The present system ensures that external noise sources do not taint sensor data recorded about a user's sleep parameters, to reduce false positives and false negatives, and provides a more accurate record of the user's sleep sounds, by cycling on and off noise sources. Additionally, the present system, in one embodiment, may be used to track changes in sound patterns from the user and from the environment. This may lead to early warning of health issues, as well as issues with the devices in the bedroom.

Abstract: Techniques for managing call sessions in multi-display systems are described. For instance, the described techniques can be implemented to manage media content in the context of a client device that includes two or more housings attached via a hinge region such that the housings are pivotable relative to one another. The described techniques, for example, enable dynamic configuration of output of call sessions based on changes in user position relative to a client device.

Abstract: A method of multi-talker separation using a 3-tuple coprime microphone array, including generating, by a subarray signal processing module, a respective subarray data set for each microphone subarray of the 3-tuple coprime microphone array based, at least in part, on an input acoustic signal comprising at least one speech signal. The input acoustic signal is captured by the 3-tuple coprime microphone array. The 3-tuple coprime microphone array includes three microphone subarrays. The method includes determining, by the subarray signal processing module, a point by point product of the three subarray data sets; and determining, by the subarray signal processing module, a cube root of the point by point product to yield an acoustic signal output data. The acoustic signal output data has an output amplitude and an output phase corresponding to an input amplitude and an input phase of a selected speech signal of the at least one speech signal.

Abstract: A signal e(z) obtained by subtracting echo-canceling sound from an output of a second microphone is used as an error of an echo cancellation adaptive filter and a noise cancellation adaptive filter, and an output of a first sound source device is added to the signal e(z) and output from a first speaker. The echo cancellation adaptive filter generates echo-canceling sound from an addition signal of the output of the second sound source device and the output of the first microphone such that the signal e(z) is minimized. The noise cancellation adaptive filter generates the noise-canceling sound from the output of the first sound source device such that the signal e(z) is minimized, and outputs the noise-canceling sound from the second speaker.

Abstract: An apparatus for providing active noise control, includes: one or more microphones configured to detect sound entering through an aperture of a building structure; a set of speakers configured to provide sound output for cancelling or reducing at least some of the sound; and a processing unit communicatively coupled to the set of speakers, wherein the processing unit is configured to provide control signals to operate the speakers, wherein the control signals are independent of an error-microphone output.

Abstract: A display device including an external device interface configured to connect the display device to an external speaker; a microphone configured to receive a microphone signal; and a controller configured to: transmit an inaudible test signal to the external speaker to measure a signal delay between the external speaker and the display device, and extract a voice signal by removing an acoustic signal output from the external speaker from the microphone signal based on the measured signal delay.

Abstract: Disclosed are systems and methods for a frontend capture module of a video conferencing application, which can modify an input signal, received from a microphone device to match predetermined signal characteristics, such as voice signal level and expected noise floor. An Input stage, a suppression module and an output stage amplify the voice signal portion of the input signal and suppress the noise signal of input signal to predetermined ranges. The input stage selectively applies gains defined by a gain table, based on signal level of the input signal. The suppression module selectively applies a suppression gain to the input signal based on presence or absence of voice signal in the input signal. The output stage further amplifies the input signal in portions having a voice signal and applies a gain table to maintain a consistent noise floor.

Abstract: A sound recognition apparatus (100) includes at least two microphones (1) that detect a surrounding sound, an attitude detection unit (4) that detects attitudes of the microphones (1), a self-position estimation unit (52) that estimates positions of the microphones (1) based on the attitudes of the microphones (1) and a signal of the sound detected by the microphone (1), a sound source estimation unit (53) that estimates a direction of the sound source (200) of the sound based on the attitudes of the microphones (1) and the signal of the sound detected by the microphone (1), and a sound environment mapping unit (54) that creates a sound environment map based on the positions of the microphones (1) and the direction of the sound source (200), the sound environment map displaying at least a position of the sound source (200).

Abstract: Embodiments that translate a sensor measurement to a frequency characteristic are disclosed. The frequency characteristic can be wirelessly detected by a reader device. The detected frequency characteristic can be used to determine the corresponding sensor measurement. Devices utilizing this approach can be characterized or calibrated to increase accuracy. Systems and methods utilizing the approaches are also described.

