Abstract: For any application that processes speech, improving the quality of the feature vectors may improve the quality of the speech application. The quality of feature vectors may be improved by modifying a neural network architecture for computing feature vectors to allocate computational resources where they are more effective for learning and computing the feature vectors. Contextual feature vectors may be computed from feature vectors by using a parameterized downsampling operation that decreases a vector sequence rate, processing the downsampled vectors with a neural network, and using a parameterized upsampling operation that increases a vector sequence rate. For example, parameterized downsampling may decrease a vector sequence rate by a factor of two, a neural may require fewer computational resources since it operates with a lower vector sequence rate, and parameterized upsampling may then increase the vector sequence rate by a factor of two.

Abstract: A speech processing model may be trained using pseudo tokens. Training a speech processing model with pseudo tokens may allow for training with a smaller amount of labeled training data and accordingly lower costs. A set of pseudo tokens may be determined by computing feature vectors from unlabeled training data, clustering the feature vectors, and performing token compression using the clustered feature vectors. A first speech processing model may be trained using unlabeled training data by determining sequences of pseudo tokens corresponding to the unlabeled training data. A second speech processing model may be initialized using the first speech processing model and then trained using labeled training data. The second speech processing model may then be deployed to a speech processing application.

Abstract: For any application that processes speech, improving the quality of the feature vectors may improve the quality of the speech application. The quality of feature vectors may be improved by modifying a neural network architecture for computing feature vectors to allocate computational resources where they are more effective for learning and computing the feature vectors. Contextual feature vectors may be computed from feature vectors by using a parameterized downsampling operation that decreases a vector sequence rate, processing the downsampled vectors with a neural network, and using a parameterized upsampling operation that increases a vector sequence rate. For example, parameterized downsampling may decrease a vector sequence rate by a factor of two, a neural may require fewer computational resources since it operates with a lower vector sequence rate, and parameterized upsampling may then increase the vector sequence rate by a factor of two.

Abstract: A device, system, and method is provided for running mobile applications, including a server for running applications and a client installed in a mobile device. The client may connect to the server via a network. The client may display content, receive user input, and send user input to the server. The server may use the client to receive user input and to display content for running applications for the mobile device.

Abstract: A device, system, and method is provided for running mobile applications, including a server for running applications and a client installed in a mobile device. The client may connect to the server via a network. The client may display content, receive user input, and send user input to the server. The server may use the client to receive user input and to display content for running applications for the mobile device.

Abstract: A device, system, and method is provided for running mobile applications, including a server for running applications and a client installed in a mobile device. The client may connect to the server via a network. The client may display content, receive user input, and send user input to the server. The server may use the client to receive user input and to display content for running applications for the mobile device.

Abstract: A device, system, and method is provided for running mobile applications, including a server for running applications and a client installed in a mobile device. The client may connect to the server via a network. The client may display content, receive user input, and send user input to the server. The server may use the client to receive user input and to display content for running applications for the mobile device.