Abstract: A computer-implemented method includes receiving a sequence of acoustic frames as input to an automatic speech recognition (ASR) model. Here, the ASR model includes a causal encoder and a decoder. The method also includes generating, by the causal encoder, a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The method also includes generating, by the decoder, a first probability distribution over possible speech recognition hypotheses. Here, the causal encoder includes a stack of causal encoder layers each including a Recurrent Neural Network (RNN) Attention-Performer module that applies linear attention.

Abstract: The present invention is directed to certain 2-aminoquinzaoline derivatives of Formula (I): Formula (I) and pharmaceutically acceptable salts thereof, wherein R1, R2, and R3 are as defined herein, which are potent inhibitors of LRRK2 kinase and may be useful in the treatment or prevention of diseases in which the LRRK2 kinase is involved, such as Parkinson's Disease and other diseases and disorders described herein. The invention is also directed to pharmaceutical compositions comprising these compounds and the use of these compounds and compositions in the prevention or treatment of such diseases in which LRRK-2 kinase is involved.

Abstract: Systems and methods can utilize a conformer model to process a data set for various data processing tasks, including, but not limited to, speech recognition, sound separation, protein synthesis determination, video or other image set analysis, and natural language processing. The conformer model can use feed-forward blocks, a self-attention block, and a convolution block to process data to learn global interactions and relative-offset-based local correlations of the input data.

Abstract: Described herein are compounds of Formula I or a pharmaceutically acceptable salt thereof, wherein R1, R2, A, and B are as defined herein. The compounds of Formula I act as IL4I1 inhibitors and can be useful in preventing, treating or acting as a remedial agent for IL4I1-related diseases.

Abstract: The present invention is directed to certain 2-aminoquinzaoline derivatives of Formula (I): (I) and pharmaceutically acceptable salts thereof, wherein A, R1, R2, and R3 are as defined herein, which are potent inhibitors of LRRK2 kinase and may be useful in the treatment or prevention of diseases in which the LRRK2 kinase is involved, such as Parkinson's Disease and other diseases and disorders described herein. The invention is also directed to pharmaceutical compositions comprising these compounds and the use of these compounds and compositions in the prevention or treatment of such diseases in which LRRK-2 kinase is involved.

Abstract: A computer-implemented method of training a streaming speech recognition model that includes receiving, as input to the streaming speech recognition model, a sequence of acoustic frames. The streaming speech recognition model is configured to learn an alignment probability between the sequence of acoustic frames and an output sequence of vocabulary tokens. The vocabulary tokens include a plurality of label tokens and a blank token. At each output step, the method includes determining a first probability of emitting one of the label tokens and determining a second probability of emitting the blank token. The method also includes generating the alignment probability at a sequence level based on the first probability and the second probability. The method also includes applying a tuning parameter to the alignment probability at the sequence level to maximize the first probability of emitting one of the label tokens.

Abstract: Systems and methods can utilize a conformer model to process a data set for various data processing tasks, including, but not limited to, speech recognition, sound separation, protein synthesis determination, video or other image set analysis, and natural language processing. The conformer model can use feed-forward blocks, a self-attention block, and a convolution block to process data to learn global interactions and relative-offset-based local correlations of the input data.

Abstract: The present invention is directed to certain 2-aminoquinzaoline derivatives of Formula (I) and pharmaceutically acceptable salts thereof, wherein R1, R2, and R3 are as defined herein, which are potent inhibitors of LRRK2 kinase and may be useful in the treatment or prevention of diseases in which the LRRK2 kinase is involved, such as Parkinson's Disease and other diseases and disorders described herein. The invention is also directed to pharmaceutical compositions comprising these compounds and the use of these compounds and compositions in the prevention or treatment of such diseases in which LRRK-2 kinase is involved.

Abstract: The present invention is directed to certain 2-aminoquinzaoline derivatives of Formula (I): and pharmaceutically acceptable salts thereof, wherein R1, R3, R4, X1, and X2 are as defined herein, which are potent inhibitors of LRRK2 kinase and may be useful in the treatment or prevention of diseases in which the LRRK2 kinase is involved, such as Parkinson's Disease and other diseases and disorders described herein. The invention is also directed to pharmaceutical compositions comprising these compounds and the use of these compounds and compositions in the prevention or treatment of such diseases in which LRRK-2 kinase is involved.

Abstract: Systems and methods of the present disclosure are directed to a computing system, including one or more processors and a machine-learned multi-mode speech recognition model configured to operate in a streaming recognition mode or a contextual recognition mode. The computing system can perform operations including obtaining speech data and a ground truth label and processing the speech data using the contextual recognition mode to obtain contextual prediction data. The operations can include evaluating a difference between the contextual prediction data and the ground truth label and processing the speech data using the streaming recognition mode to obtain streaming prediction data. The operations can include evaluating a difference between the streaming prediction data and the ground truth label and the contextual and streaming prediction data. The operations can include adjusting parameters of the speech recognition model.