Abstract: Embodiments include a microphone assembly comprising an array microphone and a housing configured to support the array microphone and sized and shaped to be mountable in a drop ceiling in place of at least one of a plurality of ceiling tiles included in the drop ceiling. A front face of the housing includes a sound-permeable screen having a size and shape that is substantially similar to the at least one of the plurality of ceiling tiles. Embodiments also include an array microphone system comprising a plurality of microphones arranged, on a substrate, in a number of concentric, nested rings of varying sizes around a central point of the substrate. Each ring comprises a subset of the plurality of microphones positioned at predetermined intervals along a circumference of the ring.

Abstract: Disclosed are systems and methods for performing adaptive equalization operations to reduce variations in the frequency response of audio signals at the eardrum of a wearer of an earphone. The assumption that the frequency response of the error microphone matches the frequency response at the eardrum may not be true due to signal leakage effects and the shape of the ear canal. Techniques are disclosed for the adaptive equalization operations to perform a calibration algorithm to compensate for the effects of the signal leakage and the shape of the ear canal. The earphone may estimate the transfer function from the speaker to the error microphone and may estimate the load impedance from the earphone based on a calibrated relationship between the transfer function and the load impedance. The adaptive equalization may use a calibration algorithm to adjust the frequency response at the error microphone to match that at the eardrum.

Abstract: In some implementations, a user device may receive input that triggers transmission of information via sound. The user device may select an audio clip based on a setting associated with the device, and may modify a digital representation of the selected audio clip using an encoding algorithm and based on data associated with a user of the device. The user device may transmit, to a remote server, an indication of the selected audio clip, an indication of the encoding algorithm, and the data associated with the user. The user device may use a speaker to play audio, based on the modified digital representation, for recording by other devices. Accordingly, the user device may receive, from the remote server and based on the speaker playing the audio, a confirmation that users associated with the other devices have performed an action based on the data associated with the user of the device.

Abstract: An audio signal processing method includes obtaining an audio signal of a sound source, performing first filter processing on the audio signal to generate an imaginary sound source of a virtual space, performing second filter processing on the audio signal to adjust a tone of the imaginary sound source, and outputting an initial reflected sound control signal generated by using the audio signal on which the first filter processing and the second filter processing have been performed, in a first case where the first filter processing is performed before the second filter processing, the first filter processing is performed on the audio signal, and the second filter processing is performed on the audio signal on which the first filter processing has been performed, and in a second case where the second filter processing is performed before the first filter processing, the second filter processing is performed on the audio signal, and the first filter processing is performed on the audio signal on which the seco

Abstract: A cochlear stimulation system for determining a Temporal Fine Structure (TFS) parameter of a spectral component of an incoming acoustic signal is provided. The system comprises a transducer receiving an incoming acoustic signal, and wherein a sampled audio signal of length N samples is provided based on the incoming acoustic signal, a storing unit including a plurality of window frequency differences and/or a plurality of window energy level differences. The system further comprises a signal processor for estimating the TFS parameter of the full frequency range of the sampled audio signal by locating a main spectrum sample of the plurality of spectrum samples having a maximum energy level within a range of frequencies centered around the main spectrum sample, and determining the TFS parameter based on the energy level difference for one or more of the spectrum samples of the group of spectrum samples and the window function.

Abstract: A detection device includes a pressure sensor, which provides a pressure signal indicative of an ambient pressure in an operating environment. An electrostatic-charge-variation sensor provides a charge-variation signal indicative of a variation of electrostatic charge associated with the operating environment, and processing circuitry is coupled to the pressure sensor and to the electrostatic-charge-variation sensor so as to receive the pressure signal and the charge-variation signal, and jointly processes the pressure signal and the charge-variation signal for detecting a variation between a first operating environment and a second operating environment for the detection device. The second operating environment is different from the first operating environment.

Abstract: A key word detection apparatus and a method for low-power voice-activated devices are presented. A first signal processing module operates with a first transducer to receive an incoming signal and generates a first sample. A second signal processing module operates with a second transducer which receives an incoming signal and generates a second sample. In summary, a signal processing system, in particular a key word detection system, has a first low power module that wakes up a second higher power module. The second module uses signals from the first module in order to improve accuracy of key word detection or other signal processing tasks.

Abstract: An audio signal processing apparatus is provided by the present disclosure, and includes: multiple microphones; and every two of the multiple microphones being arranged in close proximity to each other, and the multiple microphones forming a symmetrical structure.

