Abstract: The computing system trains an end-to-end (E2E) automatic speech recognition (ASR) model, using a transformer-transducer-based deep neural network that comprises a transformer encoder network and a transducer predictor network. The E2E ASR model is trained to have one or more adjustable hyperparameters that are configured to dynamically adjust an efficiency or a performance of the E2E ASR model when the E2E ASR model is deployed onto a device or executed by the device, by identifying one or more conditions of the device associated with computational power of the device and setting at least one of the one or more adjustable hyperparameters based on one or more conditions of the device.

Abstract: The computing system trains an end-to-end (E2E) automatic speech recognition (ASR) model, using a transformer-transducer-based deep neural network that comprises a transformer encoder network and a transducer predictor network. The E2E ASR model is trained to have one or more adjustable hyperparameters that are configured to dynamically adjust an efficiency or a performance of the E2E ASR model when the E2E ASR model is deployed onto a device or executed by the device, by identifying one or more conditions of the device associated with computational power of the device and setting at least one of the one or more adjustable hyperparameters based on one or more conditions of the device.

Abstract: A computing system is configured to generate a transformer-transducer-based deep neural network. The transformer-transducer-based deep neural network comprises a transformer encoder network and a transducer predictor network. The transformer encoder network has a plurality of layers, each of which includes a multi-head attention network sublayer and a feed-forward network sublayer. The computing system trains an end-to-end (E2E) automatic speech recognition (ASR) model, using the transformer-transducer-based deep neural network. The E2E ASR model has one or more adjustable hyperparameters that are configured to dynamically adjust an efficiency or a performance of E2E ASR model when the E2E ASR model is deployed onto a device or executed by the device.

Abstract: This invention is in the area of synthesizing pyrimidine-based compounds useful in the treatment of disorders involving abnormal cellular proliferation, including but not limited to tumors and cancers.

Abstract: Provided in this disclosure are methods for the synthesis of substituted 2-arylcyclopropylamines and 2-heteroarylcyclopropylamines and related compounds. Also provided are methods for reduction of thioesters to aldehydes, and methods for reductive amination of cyclopropylamines.

Abstract: A computer device is provided that includes one or more processors configured to receive an end-to-end (E2E) model that has been trained for automatic speech recognition with training data from a source-domain, and receive an external language model that has been trained with training data from a target-domain. The one or more processors are configured to perform an inference of the probability of an output token sequence given a sequence of input speech features. Performing the inference includes computing an E2E model score, computing an external language model score, and computing an estimated internal language model score for the E2E model. The estimated internal language model score is computed by removing a contribution of an intrinsic acoustic model. The processor is further configured to compute an integrated score based at least on E2E model score, the external language model score, and the estimated internal language model score.

Abstract: A computing system is configured to generate a transformer-transducer-based deep neural network. The transformer-transducer-based deep neural network comprises a transformer encoder network and a transducer predictor network. The transformer encoder network has a plurality of layers, each of which includes a multi-head attention network sublayer and a feed-forward network sublayer. The computing system trains an end-to-end (E2E) automatic speech recognition (ASR) model, using the transformer-transducer-based deep neural network. The E2E ASR model has one or more adjustable hyperparameters that are configured to dynamically adjust an efficiency or a performance of E2E ASR model when the E2E ASR model is deployed onto a device or executed by the device.

Abstract: Provided in this disclosure are methods for the synthesis of substituted 2-arylcyclopropylamines and 2-heteroarylcyclopropylamines and related compounds. Also provided are methods for reduction of thioesters to aldehydes, and methods for reductive animation of cyclopropylamines.

Abstract: A computer device is provided that includes one or more processors configured to receive an end-to-end (E2E) model that has been trained for automatic speech recognition with training data from a source-domain, and receive an external language model that has been trained with training data from a target-domain. The one or more processors are configured to perform an inference of the probability of an output token sequence given a sequence of input speech features. Performing the inference includes computing an E2E model score, computing an external language model score, and computing an estimated internal language model score for the E2E model. The estimated internal language model score is computed by removing a contribution of an intrinsic acoustic model. The processor is further configured to compute an integrated score based at least on E2E model score, the external language model score, and the estimated internal language model score.

