Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to receive an audio signal obtained from a microphone, input the audio signal into a neural-network pipeline, the neural-network pipeline including a convolutional network that receives the audio signal and provides a first output of the convolutional network to an enhancer, the enhancer including a deep complex convolutional recurrent network that receives the first output along with a mel spectrogram of the audio signal and outputs a second output to at least one of a vocoder and a decoder, and control an output of an enhanced audio signal from the at least one of the vocoder and the decoder.

Abstract: Methods and apparatus of controlling a temperature of components in a process chamber that is heated by a plasma or a heater and cooled by a coolant flow through a heat exchanger. An apparatus, for example, can include a chuck assembly and/or a plasma source including a respective cooling plate; a proportional bypass valve connected between the respective cooling plate and a heat exchanger; a temperature sensor configured to measure a temperature of the coolant through the outlet channel of the respective cooling plate; and a controller that receives a measured temperature from the temperature sensor measuring, and in response to receiving the measured temperature controls a rate of flow of the coolant through the first coolant output line and the second coolant output line of the proportional bypass valve.

Abstract: A method includes receiving, by a first encoder, an original speech segment, receiving, by a second encoder, an augmented speech segment of the original speech segment, generating, by the first encoder, a first speaker representation based on the original speech segment, generating, by the second encoder, a second speaker representation based on the augmented speech segment, and generating a contrastive loss based on the first speaker representation and the second speaker representation.

Abstract: An advanced temperature control system and method are described for a wafer carrier in a plasma processing chamber. In one example a heat exchanger provides a temperature controlled thermal fluid to a fluid channel of a workpiece carrier and receives the thermal fluid from the fluid channel. A proportional valve is between the heat exchanger and the fluid channel to control the rate of flow of thermal fluid from the heat exchanger to the fluid channel. A pneumatic valve is also between the heat exchanger and the fluid channel also to control the rate of flow of thermal fluid from the heat exchanger and the fluid channel. A temperature controller receives a measured temperature from a thermal sensor of the carrier and controls the proportional valve and the pneumatic valve in response to the measured temperature to adjust the rate of flow of the thermal fluid.

Abstract: An electronic device manufacturing system capable of obtaining metrology data generated using metrology equipment located within a process chamber that performs a deposition process on a substrate according to a process recipe, wherein the process recipe comprises a plurality of setting parameters, and wherein the deposition process generates a plurality of film layers on a surface of the substrate. The manufacturing system can further generate a correction profile based on the metrology data. The manufacturing system can further generate an updated process recipe by applying the correction profile to the process recipe. The manufacturing system can further cause an etch process to be performed on the substrate according to the updated process recipe.

Abstract: A substrate processing system includes a process chamber, one or more robot, a substrate measurement system, and a computing device. The process chamber may process a substrate that will comprise a film and/or feature after the processing. The one or more robot, to move the substrate from the process chamber to a substrate measurement system. The substrate measurement system may measure the film and/or feature on the substrate and generate a profile map of the film and/or feature. The computing device may process data from the profile map using a first trained machine learning model, wherein the first trained machine learning model outputs a first chamber component condition estimation for a first chamber component of the process chamber. The computing device may then determine whether to perform maintenance on the first chamber component of the process chamber based at least in part on the first chamber component condition estimation.

Abstract: A method of end-to-end speaker diarization (EESD) using neural speaker clustering, performed by at least one processor, is provided. The method includes generating a set of speech labels corresponding to a set of speakers based on an input stream. The speech labels indicate whether dialogue of a speaker is speech or non-speech. The method further includes generating dialogue based on the set of speakers, extracting speaker embeddings from the dialogue, mapping the speaker embeddings to a cluster identification (ID), an overlapped speech value, or a non-speech value based on a neural network, and outputting EESD labels based on the mapping.

Abstract: Metrology slot plates, processing chamber lids and processing chambers having metrology slot plates are described. Each of the metrology slot plates independently comprises one or more of a plate blank, a reflectometer, a capacitance sensor, a gas flow meter, a manometer, a pyrometer, a distance sensor (laser) or an emissometer.

Abstract: An unsupervised text to speech system utilizing a lexicon to map input text to the phoneme sequence, which is expanded to the frame-level forced alignment with a speaker-dependent duration model. An alignment mapping module that converts the forced alignment to the unsupervised alignment (UA). Afterword, a Conditional Disentangled Sequential Variational Auto-encoder (C-DSVAE), serving as the self-supervised TTS AM, takes the predicted UA and a target speaker embedding to generate the mel spectrogram, which is ultimately converted to waveform with a neural vocoder.

