Abstract: Examples herein provide an approach to enhance an audio mixture of a teleconference application by switching between noise suppression modes using a single model. Specifically, a machine learning (ML) model may be configured to, in response to receiving an audio mixture representation as input, suppress either a background noise of the audio mixture or suppress all noise of the audio mixture except a user's voice. In some examples, the ML model may be trained on speech and background noise training data during a training phase. In addition, the ML model may be trained on a user's voice during an enrollment phase. In addition, during an inference phase, the ML model may enhance the audio mixture by suppressing a portion of the audio mixture.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for dynamically adjusting a screensaver on a display device. An example embodiment operates by a media device detecting the initiation of a screensaver and requesting replacement objects to be injected into the screensaver while the screensaver is displayed on a display device. The media device may receive the replacement objects, select which replacement objects to be injected into the screensaver, and injecting the selected replacement objects into an off-screen portion of the screensaver prior to the off-screen portion being displayed on the displayed device.

Abstract: Real-time low-complexity stereo speech enhancement with spatial cue preservation may be performed. A stereo speech enhancement system receives a stereo input signal (e.g., a left and right input signal). The stereo speech enhancement system estimates spatial cues for a target speaker and downmixes the stereo input signal into a monaural signal. A low-complexity model may then process the monaural signal to generate an enhanced monaural signal. The stereo speech enhancement system upmixes the enhanced monaural signal based on the estimated spatial cues for the target speaker, to generate an enhanced stereo output signal.

Abstract: A recovery circuit includes a buffer and filter module that receives a sampled signal with droops between spikes over an interval of time from a sample and hold circuit and outputs a conditioned signal that has droops. The recovery circuit includes an alternating current (AC) inverter and extractor module that removes a direct current (DC) component of the conditioned signal and provides an inverted AC component signal that has signal boosts with an equal magnitude and duration to the droops in the conditioned signal. The recovery circuit also includes a summing amplifier that combines the conditioned signal and the inverted AC component signal to provide a output signal that has a nearly constant voltage over the interval of time.

Abstract: This disclosure relates to systems and methods for measuring impedance characteristics of a cryogenic device under test (DUT). A channel select circuit can be configured in a first state to electrically isolate a channel output circuit from the cryogenic DUT and in a second state to electrically couple the channel output circuit to the cryogenic DUT, and at least one resistor can be positioned along a transmission path that couples a pattern generator circuit to a channel output circuit that includes the channel select circuit. A controller can be configured to cause respective test current signals to be provided along the transmission path when the channel select circuit is in respective first and second states to establish respective first and second voltages across the at least one resistor, determine first and second impedance characteristics of the transmission path for determining an impedance of the cryogenic DUT.

Abstract: This disclosure relates to systems and methods for measuring impedance characteristics of a cryogenic device under test (DUT). A channel select circuit can be configured in a first state to electrically isolate a channel output circuit from the cryogenic DUT and in a second state to electrically couple the channel output circuit to the cryogenic DUT, and at least one resistor can be positioned along a transmission path that couples a pattern generator circuit to a channel output circuit that includes the channel select circuit. A controller can be configured to cause respective test current signals to be provided along the transmission path when the channel select circuit is in respective first and second states to establish respective first and second voltages across the at least one resistor, determine first and second impedance characteristics of the transmission path for determining an impedance of the cryogenic DUT.

Abstract: A plurality of device-sharing participants may be detected that are participating in a videoconference via a shared computing device. The detecting of the plurality of device-sharing participants may be performed based, at least in part, on at least one of an audio analysis of captured audio from one or more microphones or a video analysis of captured video from one or more cameras. A plurality of participant connections corresponding to the plurality of device-sharing participants may be joined to the videoconference. Each of the plurality of participant connections may be identified within the videoconference using a respective name. A plurality of video streams and a plurality of audio streams corresponding to the plurality of participant connections may be transmitted, and the plurality of video streams and the plurality of audio streams may be presented to at least one other conference participant.

Abstract: A plurality of talker embedding vectors may be derived that correspond to a plurality of talkers in an input audio stream. Each talker embedding vector may represent respective voice characteristics of a respective talker. The talker embedding vectors may be generated based on, for example, a pre-enrollment process or a cluster-based embedding vector derivation process. A plurality of instances of a personalized noise suppression model may be executed on the input audio stream. Each instance of the personalized noise suppression model may employ a respective talker embedding vector. A plurality of single-talker audio streams may be generated by the plurality of instances of the personalized noise suppression model. A plurality of single-talker transcriptions may be generated based on the plurality of single-talker audio streams. The plurality of single-talker transcriptions may be merged into a multi-talker output transcription.

Abstract: Joint noise and echo suppression may be performed for enhancing two-way audio communications. Audio data is captured at a communication device and audio data transmitted to the communication device from another communication device are used as input features to a trained machine learning model that uses the transmitted audio data as a reference signal to eliminate residual echo in the captured audio data when also suppressing noise in the captured audio data.

Abstract: A videoconference among a plurality of participants may be hosted, wherein the plurality of participants comprise Internet Protocol (IP)-connected participants and a Public Switched Telephone Network (PSTN)-connected participant. The IP-connected participants may send and receive audio content and video content of the videoconference via IP-based connections. The PSTN-connected participant may send and receive the audio content of the videoconference via a PSTN connection. Additional content from the videoconference may also be transmitted to the PSTN-connected participant, for example as text messages via the PSTN connection. The additional content may include, for example, images of a videoconference screen share, chat posts, polls, and the like. Images may be transmitted in the additional content based on video status change events, such as switching slides or pages in a screen share.