Abstract: Method of detecting objects in non-perspective images starts by generating an arrangement of tiles based on a field of view of a non-perspective camera lens, a predetermined size of the tiles, and a predetermined maximum object radius. The arrangement of the tiles includes the minimum number of tiles to cover the field of view. A non-perspective image is then captured using the non-perspective camera lens. The non-perspective image may be a still image frame or a video. Using the tiles, a plurality of images are generated, respectively, and at least a portion of a first object is detected in one or more images. The first object is generated using the one or more images that include the at least the portion of the first object, and the first object is displayed on a display interface. Other embodiments are described herein.

Abstract: According to some embodiments, a multi-layer speech recognition transcript post processing system may include a data-driven, statistical layer associated with a trained automatic speech recognition model that selects an initial transcript. A rule-based layer may receive the initial transcript from the data-driven, statistical layer and execute at least one pre-determined rule to generate a first modified transcript. A machine learning approach layer may receive the first modified transcript from the rule-based layer and perform a neural model inference to create a second modified transcript. A human editor layer may receive the second modified transcript from the machine learning approach layer along with an adjustment from at least one human editor. The adjustment may create, in some embodiments, a final transcript that may be used to fine-tune the data-driven, statistical layer.

Abstract: The present disclosure relates to compositions and methods for producing stereoisomerically pure aminocyclopropanes.

Abstract: Forms of 6-(3-chloro-4-cyclopropoxyphenyl)pyrimidine-4-carboxylic acid (Compound I) were prepared and characterized in the solid state: Also provided are processes of manufacture and methods of using the forms of Compound I and salts or co-crystals thereof.

Abstract: Provided in this disclosure are methods for the synthesis of substituted 2-arylcyclopropylamines and 2-heteroarylcyclopropylamines and related compounds. Also provided are methods for reduction of thioesters to aldehydes, and methods for reductive animation of cyclopropylamines.

Abstract: This invention is in the area of synthesizing pyrimidine-based compounds useful in the treatment of disorders involving abnormal cellular proliferation, including but not limited to tumors and cancers.

Abstract: According to some embodiments, a multi-layer speech recognition transcript post processing system may include a data-driven, statistical layer associated with a trained automatic speech recognition model that selects an initial transcript. A rule-based layer may receive the initial transcript from the data-driven, statistical layer and execute at least one pre-determined rule to generate a first modified transcript. A machine learning approach layer may receive the first modified transcript from the rule-based layer and perform a neural model inference to create a second modified transcript. A human editor layer may receive the second modified transcript from the machine learning approach layer along with an adjustment from at least one human editor. The adjustment may create, in some embodiments, a final transcript that may be used to fine-tune the data-driven, statistical layer.

Abstract: Forms of 6-(3-chloro-4-cyclopropoxyphenyl)pyrimidine-4-carboxylic acid (Compound I) were prepared and characterized in the solid state: Also provided are processes of manufacture and methods of using the forms of Compound I and salts or co-crystals thereof.

Abstract: This invention is in the area of synthesizing pyrimidine-based compounds useful in the treatment of disorders involving abnormal cellular proliferation, including but not limited to tumors and cancers.

Abstract: This invention is in the area of synthesizing pyrimidine-based compounds useful in the treatment of disorders involving abnormal cellular proliferation, including but not limited to tumors and cancers.

Abstract: Methods for preparing chirally purified substituted 4,5,6,7-tetrahydro-benzothiazole diamines such as, for example, (6R)2-amino-4,5,6,7-tetrahydro-6-(propylamino)benzothiazole and purifying a dominant enantiomer of substituted 4,5,6,7-tetrahydro-benzothiazole diamines from entantiomerically enriched mixtures of substituted 4,5,6,7-tetrahydro-benzothiazole diamines are provided herein.