Abstract: A method of training an audio separation network is provided. The method includes obtaining a first separation sample set, the first separation sample set including at least two types of audio with dummy labels, obtaining a first sample set by performing interpolation on the first separation sample set based on perturbation data, obtaining a second separation sample set by separating the first sample set using an unsupervised network, determining losses of second separation samples in the second separation sample set, and adjusting network parameters of the unsupervised network based on the losses of the second separation samples, such that a first loss of a first separation result outputted by an adjusted unsupervised network meets a convergence condition.

Abstract: A foldable electronic device includes a first housing and a second housing that are rotationally connected to each other by means of rotating shafts located on two sides, and an antenna. The first housing can switch between an unfolded state and a folded state relative to the second housing, and the antenna is disposed in a closed slot. The antenna includes a first antenna segment and a second antenna segment that are sequentially connected and disposed in a length direction of the antenna. One end of the first antenna segment is connected to a ground plate of the first housing. The first antenna segment extends from one end toward a direction in which an opening/closing region of the first housing and the second housing in the unfolded state is away from the first housing.

Abstract: A leakage-based physical unclonable function (L-PUF) device, a L-PUF array and applications thereof are provided. The L-PUF device includes a precharge circuit, two leaky devices and a sense amplifier. The two leaky devices are electrically connected to the precharge circuit respectively. Each leaky device includes a transistor having a control end electrically connected to ground, a first end electrically connected to the precharge circuit and a second end electrically connected to ground. The sense amplifier is electrically connected to the first end of each of the two leaky devices, and may generate a first output signal and a second output signal. The sense amplifier may switch between a first state and a second state based on a voltage difference between the first leaky device and the second leaky device, which is determined by a leakage current of the first leaky device and a leakage current of the second leaky device.

Abstract: A self-timed readout driver for a leakage-based physical unclonable function (L-PUF) device, a L-PUF array using the same, and applications thereof are provided. The self-timed readout driver includes a precharge transistor, an inverter and a leaky device. The precharge transistor has a control end, a first end and a second end. The inverter is electrically connected to the second end of the precharge transistor. The leaky device having a control end electrically connected to ground, a first end electrically connected to the second end of the precharge transistor, and a second end electrically connected to ground. The control end of the precharge transistor is configured to receive an input signal. The inverter is configured to generate a sense enable (SE) signal. The input signal and the SE signal may be used as two input signals for the L-PUF device.

Abstract: A wireless earphone assembly including a charging box and a wireless earphone is disclosed. The charging box includes a first casing and a second casing slidingly connected to the first casing, where the first casing has a first recess, a cavity connected to the first recess, and sound emitting holes connected to the first recess, and the cavity is sleeved on the second casing. The second casing has sound receiving holes opposite to the sound emitting holes and a channel disposed corresponding to the first recess, and the sound receiving holes are connected to the channel. The wireless earphone includes a sound emitting part and a sound receiving part opposite to the sound emitting part, and the sound emitting part is accommodated in the first recess.

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: This application provides a multi-band antenna. The antenna includes a feeder and a radiating element connected to the feeder, and further includes: a first notch structure, where the first notch structure is located on a side of the radiating element and is coupled to the radiating element; and a second notch structure, where the second notch structure is located on a far side of the first notch structure from the radiating element, and a far end of the second notch structure from the radiating element is grounded. The first notch structure may be selectively connected to the ground or to the second notch structure.

Abstract: An electronic device including a body and a female connector is disclosed. The Body has an opening and a positioning structure disposed corresponding to the opening. The female connector is disposed in the body corresponding to the opening and is pivotally connected to the positioning structure. A male connector is adapted to pass through the opening and plugged into the female connector, and the female connector is adapted to be driven by the male connector to rotate around a rotation axis passing through the positioning structure.

Abstract: An example system includes an electronic device and a server. The electronic device includes a display; a first communicator; and a first controller configured to: control to transmit, to the server, location data identifying locations of the electronic device. The server includes a second communicator; and a second controller configured to: control to receive the location data; identify a course of travel; link photograph images to locations on the course of travel; and control to transmit to the electronic device the course of travel and the photograph images. The first controller of the electronic device is configured to control to receive the course of travel and the photograph images and to control to display on the display, at the same time, a map image, the course of travel, and one or more of the photograph images linked to a selected location on the course of travel.

Abstract: An antenna design solution is provided. A metal frame and a PCB ground layer of an electronic device are used to form a slot. Through symmetric feeding and anti-symmetric feeding, the slot can be excited to generate two slot antenna patterns: a CM slot antenna pattern and a DM slot antenna pattern. In addition, the two slot antenna patterns share a same slot antenna radiator.