Abstract: Real-time low-complexity stereo speech enhancement with spatial cue preservation may be performed. A stereo speech enhancement system receives a stereo input signal (e.g., a left and right input signal). The stereo speech enhancement system estimates spatial cues for a target speaker and downmixes the stereo input signal into a monaural signal. A low-complexity model may then process the monaural signal to generate an enhanced monaural signal. The stereo speech enhancement system upmixes the enhanced monaural signal based on the estimated spatial cues for the target speaker, to generate an enhanced stereo output signal.

Abstract: This disclosure relates to systems and methods for measuring impedance characteristics of a cryogenic device under test (DUT). A channel select circuit can be configured in a first state to electrically isolate a channel output circuit from the cryogenic DUT and in a second state to electrically couple the channel output circuit to the cryogenic DUT, and at least one resistor can be positioned along a transmission path that couples a pattern generator circuit to a channel output circuit that includes the channel select circuit. A controller can be configured to cause respective test current signals to be provided along the transmission path when the channel select circuit is in respective first and second states to establish respective first and second voltages across the at least one resistor, determine first and second impedance characteristics of the transmission path for determining an impedance of the cryogenic DUT.

Abstract: This disclosure relates to systems and methods for current source temperature compensation for use during cryogenic electronic testing. A temperature compensation circuit can provide a temperature compensation signal to a current source circuit configured to provide an electrical current for testing a cryogenic device under test to compensate for temperature effects on the current source circuit based on a time constant adjustment signal. The time constant adjustment signal can adjust a time constant of the temperature compensation circuit to delay by a given amount of time that the temperature compensation circuit compensates for the temperature effects on the current source circuit. A controller can be configured to execute a temperature compensation method to provide the time constant adjustment signal based on at least one temperature signal characterizing a temperature of an environment that includes the current source circuit or a temperature of the current source circuit.

Abstract: A ground fault detection circuit can include a band-pass filter that can have a first node and a second node that can be coupled to an earth ground. The first node can be coupled to a local ground of an automatic test equipment (ATE) system for an electrical device that can be coupled via at least one wire to the ATE. The band-pass filter can be configured to pass and amplify a test current signal established at the first node in response to a coupling of one of a conductor of the at least one wire carrying the test current signal to the local ground, and a conductive element of the electrical device carrying the test current signal to the local ground. A fault alert signal can be provided to provide an indication of ground fault based on a comparison of the amplified test current signal.

Abstract: A current source circuit can include a first amplifier circuit and a second amplifier circuit. Each of the first and second amplifier circuits can be configured to generate respective amplifier output voltages based on a corresponding input voltage and respective feedback voltage. The current source circuit can further include a cross-coupling circuit that can include a first set of resistors and a second set of resistors. The first set of resistors can be configured to establish a first cross-coupling voltage based on the first amplifier output voltage and the second set of resistors can be configured to establish a second cross-coupling voltage based on the second amplifier output voltage. The first and second amplifier circuits can be configured to maintain the first and second cross-coupling voltage at a given voltage amplitude to provide a constant current at an output node of the current source circuit.

Abstract: A ground fault detection circuit can include a band-pass filter that can have a first node and a second node that can be coupled to an earth ground. The first node can be coupled to a local ground of an automatic test equipment (ATE) system for an electrical device that can be coupled via at least one wire to the ATE. The band-pass filter can be configured to pass and amplify a test current signal established at the first node in response to a coupling of one of a conductor of the at least one wire carrying the test current signal to the local ground, and a conductive element of the electrical device carrying the test current signal to the local ground. A fault alert signal can be provided to provide an indication of ground fault based on a comparison of the amplified test current signal.

Abstract: A current source circuit can include a first amplifier circuit and a second amplifier circuit. Each of the first and second amplifier circuits can be configured to generate respective amplifier output voltages based on a corresponding input voltage and respective feedback voltage. The current source circuit can further include a cross-coupling circuit that can include a first set of resistors and a second set of resistors. The first set of resistors can be configured to establish a first cross-coupling voltage based on the first amplifier output voltage and the second set of resistors can be configured to establish a second cross-coupling voltage based on the second amplifier output voltage. The first and second amplifier circuits can be configured to maintain the first and second cross-coupling voltage at a given voltage amplitude to provide a constant current at an output node of the current source circuit.

Abstract: Disclosed are methods to locate the posterior cancellous os of a pedicle on a vertebra and/or optimize implant trajectory in a subject, especially for spinal fusion surgery. The methods generally include: (a) directing a beam of laser light at or positioning a fiber that diffuses laser light over a pars interarticularis of the vertebra of the subject; and (b) acquiring photoacoustic signal for imaging the vertebra. The methods can further include selecting and/or adjusting parameters of the laser light such that the laser light penetrates a single layer of cortical bone covering the pars interarticularis into cancellous bone thereunder, reaching a quantifiable depth within the cancellous bone. Preferably, the quantifiable depth reaches at least about the full length of the pedicle.

Abstract: A starter fertilizer product combining manganese with P and Zn creates a previously unknown synergy in early plant growth and plant health.