Abstract: An acoustic sensor assembly includes a non-directional acoustic sensor having a first directional pattern, a plurality of directional acoustic sensors surrounding the non-directional acoustic sensor and including a plurality of resonators having different resonance frequencies from each other, each of the plurality of directional acoustic sensors having a second directional pattern, and a processor configured to obtain output signals from the non-directional acoustic sensor and the plurality of directional acoustic sensors. The processor is further configured to calculate an acoustic signal having directivity by selecting any one or any combination of the obtained output signals or selectively combining the obtained output signals, and obtain sound around the acoustic sensor assembly, using the calculated acoustic signal.

Abstract: A speech processing device includes a processor. The processor performs operations including: detecting a single-talk state based on a speech signal collected by each of microphones, the single-talk state in which any one of persons speaks; estimating a mixing rate indicating a ratio of a speech signal of the main speaking person to a speech signal of another person based on a sound pressure ratio of the speech signals collected by the microphones in the single-talk state of the main speaking person and a sound pressure ratio of the speech signals collected by the plurality of microphones in the single-talk state of the another person; and determining whether suppression of a crosstalk component due to speaking of the another person contained in the speech signal of the main speaking person is necessary based on an estimation result of the mixing rate.

Abstract: A robot and operation method is disclosed. The robot according to the present disclosure may include a sensor, a microphone, and a controller. The robot may execute an artificial intelligence (AI) algorithm and/or a machine learning algorithm, and may communicate with other electronic devices in a 5G communication environment. An embodiment may include detecting a movement of the robot to a location; detecting an obstacle within a predetermined range from the robot; estimating an occupation area of the obstacle in space; and identifying a sound signal received from the estimated occupation area of the obstacle from among a plurality of sound signals received by a plurality of microphones of the robot at the location.

Abstract: An earphone includes a feedforward microphone located outside ear and a feedback microphone located inside ear.

Abstract: A method, apparatus and device for displaying a lyric, and a storage medium. The method includes: displaying a control panel and a lyric display panel of a target player application on an interface; canceling the display of the control panel when a trigger operation on the interface satisfies a reference condition, and setting the lyric display panel to be in a non-triggerable state, such that a desktop area of the current interface covered by the control panel and the lyric display panel becomes capable of receiving a trigger operation; displaying an interactive control on the interface, the interactive control being used to perform a lyric display control function; and restoring the display of the control panel when a click operation on the interactive control is detected.

Abstract: A waveguide assembly for guiding sound includes a chassis that provides a cavity configured to receive sound propagating in a forwards direction along a primary axis of the waveguide assembly; a fixed waveguide that is fixed with respect to the chassis and positioned on the primary axis of the waveguide assembly, wherein the fixed waveguide is spaced apart from the chassis and is configured to guide sound received by the cavity through at least one opening formed between the fixed waveguide element and the chassis; a moveable waveguide that is moveable with respect to the chassis between: a standby position in which the moveable waveguide is configured to obstruct the at least one opening and form a forward-facing surface of the waveguide assembly; an operational position in which the moveable waveguide is configured to allow sound to exit the cavity through the at least one opening.

Abstract: Techniques for dynamically adjusting received audio are described. In an example, a computer system receives audio data representing noise and utterance received by a device during a first time interval that has a start and an end. The start corresponds to a beginning of the utterance. The end corresponds to at a selection by the device of an audio beam associated with a direction towards an utterance source. The computer system determines a value associated with an audio adjustment factor. The audio adjustment factor is represented by values that vary during the time interval. The value is one of the values associated with a time point of the first time interval. The computer system generates, based at least in part on the audio data and the value, first data that indicates a measurement of at least one of the noise or the utterance.

Abstract: The present disclosure describes aspects of adaptive energy limiting for transient noise suppression. In some aspects, an adaptive energy limiter sets a limiter ceiling for an audio signal to full scale and receives a portion of the audio signal. For the portion of the audio signal, the adaptive energy limiter determines a maximum amplitude and evaluates the portion with a neural network to provide a voice likelihood estimate. Based on the maximum amplitude and the voice likelihood estimate, the adaptive energy limiter determines that the portion of the audio signal includes noise. In response to determining that the portion of the audio signal includes noise, the adaptive energy limiter decreases the limiter ceiling and provides the limiter ceiling to a limiter module effective to limit an amount of energy of the audio signal. This may be effective to prevent audio signals from carrying full energy transient noise into conference audio.

