Abstract: Improvements in speaker identification and verification are provided via an attention model for speaker recognition and the end-to-end training thereof. A speaker discriminative convolutional neural network (CNN) is used to directly extract frame-level speaker features that are weighted and combined to form an utterance-level speaker recognition vector via the attention model. The CNN and attention model are join-optimized via an end-to-end training algorithm that imitates the speaker recognition process and uses the most-similar utterances from imposters for each speaker.

Abstract: Systems and methods can be implemented to conduct speaker-invariant training for speech recognition in a variety of applications. An adversarial multi-task learning scheme for speaker-invariant training can be implemented, aiming at actively curtailing the inter-talker feature variability, while maximizing its senone discriminability to enhance the performance of a deep neural network (DNN) based automatic speech recognition system. In speaker-invariant training, a DNN acoustic model and a speaker classifier network can be jointly optimized to minimize the senone (triphone state) classification loss, and simultaneously mini-maximize the speaker classification loss. A speaker invariant and senone-discriminative intermediate feature is learned through this adversarial multi-task learning, which can be applied to an automatic speech recognition system. Additional systems and methods are disclosed.

Abstract: A pixel driving circuit includes a pixel unit including a blue sub-pixel connected to a data line to receive a data voltage, and a limit circuit connected between the data line and a reference voltage line configured to transfer a fixed DC voltage, the limit circuit being configured to limit the received data voltage when the received data voltage exceeds a voltage threshold.

Abstract: The present disclosure provides a digital microfluidic chip, a fabricating method and a control method thereof. The digital microfluidic chip includes: at least one substrate, a capillary channel, a plurality of first electrothermal components and a plurality of first switch elements. The capillary channel is disposed at at least one of the substrate; the plurality of first electrothermal components are disposed at the substrate and distributed to be spaced apart in an extending direction of the capillary channel; and each of the first switch elements is coupled with a current circuit with which the first electrothermal components are coupled, and receiving a control signal to control closure of a current circuit coupled with which the plurality of first electrothermal components are coupled.

Abstract: A method includes obtaining a source domain having labels for source domain speech input features, obtaining a target domain having target domain speech input features without labels, extracting private components from each of the source and target domain speech input features, extracting shared components from the source and target domain speech input features using a shared component extractor, and reconstructing the source and target input features as a regularization of private component extraction.

Abstract: Representative embodiments disclose mechanisms to separate and recognize multiple audio sources (e.g., picking out individual speakers) in an environment where they overlap and interfere with each other. The architecture uses a microphone array to spatially separate out the audio signals. The spatially filtered signals are then input into a plurality of separators, so each signal is input into a corresponding signal. The separators use neural networks to separate out audio sources. The separators typically produce multiple output signals for the single input signals. A post selection processor then assesses the separator outputs to pick the signals with the highest quality output. These signals can be used in a variety of systems such as speech recognition, meeting transcription and enhancement, hearing aids, music information retrieval, speech enhancement and so forth.

Abstract: A frequency-sweep experimental method for predicting noise of a power capacitor, comprises steps of: (1) loading the capacitor with a sine voltage excitation with a loading frequency value of ½ to 50 times of a power frequency in sequence, at an increase of half of the power frequency for each time, and measuring vibration velocity at various points on a case of the capacitor; (2) under each loading frequency, dividing vibration velocity by a square of each voltage applied; (3) calculating frequency spectrum of a square of the voltage of the capacitor according to the voltage and a current of the capacitor; (4) multiplying the frequency spectrum of the square of the voltage of the capacitor by the electromechanical vibration frequency response function value of the capacitor to obtain a vibration velocity spectrum of the case of the capacitor; (5) calculating acoustical power of the noise.

Abstract: A touch display panel and a display device are disclosed. The touch display panel includes a plurality of touch signal lines and a plurality of data lines disposed in a display area, and a plurality of lead terminals disposed in a peripheral area. The plurality of lead terminals includes a plurality of first terminals respectively connected to the plurality of data lines and a plurality of second terminals respectively connected to the plurality of touch signal lines. The plurality of lead terminals are arranged in a matrix. The first terminals and the second terminals are provided in a row direction or a column direction so as to be consistent with the sequence in which the data lines connected to the first terminals and the touch signal lines connected to the second terminals are arranged.

Abstract: Improvements in speech recognition in a new domain are provided via the student/teacher training of models for different speech domains. A student model for a new domain is created based on the teacher model trained in an existing domain. The student model is trained in parallel to the operation of the teacher model, with inputs in the new and existing domains respectfully, to develop a neural network that is adapted to recognize speech in the new domain. The data in the new domain may exclude transcription labels but rather are parallelized with the data analyzed in the existing domain analyzed by the teacher model. The outputs from the teacher model are compared with the outputs of the student model and the differences are used to adjust the parameters of the student model to better recognize speech in the second domain.

Abstract: The present disclosure provides a touch display panel including a a display substrate, a touch electrode layer, and an insulating layer located between the display substrate and the touch electrode layer. The touch electrode layer includes a touch graph with grooves. The touch display panel further includes a transparent conducting film layer insulated from the touch electrode layer by the insulating layer.

