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: Methods of forming magnetic tunnel junction (MTJ) memory cells used in a magneto-resistive random access memory (MRAM) array are provided. A pre-clean process is performed to remove a metal oxide layer that may form on the top surface of the bottom electrodes of MTJ memory cells during the time the bottom electrode can be exposed to air prior to depositing MTJ layers. The pre-clean processes may include a remote plasma process wherein the metal oxide reacts with hydrogen radicals generated in the remote plasma.

Abstract: A method, computer program, and computer system is provided for an all-deep-learning based AEC system by recurrent neural networks. The model consists of two stages, echo estimation stage and echo suppression stage, respectively. Two different schemes for echo estimation are presented herein: linear echo estimation by multi-tap filtering on far-end reference signal and non-linear echo estimation by single-tap masking on microphone signal. A microphone signal waveform and a far-end reference signal waveform are received. An echo signal waveform is estimated based on the microphone signal waveform and a far-end reference signal waveform. A near-end speech signal waveform is output based on subtracting the estimated echo signal waveform from the microphone signal waveform, and echoes are suppressed within the near-end speech signal waveform.

Abstract: A top electrode of a magnetoresistive random access memory (MRAM) device over a magnetic tunnel junction (MTJ) is formed using a film of titanium nitride oriented in a (111) crystal structure rather than a top electrode which uses tantalum, tantalum nitride, and/or a multilayer including tantalum and tantalum nitride.

Abstract: A method of manufacturing a semiconductor device includes: forming a substrate over the substrate, the substrate defining a logic region and a memory region; depositing a bottom electrode layer across the logic region and the memory region; depositing a magnetic tunnel junction (MTJ) layer over the bottom electrode layer; depositing a first conductive layer over the MTJ layer; depositing a sacrificial layer over the first conductive layer; etching the sacrificial layer in the memory region to expose the first conductive layer in the memory region while keeping the first conductive layer in the logic region covered; depositing a second conductive layer in the memory region and the logic region; patterning the second conductive layer to expose the MTJ layer in the memory region; and etching the patterned second conductive layer and the MTJ layer to form a top electrode and an MTJ, respectively, in the memory region.

Abstract: An air purification equipment and an air purification method are provided, including a housing, a purification device, a guiding assembly, and an air driving device. The housing defines an air inlet and an air outlet, the air inlet imports air into the housing, the air outlet exports air out of the housing. The purification device purifies the air in the housing. The guiding assembly guides the air from the air inlet to the purification device. The air driving device drives the air from the air inlet to the purification device, and drives the air to the air outlet. The guiding assembly forms a first channel and a second channel, the first channel is corresponding to the air inlet, the first channel guides the air to flow into the second channel, at least a part of the purification device is positioned in the second channel.

Abstract: A method for forming a semiconductor device structure is provided. The method includes providing a substrate, a fin, and a semiconductor layer. The fin is over the substrate, the semiconductor layer is over the fin, the substrate and the fin are made of different materials, and the fin and the semiconductor layer are made of different materials. The method includes forming a dielectric layer over the semiconductor layer and the fin. The method includes forming a semiconductor structure over a sidewall of the dielectric layer. The method includes removing a first top portion of the dielectric layer over a top surface of the semiconductor layer. The method includes forming a gate over the semiconductor layer, the dielectric layer, and the semiconductor structure.

Abstract: A method, computer program, and computer system is provided for an all-deep-learning based AEC system by recurrent neural networks. The model consists of two stages, echo estimation stage and echo suppression stage, respectively. Two different schemes for echo estimation are presented herein: linear echo estimation by multi-tap filtering on far-end reference signal and non-linear echo estimation by single-tap masking on microphone signal. A microphone signal waveform and a far-end reference signal waveform are received. An echo signal waveform is estimated based on the microphone signal waveform and a far-end reference signal waveform. A near-end speech signal waveform is output based on subtracting the estimated echo signal waveform from the microphone signal waveform, and echoes are suppressed within the near-end speech signal waveform.

Abstract: An integrated circuit includes a complimentary field effect transistor (CFET). The CFET includes a first transistor having a first semiconductor nanostructure corresponding to a channel region of the first semiconductor nanostructure and a first gate metal surrounding the second semiconductor nanostructure. The CFET includes a transistor including a second semiconductor nanostructure above the first semiconductor nanostructure and a second gate metal surrounding the second semiconductor nanostructure. The CFET includes an isolation structure between the first and second semiconductor nanostructures.

Abstract: A fixing device for accurately fixing an optical assembly to a rear housing of an electronic device fixes the optical assembly in a predetermined position and includes a cover plate. The cover plate defines a hole and a limiting portion. The hole corresponds to a photosensitive portion of the optical assembly and the photosensitive portion is configured to protrude out of the cover plate. The limiting portion is configured to limit a movement of the optical assembly away from the rear housing before being fixed in position. The fixing device fixes the optical assembly in the predetermined position so that the assembly accuracy and efficiency are improved. An optical module including the fixing device, and an electronic device including the optical module are also provided.