Abstract: An open acoustic device (100) may include a fixing structure (120) configured to fix the acoustic device (100) near an ear of a user without blocking an ear canal of the user; a first microphone array (130) configured to acquire environmental noise (410); a signal processor (140) configured to: determine, based on the environmental noise, a primary route transfer function (420) between the first microphone array (130) and the ear canal of the user; estimate, based on the environmental noise and the primary route transfer function, a noise signal (430) at the ear canal of the user; and generate, based on the noise signal at the ear canal of the user, a noise reduction signal (440); and a speaker (150) configured to output, according to the noise reduction signal, a noise reduction acoustic wave (450), the noise reduction acoustic wave being configured to eliminate the noise signal.

Abstract: Apparatus, methods and computer-readable medium are provided for processing wind noise. Audio input is processed by receiving an audio input. A wind noise level representative of a wind noise at the microphone array is measured using the audio input and a determination is made, based on the wind noise level, whether to perform either (i) a wind noise suppression process on the audio input on-device, or (ii) the wind noise suppression process on the audio input on-device and an audio reconstruction process in-cloud.

Abstract: Techniques for improving microphone noise detection and suppression are provided. A method for detecting wind noise corresponding to microphone signals may include determining a phase of a complex coherence of the microphone signals. The phase may be used to determine a presence of wind near the microphones. A derivative of the phase may be used to determine a presence of speech near the microphones. Further, a method for suppressing noise caused by the wind may include determining a gain based on a cross power spectrum of the microphone signals and applying the gain to the microphone signals. The method for suppressing the noise may also include attenuating the microphone signals using a post filter. Based on detection of the wind, microphones which are more exposed to the wind may not be used to process the speech whereas microphones less exposed to the wind may be used to process the speech.

Abstract: An apparatus and method for auto echo cancellation utilizing an occluded voice sensor. The technology as disclosed and claimed herein and the various implementations and embodiments improves Acoustic Echo Cancellation (AEC) system performance by increasing cancellation quality and speech SNR by the replacement of the lower frequency portion of the microphone signal with the signal of an Occluded Voice Sensor (OVS) signal and never including the spectral band in the transmission. This frequency band replacement excludes the reinjection of that band from the speaker.

Abstract: The present disclosure relates to an acoustic output apparatus including a first acoustic driver for outputting sounds within a first frequency range via a plurality of first sound guiding holes and a second acoustic driver for outputting sounds within a second frequency range via a plurality of second sound guiding holes. The sounds output via the plurality of first sound guiding holes may radiate to the environment and form a leaked sound. The acoustic output apparatus may further include a support structure configured to support the first acoustic driver and the second acoustic driver such that the plurality of sound guiding holes are located at positions away from a user's ear. The sounds output via the plurality of second sound guiding holes may interfere with the leaked sound in an overlapping frequency range between the second frequency range and the first frequency range to reduce the leaked sound.

Abstract: A filtering method includes the following steps: receiving an sound signal; decomposing the sound signal into a primary lung sound signal and a reference heart sound signal; adjusting the reference heart sound signal according to a weighted value to generate an adjusted heart sound signal; and subtracting the adjusted heart sound signal from the primary lung sound signal to generate a filtered lung sound signal.

Abstract: Methods and systems for performing automatic speed-based audio control. One method includes receiving, with an electronic control unit included in a vehicle, a speed of the vehicle and receiving, with the electronic control unit, an audio signal. The method also includes accessing, with the electronic control unit, a plurality of equalization curves based on the speed of the vehicle, each of the plurality of equalization curves associated with the speed of the vehicle and each of the plurality of equalization curves defining a gain adjustment for one of a plurality of frequencies, and, for each curve of the plurality of equalization curves, applying the gain adjustment defined by the curve to one of the plurality of frequencies of the audio signal.

Abstract: Embodiments of the present application provide an audio processing method and an apparatus. The method includes: a mobile terminal and a vehicle terminal are in a connected state, and playing, by the mobile terminal, a first audio synchronously with the vehicle terminal; obtaining, by the mobile terminal, a recorded audio of a current environment, where the recorded audio includes the first audio played by the vehicle terminal and a second audio for voice recognition; and eliminating, according to the first audio played by the mobile terminal, the first audio played by the vehicle terminal in the recorded audio to obtain the second audio. In the embodiments of the present application, by playing the first audio synchronously by the mobile terminal and the vehicle terminal, the second audio for voice recognition in the recorded audio can be obtained according to the first audio played by the mobile terminal.