Abstract: Embodiments of the present disclosure provide an array substrate and a manufacturing method thereof, and a display device. The array substrate includes a plurality of pixel structures. The pixel structure includes a gate electrode, a gate electrode insulating layer, an active layer, source and drain electrodes, and a passivation layer which are sequentially stacked. The pixel structure further includes a first electrode and a second electrode. The first electrode is located between the gate electrode insulating layer and the passivation layer, and electrically connected to one of the source electrode and the drain electrode. The second electrode is located above the passivation layer. A first via passing through the passivation layer is provided, and the second electrode is electrically connected to one of the source electrode and the drain electrode through the first via.

Abstract: Improvements in speaker identification and verification are provided via an attention model for speaker recognition and the end-to-end training thereof. A speaker discriminative convolutional neural network (CNN) is used to directly extract frame-level speaker features that are weighted and combined to form an utterance-level speaker recognition vector via the attention model. The CNN and attention model are join-optimized via an end-to-end training algorithm that imitates the speaker recognition process and uses the most-similar utterances from imposters for each speaker.

Abstract: The disclosure provides a shift register unit, a shift register, a driving method and an array substrate. The shift register unit may comprise a touch-controlled circuit comprising a touch-controlled turning-on module and a touch-controlled turning-off module, wherein a control of the touch-controlled turning-on module is connected to a touch-controlled turning-on signal, an input is connected to a negative power supply signal, and an output is connected to an output terminal, and the touch-controlled turning-on signal is a pulse signal at a start of a touch controlling period; and a control of the touch-controlled turning-off module is connected to a touch-controlled turning-off signal, an input of the touch-controlled turning-off module is connected to a positive power supply signal, and an output of the touch-controlled turning-off module is connected to the output terminal, wherein the touch-controlled turning-off signal is a pulse signal at an end of the touch controlling period.

Abstract: A touch display panel and a display device are disclosed which achieve touch function and narrow bezel function while the required number of the vertical wiring is reduced and the aperture ratio of the touch display panel is increased.

Abstract: An electronic paper display panel, including a first and second substrate; an electrophoresis layer arranged between the first and second substrates, the electrophoresis layer including black electrophoretic particle, white electrophoretic particle and at least one color electrophoretic particle; a first electrode layer arranged at a side of the first substrate facing the second substrate including multiple first electrodes; a second electrode layer arranged at a side of the second substrate facing the first substrate including multiple second electrodes; and a drive circuit; multiple pixel areas correspond multiple second electrodes; each first electrode includes a first sub-electrode and a second sub-electrode placed in same pixel area, which are insulated from each other, correspond to one second electrode and are connected with drive circuit, the first sub-electrode receives voltage signal different from voltage signal the second sub-electrode receives; the first electrode is common electrode and the seco

Abstract: Systems and methods for identifying a false representation of a human face are provided. In one example, a method for identifying a false representation of a human face includes receiving one or more data streams captured by one or more sensors sensing a candidate face. In a plurality of stages that each comprises a different analysis, one or more of the data streams are analyzed, and the stages comprise determining whether a plurality of candidate face depth points lies on a single flat plane or a curving plane. Based at least in part on determining that the plurality of candidate face depth points lies on the single flat plane, an indication of the false representation of the human face is outputted.

Abstract: Examples are disclosed herein that relate to detecting spoofed human faces. One example provides a computing device comprising a processor configured to compute a first feature distance between registered image data of a human face in a first spectral region and test image data of the human face in the first spectral region, compute a second feature distance between the registered image data and test image data of the human face in a second spectral region, compute a test feature distance between the test image data in the first spectral region and the test image data in the second spectral region, determine, based on a predetermined relationship, whether the human face to which the test image data in the first and second spectral regions corresponds is a real human face or a spoofed human face, and modify a behavior of the computing device.

Abstract: Systems and methods for speech recognition incorporating environmental variables are provided. The systems and methods capture speech to be recognized. The speech is then recognized utilizing a variable component deep neural network (DNN). The variable component DNN processes the captured speech by incorporating an environment variable. The environment variable may be any variable that is dependent on environmental conditions or the relation of the user, the client device, and the environment. For example, the environment variable may be based on noise of the environment and represented as a signal-to-noise ratio. The variable component DNN may incorporate the environment variable in different ways. For instance, the environment variable may be incorporated into weighting matrices and biases of the DNN, the outputs of the hidden layers of the DNN, or the activation functions of the nodes of the DNN.

Abstract: Systems and methods for identifying a false representation of a human face are provided. In one example, a method for identifying a false representation of a human face includes receiving a plurality of different data streams captured by a respective plurality of sensors of differing sensor types sensing a candidate face. In a cascading plurality of stages, one or more of the different data streams are analyzed, wherein each of the stages comprises a different analysis. In one of the cascading plurality of stages, the method determines that one or more of the different data streams corresponds to a false representation of the human face. Based on determining that one or more of the different data streams corresponds to a false representation of a human face, an indication of the false representation is outputted.

Abstract: A shift register and a driving method therefor, a gate driving circuit and a display apparatus. The shift register comprises a trigger reset module, a pull-up module, a first capacitor and a pull-down module, and further comprises a denoising module. The pull-up module is used for pulling up a signal output from an output terminal of the shift register and a signal output from a transmission signal output terminal. The pull-down module is used for pulling down a signal output from the output terminal of the shift register and the signal output from the transmission signal output terminal. The denoising module is used for cutting off the connection path between the transmission signal output terminal and a second terminal of the first capacitor in a pull-down phase.