Abstract: A plural-fans driving apparatus is provided to drive a first fan and a second fan, and the first fan and the second fan are three-phase fans. The plural-fans driving apparatus includes a controller, a first three-phase motor driver structure, a second three-phase motor driver structure, and a protection and input interface circuit. The protection and input interface circuit is coupled to the first three-phase motor driver structure and the second three-phase motor driver structure, and protects the first three-phase motor driver structure and the second three-phase motor driver structure. The controller controls the first three-phase motor driver structure to drive the first fan, and controls the second three-phase motor driver structure to drive the second fan.

Abstract: The present disclosure describes an exemplary method that can prevent or reduce out-diffusion of Cu from interconnect layers to magnetic tunnel junction (MTJ) structures. The method includes forming an interconnect layer over a substrate that includes an interlayer dielectric stack with openings therein; disposing a metal in the openings to form corresponding conductive structures; and selectively depositing a diffusion barrier layer on the metal. In the method, selectively depositing the diffusion barrier layer includes pre-treating the surface of the metal; disposing a precursor to selectively form a partially-decomposed precursor layer on the metal; and exposing the partially-decomposed precursor layer to a plasma to form the diffusion barrier layer. The method further includes forming an MTJ structure on the interconnect layer over the diffusion barrier layer, where the bottom electrode of the MTJ structure is aligned to the diffusion barrier layer.

Abstract: A method, computer program, and computer system for separating a target voice from among a plurality of speakers is provided. Video data associated with the plurality of speakers and audio data associated with each of the one or more speakers are received. Video feature data is extracted from the received video data. The target voice is identified from among the plurality of speakers based on the received audio data and the extracted video feature data.

Abstract: Embodiments of the present disclosure relate to forming a nanosheet multi-channel device with an additional spacing layer and a hard mask layer. The additional spacing layer provides a space for an inner spacer above the topmost channel. The hard mask layer functions as an etch stop during metal gate etch back, providing improve gate height control.

Abstract: A heat dissipation assembly is disclosed and includes a frame and a fan. The frame includes a heat conduction channel and an airflow intake. The heat conduction channel is communication with an exterior through airflow intake. The frame includes a first plane, a second plane and an inclined plane. The first plane is disposed adjacent to the airflow intake. The inclined plane is connected between the first plane and the second plane. The second plane includes an inlet. The heat conduction channel is in communication between the airflow intake and the inlet. A cross-section area of the heat conduction channel adjacent to the airflow intake is greater than that of the heat conduction channel adjacent to the inlet. The fan is spatially corresponding to the inlet, and assembled with the frame to form an outlet in communication with the airflow intake and the heat conduction channel through the inlet.

Abstract: There is included a method and apparatus comprising computer code for generating enhanced target speech from audio data, performed by a computing device, the method comprising: receiving audio data corresponding to one or more speakers; generating estimated an target speech, an estimated noise, and an estimated echo simultaneously based on the audio data using a jointly trained complex ratio mask; predicting frame-level multi-tap time-frequency (T-F) spatio-temporal-echo filter weights based on the estimated target speech, the estimated noise, and the estimated echo using a trained neural network model; and predicting enhanced target speech based on the frame-level multi-tap T-F spatio-temporal-echo filter weights.

Abstract: The present disclosure describes an exemplary method that can prevent or reduce out-diffusion of Cu from interconnect layers to magnetic tunnel junction (MTJ) structures. The method includes forming an interconnect layer over a substrate that includes an interlayer dielectric stack with openings therein; disposing a metal in the openings to form corresponding conductive structures; and selectively depositing a diffusion barrier layer on the metal. In the method, selectively depositing the diffusion barrier layer includes pre-treating the surface of the metal; disposing a precursor to selectively form a partially-decomposed precursor layer on the metal; and exposing the partially-decomposed precursor layer to a plasma to form the diffusion barrier layer. The method further includes forming an MTJ structure on the interconnect layer over the diffusion barrier layer, where the bottom electrode of the MTJ structure is aligned to the diffusion barrier layer.

Abstract: A method, computer program, and computer system is provided for an all-deep-learning based AEC system by recurrent neural networks. The model consists of two stages, echo estimation stage and echo suppression stage, respectively. Two different schemes for echo estimation are presented herein: linear echo estimation by multi-tap filtering on far-end reference signal and non-linear echo estimation by single-tap masking on microphone signal. A microphone signal waveform and a far-end reference signal waveform are received. An echo signal waveform is estimated based on the microphone signal waveform and a far-end reference signal waveform. A near-end speech signal waveform is output based on subtracting the estimated echo signal waveform from the microphone signal waveform, and echoes are suppressed within the near-end speech signal waveform.

Abstract: A data processing method includes the following steps: generating a machine-learning parameter and obtaining a storage parameter code, wherein the storage parameter code corresponds to a storage space; receiving the machine-learning parameter and the storage parameter code, and storing the machine-learning parameter in the storage space according to the storage parameter code, and generating an event notification when the machine-learning parameter is modified; and generating a loading request according to the event notification, and the loading request is used to request the modified machine-learning parameter, wherein after the loading request is generated, the modified machine-learning parameter is downloaded from the storage space corresponding to the storage parameter code.