Abstract: A composite cable is composed of a plurality of power supply wires, a plurality of signal wires, two or more of which are configured to be connected to a common terminal member, and a sheath provided to cover the plurality of power supply wires and the plurality of signal wires together. The two or more of the plurality of signal wires being configured to be connected to the common terminal member are provided adjacent to each other.

Abstract: Embodiments include techniques and objects related to a wearable audio device that includes a microphone to detect a plurality of sounds in an environment in which the wearable audio device is located. The wearable audio device further includes a non-acoustic sensor to detect that a user of the wearable audio device is speaking. The wearable audio device further includes one or more processors communicatively to alter, based on an identification by the non-acoustic sensor that the user of the wearable audio device is speaking, one or more of the plurality of sounds to generate a sound output. Other embodiments may be described or claimed.

Abstract: An apparatus for improving the sound of a vehicle according to one embodiment of the present invention, may comprise: a window open/closed detection sensor for detecting the open/closed state of a window of the vehicle; a car door open/closed detection sensor for detecting the open/closed state of a car door of the vehicle; a speed sensor for measuring the speed of the vehicle; a microphone; a memory; and a processor for adjusting a coefficient of an adaptive filter used for an engine order cancellation (EOC) function, on the basis of the opened degree of the window and the speed, when the car door is closed, the window is open, and the magnitude of noise inputted to the microphone is less than or equal to a threshold magnitude.

Abstract: A hearing system contains a hearing instrument and the hearing instrument is configured to support the hearing of a hearing-impaired user. The hearing instrument is operated via an operating method. The method includes capturing a sound signal from an environment of the hearing instrument, processing the captured sound signal to at least partially compensate the hearing-impairment of the user and outputting the processed sound signal to the user. The captured sound signal is analyzed to recognize speech intervals, in which the captured sound signal contains speech. During recognized speech intervals, at least one time derivative of an amplitude and/or a pitch of the captured sound signal is determined. The amplitude of the processed sound signal is temporarily increased, if the at least one derivative fulfills a predefined criterion.

Abstract: The present disclosure discloses a method and system for generating mixed voice data, and belongs to the technical field of voice recognition. In the method for generating mixed voice data according to the present disclosure, a pure voice and noise are collected first, normalization processing is performed on the collected voice data, randomization processing is performed on processed data, then GAIN processing is performed on the data, and finally filter processing is performed to obtain mixed voice data. The system for generating mixed voice data according to the present disclosure includes a collecting unit, a calculating unit, and a storage unit, the collecting unit being electrically connected to the calculating unit, and the calculating unit being connected to the storage unit through a data transmitting unit. The present disclosure provides the method and the system to meet the data requirement of deep learning.

Abstract: A method for detecting wind noise incident on a single microphone may include receiving an audio signal indicative of sound incident on the single microphone, dividing the audio signal into a plurality of audio frames, and determining whether wind noise is incident on the single microphone based on a combination of a correlation metric between successive audio frames of the plurality of audio frames and a power ratio difference between a first power ratio and a second power ratio. The first power ratio may equal an amount of power present in a first frequency range of the audio signal to a total amount of power present in the audio signal across all frequencies. The second power ratio may equal an amount of power present in a second frequency range of the audio signal to the total amount of power present in the audio signal across all frequencies.

Abstract: A method and system for improving the intelligibility of an audio signal emitted from plural audio output devices in a space can help mitigate systems that have low intelligibility at installation due to reverberation effects; it can provide a quick post installation check of a system prior to a full-fledged STIPA (Speech Transmission Index for Public Address Systems) or equivalent test; and it allows for a quick verification if changes to the acoustical environment are expected to have major effects on STIPA tests.

Abstract: An information processor including: an operation control unit that controls a motion of an autonomous mobile body acting on the basis of recognition processing, in a case where a target sound that is a target voice for voice recognition processing is detected, the operation control unit moving the autonomous mobile body to a position, around an approach target, where an input level of a non-target sound that is not the target voice becomes lower, the approach target being determined on the basis of the target sound.

Abstract: The present invention relates to a sound diffusion device (300) comprising a single box (310) and, in this single box (310), at least two superimposed high-frequency acoustic sources (320), and a plurality of superimposed medium and/or low-frequency sources (330) and arranged to the left and/or to the right of the high-frequency acoustic sources (320), the high-frequency acoustic sources (320) being coupled individually to a wave guide (340) so as to generate a vertical wave front with a fixed non-constant curvature. Such a device (300) makes it possible to minimise discontinuities between the acoustic sources providing high quality sound diffusion (no parasite lobe), to considerably reduce the weight and the cost of manufacturing and also enables rapid installation which does not require the angular adjustment of each acoustic source relative to one another contrary to existing devices.