Abstract: A computer-implemented method includes receiving a sequence of acoustic frames as input to an automatic speech recognition (ASR) model. Here, the ASR model includes a causal encoder and a decoder. The method also includes generating, by the causal encoder, a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The method also includes generating, by the decoder, a first probability distribution over possible speech recognition hypotheses. Here, the causal encoder includes a stack of causal encoder layers each including a Recurrent Neural Network (RNN) Attention-Performer module that applies linear attention.

Abstract: The present invention is directed to substituted certain N-(heteroaryl)quinazolin-2-amine derivatives of Formula (I): and pharmaceutically acceptable salts thereof, wherein J, R3, and R4, are as defined herein, which are potent inhibitors of LRRK2 kinase and may be useful in the treatment or prevention of diseases in which the LRRK2 kinase is involved, such as Parkinson's Disease and other diseases and disorders described herein. The invention is also directed to pharmaceutical compositions comprising these compounds and the use of these compounds and compositions in the prevention or treatment of diseases, such as Parkinson's disease, in which LRRK-2 kinase is involved.

Abstract: The present invention is directed to substituted certain 1-pyrazolyl, 5-, 6-disubstituted indazole derivatives of Formula (I) and pharmaceutically acceptable salts thereof, wherein R1, R2, and ring A are as defined herein, which are potent inhibitors of LRRK2 kinase and may be useful in the treatment or prevention of diseases in which the LRRK2 kinase is involved, such as Parkinson's Disease and other diseases and disorders described herein. The invention is also directed to pharmaceutical compositions comprising these compounds and the use of these compounds and compositions in the prevention or treatment of diseases, such as Parkinson's disease, in which LRRK-2 kinase is involved.

Abstract: Systems and methods can utilize a conformer model to process a data set for various data processing tasks, including, but not limited to, speech recognition, sound separation, protein synthesis determination, video or other image set analysis, and natural language processing. The conformer model can use feed-forward blocks, a self-attention block, and a convolution block to process data to learn global interactions and relative-offset-based local correlations of the input data.

Abstract: A computer-implemented method of training a streaming speech recognition model that includes receiving, as input to the streaming speech recognition model, a sequence of acoustic frames. The streaming speech recognition model is configured to learn an alignment probability between the sequence of acoustic frames and an output sequence of vocabulary tokens. The vocabulary tokens include a plurality of label tokens and a blank token. At each output step, the method includes determining a first probability of emitting one of the label tokens and determining a second probability of emitting the blank token. The method also includes generating the alignment probability at a sequence level based on the first probability and the second probability. The method also includes applying a tuning parameter to the alignment probability at the sequence level to maximize the first probability of emitting one of the label tokens.

Abstract: The present invention is directed to substituted certain reversed indazolyl-spiro[2.2]pentane-carbonitrile derivatives of Formula (I): and pharmaceutically acceptable salts thereof, wherein R1, R2, R3, X, Y, and Z are as defined herein, which are potent inhibitors of LRRK2 kinase and may be useful in the treatment or prevention of diseases in which the LRRK2 kinase is involved, such as Parkinson's Disease and other diseases and disorders described herein. The invention is also directed to pharmaceutical compositions comprising these compounds and the use of these compounds and compositions in the prevention or treatment of such diseases in which LRRK-2 kinase is involved.

Abstract: The present invention is directed to substituted certain reversed indazolyl-spiro[2.2]pentane-carbonitrile derivatives of Formula (I): and pharmaceutically acceptable salts thereof, wherein R1, R2, R3, X, Y, and Z are as defined herein, which are potent inhibitors of LRRK2 kinase and may be useful in the treatment or prevention of diseases in which the LRRK2 kinase is involved, such as Parkinson's Disease and other diseases and disorders described herein. The invention is also directed to pharmaceutical compositions comprising these compounds and the use of these compounds and compositions in the prevention or treatment of such diseases in which LRRK-2 kinase is involved.

Abstract: Systems and methods are described to notify an author that suggested content is available. An author-assistance tool is instantiated with a document processor to perform research to suggest content for a document being edited at the document processor. A user interaction relating to a document is received via the document processor, and the author-assistance tool generates suggested content for the document when the author has intent for content suggestion or the document has a document type that is on a list of document types for which a content suggestion should be made. The author-assistance tool then determines that the suggested content meets a pre-determined quality threshold, and generates, via the user interface of the document processor, a notification to the author that the suggested content is available.

Abstract: Systems and methods are described to notify an author that suggested content is available. An author-assistance tool is instantiated with a document processor to perform research to suggest content for a document being edited at the document processor. A user interaction relating to a document is received via the document processor, and the author-assistance tool generates suggested content for the document when the author has intent for content suggestion or the document has a document type that is on a list of document types for which a content suggestion should be made. The author-assistance tool then determines that the suggested content meets a pre-determined quality threshold, and generates, via the user interface of the document processor, a notification to the author that the suggested content is available.