Abstract: Implementations disclosed describe a system including a light source, an optical sensor, and a processing device. The light source directs, during a first time, a probe light into a processing chamber through a window. The light source ceases, during a second time, directing the probe light into the processing chamber through the window. The optical sensor detects, during the first time, a first intensity of a first light. The first light includes a portion of the probe light reflected from the window and a light transmitted from an environment of the processing chamber through the window. The optical sensor detects, during the second time, a second intensity of a second light. The second light includes the light transmitted from the environment of the processing chamber through the window. The processing device determines, using the first intensity and the second intensity, a transmission coefficient of the window.

Abstract: A pixel circuit and a display panel. The pixel circuit includes a drive circuit, a first reset circuit, a data write circuit, a first light emission control circuit, a second light emission control circuit and a storage circuit. The first reset circuit is connected to the drive circuit; the data write circuit is connected to the drive circuit; the first light emission control circuit is connected in series with a light-emitting element between a positive voltage power supply and the drive circuit; the second light emission control circuit is connected between the drive circuit and a negative voltage power supply; the storage circuit is electrically connected to the drive circuit.

Abstract: A driving method and apparatus of a display panel, and a display device. The method includes the following: acquiring display data of a frame, where the display data includes grayscale values corresponding to subpixels emitting light having at least two colors; calculating a typical grayscale value corresponding to subpixels emitting light having each color according to the display data, where the typical grayscale value represents the overall grayscale level of the subpixels emitting light having each color, and determining a common supply voltage corresponding to the subpixels emitting light having each color according to the typical grayscale value.

Abstract: A pixel circuit includes a drive circuit, a data write circuit, and a light-emitting device; the data write circuit is connected between a data line and the drive circuit and is configured to transmit a data voltage of the data line to the drive circuit during a data writing stage; the drive circuit is connected between a power line and a first electrode of the light-emitting device, a second electrode of the light-emitting device is connected to the data line, and during a light emission stage, a second power voltage is transmitted to the second electrode of the light-emitting device through the data line connected to the second electrode of the light-emitting device.

Abstract: Metrology slot plates, processing chamber lids and processing chambers having metrology slot plates are described. Each of the metrology slot plates independently comprises one or more of a plate blank, a reflectometer, a capacitance sensor, a gas flow meter, a manometer, a pyrometer, a distance sensor (laser) or an emissometer.

Abstract: Implementations disclosed describe a system including a light source, an optical sensor, and a processing device. The light source directs, during a first time, a probe light into a processing chamber through a window. The light source ceases, during a second time, directing the probe light into the processing chamber through the window. The optical sensor detects, during the first time, a first intensity of a first light. The first light includes a portion of the probe light reflected from the window and a light transmitted from an environment of the processing chamber through the window. The optical sensor detects, during the second time, a second intensity of a second light. The second light includes the light transmitted from the environment of the processing chamber through the window. The processing device determines, using the first intensity and the second intensity, a transmission coefficient of the window.

Abstract: An unsupervised text to speech system utilizing a lexicon to map input text to the phoneme sequence, which is expanded to the frame-level forced alignment with a speaker-dependent duration model. An alignment mapping module that converts the forced alignment to the unsupervised alignment (UA). Afterword, a Conditional Disentangled Sequential Variational Auto-encoder (C-DSVAE), serving as the self-supervised TTS AM, takes the predicted UA and a target speaker embedding to generate the mel spectrogram, which is ultimately converted to waveform with a neural vocoder.

Abstract: An electrostatic chuck is described that has radio frequency coupling suitable for use in high power plasma environments. In some examples, the chuck includes a base plate, a top plate, a first electrode in the top plate proximate the top surface of the top plate to electrostatically grip a workpiece, and a second electrode in the top plate spaced apart from the first electrode, the first and second electrodes being coupled to a power supply to electrostatically charge the first electrode.

Abstract: A method of acoustic echo suppression using a recurrent neural network, performed by at least one processor, is provided. The method includes receiving a microphone signal and a far-end reference signal, estimating an echo suppressed signal and an echo signal based on the microphone signal and the far-end reference signal, estimating enhancement filters for the microphone signal based on the echo suppressed signal and the echo signal, generating an enhanced signal based on the enhancement filters, and adjusting the enhanced signal using automatic gain control (AGC) and outputting the adjusted signal.

Abstract: A method of acoustic echo suppression using a recurrent neural network, performed by at least one processor, is provided. The method includes receiving a microphone signal and a far-end reference signal, estimating an echo suppressed signal and an echo signal based on the microphone signal and the far-end reference signal, estimating enhancement filters for the microphone signal based on the echo suppressed signal and the echo signal, generating an enhanced signal based on the enhancement filters, and adjusting the enhanced signal using automatic gain control (AGC) and outputting the adjusted signal.