Abstract: A CS CTC model may be initialed from a major language CTC model by keeping network hidden weights and replacing output tokens with a union of major and secondary language output tokens. The initialized model may be trained by updating parameters with training data from both languages, and a LID model may also be trained with the data. During a decoding process for each of a series of audio frames, if silence dominates a current frame then a silence output token may be emitted. If silence does not dominate the frame, then a major language output token posterior vector from the CS CTC model may be multiplied with the LID major language probability to create a probability vector from the major language. A similar step is performed for the secondary language, and the system may emit an output token associated with the highest probability across all tokens from both languages.

Abstract: To generate substantially domain-invariant and speaker-discriminative features, embodiments are associated with a feature extractor to receive speech frames and extract features from the speech frames based on a first set of parameters of the feature extractor, a senone classifier to identify a senone based on the received features and on a second set of parameters of the senone classifier, an attention network capable of determining a relative importance of features extracted by the feature extractor to domain classification, based on a third set of parameters of the attention network, a domain classifier capable of classifying a domain based on the features and the relative importances, and on a fourth set of parameters of the domain classifier; and a training platform to train the first set of parameters of the feature extractor and the second set of parameters of the senone classifier to minimize the senone classification loss, train the first set of parameters of the feature extractor to maximize the dom

Abstract: Embodiments are associated with a speaker-independent acoustic model capable of classifying senones based on input speech frames and on first parameters of the speaker-independent acoustic model, a speaker-dependent acoustic model capable of classifying senones based on input speech frames and on second parameters of the speaker-dependent acoustic model, and a discriminator capable of receiving data from the speaker-dependent acoustic model and data from the speaker-independent acoustic model and outputting a prediction of whether received data was generated by the speaker-dependent acoustic model based on third parameters.

Abstract: An electrowetting display panel includes a plurality of subpixels. Each of the plurality of subpixels having a subpixel area and an hater-subpixel area. The electrowetting display panel includes a first substrate, including a first insulating layer, a first electrode layer on the first insulating layer, and a first lyophobic layer on a side of the first electrode layer away from the first insulating layer; a second substrate facing the first substrate, including a second electrode layer, and a second lyophobic layer on the second electrode layer; and a plurality of sealing elements between the first substrate and the second substrate to define a plurality of fluid channels, each of the plurality of sealing elements being in the inter-subpixel area. The electrowetting display panel includes a first fluid reservoir and a respective one of the plurality of fluid channels between the first lyophobic layer and the second lyophobic layer.

Abstract: Embodiments are associated with conditional teacher-student model training. A trained teacher model configured to perform a task may be accessed and an untrained student model may be created. A model training platform may provide training data labeled with ground truths to the teacher model to produce teacher posteriors representing the training data. When it is determined that a teacher posterior matches the associated ground truth label, the platform may conditionally use the teacher posterior to train the student model. When it is determined that a teacher posterior does not match the associated ground truth label, the platform may conditionally use the ground truth label to train the student model. The models might be associated with, for example, automatic speech recognition (e.g., in connection with domain adaptation and/or speaker adaptation).

Abstract: To generate substantially condition-invariant and speaker-discriminative features, embodiments are associated with a feature extractor capable of extracting features from speech frames based on first parameters, a speaker classifier capable of identifying a speaker based on the features and on second parameters, and a condition classifier capable of identifying a noise condition based on the features and on third parameters. The first parameters of the feature extractor and the second parameters of the speaker classifier are trained to minimize a speaker classification loss, the first parameters of the feature extractor are further trained to maximize a condition classification loss, and the third parameters of the condition classifier are trained to minimize the condition classification loss.

Abstract: An electrowetting panel includes a base substrate; an electrode array layer, including a plurality of electrodes arranged into an array; an insulating hydrophobic layer; a microfluidic channel layer located on the base substrate. Each electrode of the plurality of electrodes is connected to a driving circuit, and a droplet can move along a first direction by applying an electric voltage on each electrode. The insulating hydrophobic layer is located on the electrode array layer, and the microfluidic channel layer is located on the insulating hydrophobic layer. The electrodes includes a plurality of driving electrodes and a plurality of detecting electrodes. Along the first direction, a number N of the driving electrodes is located between every two adjacent detecting electrodes, where N is a natural number. The electrowetting panel also includes a detecting chip electrically connected to the detecting electrodes.

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: Representative embodiments disclose machine learning classifiers used in scenarios such as speech recognition, image captioning, machine translation, or other sequence-to-sequence embodiments. The machine learning classifiers have a plurality of time layers, each layer having a time processing block and a depth processing block. The time processing block is a recurrent neural network such as a Long Short Term Memory (LSTM) network. The depth processing blocks can be an LSTM network, a gated Deep Neural Network (DNN) or a maxout DNN. The depth processing blocks account for the hidden states of each time layer and uses summarized layer information for final input signal feature classification. An attention layer can also be used between the top depth processing block and the output layer.

