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: An electronic device includes an antenna unit having an antenna body having a feed point and a ground point between a first end and a second end. The antenna body has an operating band with a resonance of a first wavelength. An electrical length of the antenna body from the feed point to the ground point is greater than or equal to ¼ and less than ½ of the first wavelength. An electrical length from the first end to the feed point is greater than or equal to ? and less than or equal to ¼ of the first wavelength. An electrical length from the second end to the ground point is greater than or equal to ? and less than or equal to ¼ of the first wavelength. The antenna body is adapted to operate in a slot mode and in a wire mode.

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 method, computer program, and computer system is provided for identifying a speaker in at text based work. Labeled and unlabeled instances corresponding to one or more speakers are extracted. Pseudo-labels are inferred for the extracted unlabeled instances based on the labeled instances. One or more of the unlabeled instances are labeled based on the inferred pseudo-labels.

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: A method and apparatus comprising computer code configured to cause a processor or processors to receive a text comprising a plurality of sentences, by a machine learning model, extract a nonverbal message from one of the sentences and add an annotation to the text, the annotation indicating the nonverbal message, and output a version of the text including the annotation.

Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to receive multiple audio signals obtained from ones of a plurality of microphones of a microphone array, implement an audio zooming based on the audio signals by selectively focusing and enhancing first ones of the audio signals and by attenuating other ones of the audio signals, and control an output of audio based on the audio zooming, and the audio zooming includes a consolidating of a plurality of directional features of the first ones of the audio signals within a field around the microphone array and a countering based on determining directional aspects of the other ones of the audio signals from outside of the field.

Abstract: An electronic device including an antenna structure is provided. A side frame between a first position and a second position of the electronic device is configured as a first radiator of the antenna structure. A side frame between the second position and a third position of the electronic device is configured as a second radiator of the antenna structure. A first slot is provided at the second position of the side frame. A second slot is formed between the second radiator and a ground. The first radiator extends in a first direction, and is spaced from the third radiator in a second direction. Projections of the third radiator and the first radiator in the second direction at least partially overlap. A first feed point is disposed on the third radiator or the first radiator, and the first feed point is configured to feed the antenna structure.

Abstract: A method performed by at least one processor of an acoustic howling suppression (AHS) system includes receiving, from an input source device, an audio signal. The method includes refining one or more parameters of a Kalman filter based on one or more neural networks. The method includes filtering the audio signal using the Kalman filter with the one or more refined parameters of the Kalman filter to reduce acoustic howling included in the audio signal.

Abstract: A model training method includes obtaining an image sample set and brief-prompt information; generating a content mask set according to the image sample set and the brief-prompt information; generating a to-be-trained image set according to the content mask set; obtaining, based on the image sample set and the to-be-trained image set, a predicted image set through a to-be-trained information synthesis model, the predicted image set comprising at least one predicted image, the predicted image being in correspondence to the image sample; and training, based on the predicted image set and the image sample set, the to-be-trained information synthesis model by using a target loss function, to obtain an information synthesis model.

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, train the neural-network based AHS model based on input signals which are recursively generated from the audio signal during training of the AHS model, 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 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 antenna apparatus includes a circuit board and an antenna body. The antenna body includes a first radiator and a second radiator that are indirectly coupled. The first radiator comprises a first stub and a second stub that are opposite to, but do not touch each other to form a first gap, the first stub and the second stub are located on a first side edge of the circuit board, a second gap is configured between the first stub and the first side edge, and also between the second stub and the first side edge. The second radiator is located on the circuit board to form a third gap in-between. A vertical projection of the second radiator is located on the first surface. The first stub and the second stub are electrically connected to reference ground of the circuit board separately.

Abstract: An audio processing apparatus and an audio processing method for dynamically adjusting an audio clock are provided. The audio processing apparatus includes a first interface, a buffer, a clock generator, a processor, and a second interface. The first interface receives audio data from the host. The buffer stores the audio data to generate a first audio packet and determines relationships between a data volume of the first audio packet and a first upper threshold and a first lower threshold. The second interface outputs the first audio packet and a clock signal to a codec apparatus. In response to the data volume of the first audio packet being less than the first lower threshold, the buffer outputs an underflow interrupt signal. In response to the data volume of the first audio packet being greater than the first upper threshold, the buffer outputs an overflow interrupt signal.

Abstract: There is included a method and apparatus comprising computer code for instance-wise adaptive knowledge injection in a pre-trained language model (PTLM) including determining a necessity of external knowledge in a plurality of queries of a first dataset based on a likelihood that a respective query is solved by internal knowledge of a target model. Then, the one or more queries determined to need external knowledge may be augmented with pieces of external knowledge. A combined dataset may be generated by combining the first dataset and the one or more augmented queries, and the combined dataset may be applied to the target model.

Abstract: Provided are an organic magnetic material and a semiconductor device including the same. According to the inventive concept, the organic magnetic material may include a material represented by Formula 1 below.

Abstract: In an antenna design, a metal frame of an electronic device and a printed circuit board (PCB) form a slot antenna radiator, where two common mode (CM) slot antenna modes of the slot antenna radiator are excited through anti-symmetrical feeding, so that when dual resonances and wideband coverage are implemented, specific absorption ratio (SAR) values in the two CM slot antenna modes are close.

Abstract: An apparatus includes logic circuitry that selects a retag transaction identifier for an original transaction identifier of an incoming transaction request, based on a plurality of sub-groups of retag tracking data. Each sub-group of retag tracking data is associated with a corresponding sub-group of retag transaction identifiers in a group of retag transaction identifiers. The logic circuitry retags the incoming transaction request with the selected retag transaction identifier (ID) by replacing the original transaction identifier associated with the incoming transaction request and sends the retagged incoming transaction request to a target. A returned response is received from the target. The retag transaction ID in the returned response is removed and replaced with the original transaction ID before being sent as a reply to the requesting unit. Associated methods are also presented.

Abstract: There is included a method and apparatus comprising computer code configured to cause a processor or processors to perform generating one or more aligned inventories, wherein the one or more aligned inventories are generated using one or more word sense inventories, obtaining a word in a context sentence, determining one or more semantic equivalence scores indicating semantic similarity between the word in the context sentence and each of one or more associated glosses in the one or more aligned inventories using a semantic equivalence recognizer model, and predicting a correct sense of the word in the context sentence based on the determined one or more semantic equivalence scores.

Abstract: The electronic device includes a composite antenna including a slot antenna and a wire antenna. A first strip-shaped conductor of the slot antenna includes a first ground part, a second ground part, and a feeding part. The first ground part and the second ground part are respectively two ends of the first strip-shaped conductor. The feeding part is located between the first ground part and the second ground part. A second strip-shaped conductor of the wire antenna includes a first end and a second end. The first end of the second strip-shaped conductor is electrically connected to the first ground part. The second end of the second strip-shaped conductor is an open end.