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: Embodiments are associated with a speaker-independent attention-based encoder-decoder model to classify output tokens based on input speech frames, the speaker-independent attention-based encoder-decoder model associated with a first output distribution, a speaker-dependent attention-based encoder-decoder model to classify output tokens based on input speech frames, the speaker-dependent attention-based encoder-decoder model associated with a second output distribution, training of the second attention-based encoder-decoder model to classify output tokens based on input speech frames of a target speaker and simultaneously training the speaker-dependent attention-based encoder-decoder model to maintain a similarity between the first output distribution and the second output distribution, and performing automatic speech recognition on speech frames of the target speaker using the trained speaker-dependent attention-based encoder-decoder model.

Abstract: A compound of Formula I: is disclosed. A method of preparing the compound of Formula I is also disclosed. R is alkyl, haloalkyl, aryl, or substituted aryl.

Abstract: A method for extracting herbal medicine includes: step one, spray extraction; step two, pressure filtration and concentration; step three, spray and countercurrent precipitation; and step four, concentrating reduced pressure and drying.

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: 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: 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 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: 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: 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: 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 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: An LED unit lamp comprises a bracket, a lamp base with a LED lamp, a lampshade provided on the lamp base, and a control device. The lamp base is connected with the bracket via a movable connecting device, so as to permit the omnidirectional angular adjustment of the lamp base with respect to the bracket. A solar panel is disposed on the back side of the lamp base. A battery and a charge and discharge control device are provided in the lamp base. The solar panel is connected with the charge and discharge control device, the battery and the LED lamp via circuits.

Abstract: A computer enclosure includes a chassis and a cover. The chassis has a first hole, and the cover has a second hole which is substantially coaxial with the first hole. A securing means engages in the first and second holes for mounting the cover on the chassis. A shield is fixed on one of the chassis and the cover. The shield defines a through hole communicating an outer side of the shield with the securing means and a receiving hole intersecting the through hole. A rotating block is rotatably positioned in the receiving hole between the through hole and the securing means. The rotating block includes a blocking portion configured to block the through hole. The rotating block defines an access hole in the blocking portion. The access hole is configured to communicate the through hole with the securing means by rotating the block to align the access hole with the securing means.

Abstract: A computer enclosure includes a chassis and a cover. The chassis has a first hole, and the cover has a second hole which is substantially coaxial with the first hole. A securing means engages in the first and second holes for mounting the cover on the chassis. A shield is fixed on one of the chassis and the cover. The shield defines a through hole communicating an outer side of the shield with the securing means and a receiving hole intersecting the through hole. A rotating block is rotatably positioned in the receiving hole between the through hole and the securing means. The rotating block includes a blocking portion configured to block the through hole. The rotating block defines an access hole in the blocking portion. The access hole is configured to communicate the through hole with the securing means by rotating the block to align the access hole with the securing means.