Abstract: A digital microfluidic chip and a digital microfluidic system. The digital microfluidic chip comprises: an upper substrate and a lower substrate arranged opposite to each other; multiple driving circuits and multiple addressing circuits disposed between the lower substrate and the upper substrate; and a control circuit, electrically connected to the driving circuits and the addressing circuits. The control circuit is configured to apply, in a driving stage, a driving voltage to each driving circuit, such that a droplet is controlled to move inside a droplet accommodation space according to a set path, measure, in a detection stage, after a bias voltage is applied to each addressing circuit, a charge loss amount of each addressing circuit, and to determine the position of the droplet according to the charge loss amount. The charge loss amount of each addressing circuit is related to the intensity of received external light.

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: 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: The use of user-specific data to process a biometric print, such that use of the biometric print is revoked by invalidating the user-specific data. The processed print is generated by performing one-way processing of the biometric print using the user-specific data. The processed print, not the biometric print, is then provided to the authentication system for later authentication of the user. During matching, the user later provides a current biometric, resulting in generation of a current biometric print. For each of multiple users, the user-specific is obtained for that user, and at least one processed print is generated for each user based on the current biometric print. The current processed prints are used by the authentication system to match against each of the enrolled processed prints. If a match is found, the user is identified as being the user associated with the matching enrolled print.

Abstract: Methods, systems, and computer programs are presented for training, with adversarial constraints, a student model for speech recognition based on a teacher model. One method includes operations for training a teacher model based on teacher speech data, initializing a student model with parameters obtained from the teacher model, and training the student model with adversarial teacher-student learning based on the teacher speech data and student speech data. Training the student model with adversarial teacher-student learning further includes minimizing a teacher-student loss that measures a divergence of outputs between the teacher model and the student model; minimizing a classifier condition loss with respect to parameters of a condition classifier; and maximizing the classifier condition loss with respect to parameters of a feature extractor. The classifier condition loss measures errors caused by acoustic condition classification. Further, speech is recognized with the trained student model.

Abstract: Non-limiting examples of the present disclosure describe advancements in acoustic-to-word modeling that improve accuracy in speech recognition processing through the replacement of out-of-vocabulary (OOV) tokens. During the decoding of speech signals, better accuracy in speech recognition processing is achieved through training and implementation of multiple different solutions that present enhanced speech recognition models. In one example, a hybrid neural network model for speech recognition processing combines a word-based neural network model as a primary model and a character-based neural network model as an auxiliary model. The primary word-based model emits a word sequence, and an output of character-based auxiliary model is consulted at a segment where the word-based model emits an OOV token. In another example, a mixed unit speech recognition model is developed and trained to generate a mixed word and character sequence during decoding of a speech signal without requiring generation of OOV tokens.

Abstract: Generally discussed herein are devices, systems, and methods for speech recognition. Processing circuitry can implement a connectionist temporal classification (CTC) neural network (NN) including an encode NN to receive an audio frame and generate a current encoded hidden feature vector, an attend NN to generate, based on a current encoded hidden feature vector and a first context vector from a previous time slice, a weight vector indicating an amount the current encoded hidden feature vector, a previous encoded hidden feature vector, and a future encoded hidden feature vector from a future time slice contribute to a current, second context vector, an annotate NN to generate the current, second context vector based on the weight vector, the current encoded hidden feature vector, the previous encoded hidden feature vector, and the future encoded hidden feature vector, and a normal NN to generate a normalized output vector based on the context vector.

Abstract: Conversion of a large-footprint DNN to a small-print DNN is performed using a variety of techniques, including split-vector quantization. The small-foot print DNN may be distributed to a variety of devices, including mobile devices. Further, the small-footprint DNN may aid a digital assistant on a device in interpreting speech input.

Abstract: A microfluidic chip configured to move a microdroplet along a predetermined path, includes a plurality of probe electrode groups spaced apart along the predetermined path. Each of the plurality of probe electrode groups includes a first probe electrode and a second probe electrode spaced apart from each other. The first probe electrode and the second probe electrode among a plurality of first probe electrodes and a plurality of second probe electrodes are configured to form an electrical loop with the microdroplet to thereby facilitate determining a position of the microdroplet.

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: Methods, systems, and computer programs are presented for training, with adversarial constraints, a student model for speech recognition based on a teacher model. One method includes operations for training a teacher model based on teacher speech data, initializing a student model with parameters obtained from the teacher model, and training the student model with adversarial teacher-student learning based on the teacher speech data and student speech data. Training the student model with adversarial teacher-student learning further includes minimizing a teacher-student loss that measures a divergence of outputs between the teacher model and the student model; minimizing a classifier condition loss with respect to parameters of a condition classifier; and maximizing the classifier condition loss with respect to parameters of a feature extractor. The classifier condition loss measures errors caused by acoustic condition classification. Further, speech is recognized with the trained student model.