Abstract: An electronic device includes a decoupling member, a first radiator, a second radiator, a first feed unit, a second feed unit, and a rear cover. A gap is formed between the first radiator and the second radiator, the decoupling member is indirectly coupled to the first radiator and the second radiator, and the decoupling member is disposed on a surface of the rear cover. The decoupling member does not overlap a first projection, and the first projection is a projection of the first radiator in a first direction. The decoupling member does not overlap a second projection, and the second projection is a projection of the second radiator in the first direction. The first direction is a direction perpendicular to a plane on which the rear cover is located.

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 based AHS model, wherein the neural-network based AHS model is trained using a training audio signal, and output an AHS signal from the neural-network based AHS model in which AHS is applied to the audio signal, wherein the AHS signal is a version of the audio signal in which acoustic howling noise of the audio signal is suppressed and target audio of the audio signal is sustained.

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 based AEC model, and output an AEC signal from the neural-network based AEC model in which AEC is applied to the audio signal, and the AEC signal is a version of the audio signal in which acoustic echo noise of the audio signal is suppressed and target audio of the audio signal is sustained.

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: The present disclosure relates to the technical field of small nucleic acid drug delivery, and particularly discloses a compound, a conjugate and uses thereof. The present disclosure provides a nucleic acid drug targeted delivery monomer and conjugate and a preparation method thereof, the monomer and the conjugate which is formed by the monomer and has a specific design structure can specifically deliver an active drug (or small nucleic acid) to a cell receptor (or surface) in a targeted manner and can be combined with the receptor. The conjugate connected with the active drug (or small nucleic acid) can improve the cell penetration capability of the nucleic acid drug and enhance the stability of the nucleic acid drug in cells owing to the structural characteristics of the conjugate, and can effectively solve the problem of directional delivery of the drug.

Abstract: A method, computer system, and computer readable medium are provided for activating speech recognition based on keyword spotting (KWS). Waveform data corresponding to one or more speakers is received. One or more direction features are extracted from the received waveform data. One or more keywords are determined from the received waveform data based on the one or more extracted features. Speech recognition is activated based on detecting the determined keyword.

Abstract: Method, apparatus, and non-transitory storage medium for hybrid acoustic howling suppression based on a frequency filter model and a deep neural network are provided. The method may include receiving a speech signal, the speech signal including target speech, feedback, and noise, and inputting the speech signal into a trained hybrid neural-network based howling suppression model, wherein the trained hybrid neural-network based howling suppression model is trained using training speech signal and pre-processed acoustic feedback from a first frequency filter model. The method may also include generating an enhanced speech signal with suppressed howling as an output of the trained hybrid neural-network based howling suppression model, wherein the enhanced speech signal is used to update parameters of the first frequency filter model.

Abstract: Method, apparatus, and non-transitory storage medium for training a deep neural-network model jointly for acoustic echo suppression and acoustic howling suppression are provided. The method may include generating a teacher speech signal for training the deep neural-network model based on a input speech from a speech system and at least one reference signal. The deep neural-network model is trained jointly for both acoustic echo suppression and acoustic howling suppression by using the teacher speech signal and a correlation loss. During training of the deep neural-network model, the training task formulates a recurrent feedback suppression process as an instantaneous speech separation task using the teacher-forced training strategy.

Abstract: A circuit sleep method includes: writing all data stored in a memory unit into a current data-backup block and performing a check calculation on the data written into the current data-backup block to obtain a first verification value; powering down the circuit to make the circuit enter a sleep mode; restarting the circuit and determining whether the processing unit has written all the data stored in the memory unit into the current data-backup block before the circuit enters the sleep mode; performing the check calculation on the data stored in the current data-backup block to obtain a second verification value and comparing the first verification value with the second verification value; and writing back the data stored in the current data-backup block to the memory unit in a case that the first verification value and the second verification value are the same.

Abstract: A method including receiving an input comprising natural language texts; segmenting the natural language texts into sections; summarizing the natural language texts; developing a first model based on the plurality of sections and the summary of the natural language texts; identifying one or more salient sentences within the natural language texts using the first model; determining a sentence quality score based on how informative a salient sentence is; determining a sentence similarity score based on a salient sentence's similarity to another salient sentence; developing a second model based on the sentence quality score and the sentence similarity score; combining the first model and the second model into a final model; selecting sentences based on the final model; and generating an extractive summarization using the selected sentences.