Abstract: A system and method are described for automatic acoustic feedback cancellation in real time. In some implementations, the system may receive audio data describing an audio signal, which the system may use to determine a set of frames of the audio signal. Spectral analysis may be performed on the one or more frames of the audio to detect spectral patterns of two or more frames indicative of acoustic feedback. An additional delay identification test may be performed to identify a consistent delay indicative of acoustic feedback. In some implementations, a state machine is advanced based in part on accumulated delay votes. Decisions can be made to mute the acoustic feedback and cease the muting operation when silence is detected.

Abstract: A sensor system includes a triplet element including a first hydrophone, a second hydrophone, and a third hydrophone configured to receive an incoming signal at a first phase, a second phase, and a third phase, respectively, the first to third hydrophones extending along a first direction, and a processor configured to determine an incidence direction of the incoming signal, and to dynamically generate a cardioid null in the incidence direction to reject the incoming signal based on the incoming signal at the first to third phases.

Abstract: A method for detecting blocking of a microphone and related products are provided. The method includes the following. A first electric quantity of a first wireless earphone and a second electric quantity of a second wireless earphone are determined when both the first wireless earphone and the second wireless earphone are worn. A first operation and a second operation are performed in parallel when the first electric quantity is greater than the second electric quantity, where the first operation is to obtain first audio through the first microphone, and the second operation is to obtain second audio through the second microphone. A reference parameter of the second audio is determined. The first wireless earphone is determined to be blocked in response to detecting that a first parameter of the first audio does not match the reference parameter.

Abstract: A speech processing device includes a processor. The processor performs operations including: detecting a single-talk state based on a speech signal collected by each of microphones, the single-talk state in which any one of persons speaks; estimating a mixing rate indicating a ratio of a speech signal of the main speaking person to a speech signal of another person based on a sound pressure ratio of the speech signals collected by the microphones in the single-talk state of the main speaking person and a sound pressure ratio of the speech signals collected by the plurality of microphones in the single-talk state of the another person; and determining whether suppression of a crosstalk component due to speaking of the another person contained in the speech signal of the main speaking person is necessary based on an estimation result of the mixing rate.

Abstract: The present invention relates to a flat-type slim speaker, specifically, to a rectangular flat-type slim speaker having an integrated yoke enabling a slim magnetic core. The present invention comprises: a voice coil plate which comprises a voice coil vertically erected; magnets separated with the voice coil plate therebetween; a diaphragm coming into contact with an upper end surface of the voice coil plate and having an edge part which adheres to a seating part of the upper end of a yoke; a damper which is connected to a damper attachment part of the lower end surface of the voice coil plate and adheres to the lower end of the yoke; and the yoke having a slit into which the voice coil plate can be inserted in a longitudinal direction at the center thereof, and a space into which the magnets can be inserted from side to side.

Abstract: A method, system and computer-usable medium are disclosed for sentiment detection based on applying an antonym dictionary to a natural language processing (NLP) system. A binary classifier is trained to predict negation cues, where a constituency parse tree is used to create rules for scope detection. The trained binary classifier, a list of conversational negation terms, and a list of antonyms are used to annotate content that considers negation cues and scope for the created rules.

Abstract: A system efficiently selects at least one device from multiple devices based on received audio signals. In some instances, the system receives audio signals from devices that each comprise at least one microphone. A respective audio signal of the audio signals includes a representation of a sound originating from a location. The system then determines a device to be used to respond to the sound. In some instances, the system analyzes times in which the received audio signals that represent the sound are generated and/or volumes of the sound as represented by the received audio signals. The system can then select the device based on the analysis.

Abstract: A method, an apparatus, and logic to post-process raw gains determined by input processing to generate post-processed gains, comprising using one or both of delta gain smoothing and decision-directed gain smoothing. The delta gain smoothing comprises applying a smoothing filter to the raw gain with a smoothing factor that depends on the gain delta: the absolute value of the difference between the raw gain for the current frame and the post-processed gain for a previous frame. The decision-directed gain smoothing comprises converting the raw gain to a signal-to-noise ratio, applying a smoothing filter with a smoothing factor to the signal-to-noise ratio to calculate a smoothed signal-to-noise ratio, and converting the smoothed signal-to-noise ratio to determine the second smoothed gain, with smoothing factor possibly dependent on the gain delta.