Abstract:
Certain aspects of the present disclosure provide techniques for performing piecewise pointwise convolution, comprising: performing a first piecewise pointwise convolution on a first subset of data received via a first branch input at a piecewise pointwise convolution layer of a convolutional neural network (CNN) model; performing a second piecewise pointwise convolution on a second subset of data received via a second branch input at the piecewise pointwise convolution layer; determining a piecewise pointwise convolution output by summing a result of the first piecewise pointwise convolution and a result of the second piecewise pointwise convolution; and providing the piecewise pointwise convolution output to a second layer of the CNN model.
Abstract:
Various embodiments include methods and devices for implementing automatic grammar augmentation for improving voice command recognition accuracy in systems with a small footprint acoustic model. Alternative expressions that may capture acoustic model decoding variations may be added to a grammar set. An acoustic model-specific statistical pronunciation dictionary may be derived by running the acoustic model through a large general speech dataset and constructing a command-specific candidate set containing potential grammar expressions. Greedy based and cross-entropy-method (CEM) based algorithms may be utilized to search the candidate set for augmentations with improved recognition accuracy.
Abstract:
Systems and methods share context information on a neighbor aware network. In one aspect, a context providing device receives a plurality of responses to a discovery query from a context consuming device, and tailors services it offers to the context consuming device based on the responses. In another aspect, a context providing device indicates in its response to a discovery query which services or local context information it can provide to the context consuming device, and also a cost associated with providing the service or the local context information. In some aspects, the cost is in units of monetary currency. In other aspects, the cost is in units of user interface display made available to an entity associated with the context providing device in exchange for the services or local context information offered to the context consuming device.
Abstract:
Methods, systems, and devices are described for using information relating to a motion state of a mobile device to inform a handover decision of the mobile device. In one aspect, a method may include obtaining motion state information of the mobile device and, based on the motion state information, generating predictive information, for example relating to whether the mobile device is moving out of a network coverage area, such as a WLAN, to a WWAN or another WLAN. The mobile device may then participate in a handover based on the predictive information. In one aspect, the mobile device may participate in the handover prior to disconnection with a serving network and/or prior to a connection quality with the serving network falling below a connection quality threshold.
Abstract:
Various embodiments include methods and devices for implementing automatic grammar augmentation for improving voice command recognition accuracy in systems with a small footprint acoustic model. Alternative expressions that may capture acoustic model decoding variations may be added to a grammar set. An acoustic model-specific statistical pronunciation dictionary may be derived by running the acoustic model through a large general speech dataset and constructing a command-specific candidate set containing potential grammar expressions. Greedy based and cross-entropy-method (CEM) based algorithms may be utilized to search the candidate set for augmentations with improved recognition accuracy.
Abstract:
The disclosure is directed to using motion to reduce unnecessary scans for local wireless networks. An aspect determines whether or not a motion state change event of a user device indicates a change from a moving motion state to a stationary motion state, and if the motion state change event indicates a change from a moving motion state to a stationary motion state, ignoring the motion state change event. An aspect of the disclosure is directed to using motion to reduce latency of scanning for local wireless networks. An aspect determines whether or not a user device is in motion, determines whether or not a periodic scan timer has expired and/or a received signal strength indicator (RSSI) is below a threshold, and if the user device is in motion and the periodic scan timer has expired or the RSSI is below the threshold, scanning for a local wireless network.
Abstract:
Systems and methods share context information on a neighbor aware network. In one aspect, a context providing device receives a plurality of responses to a discovery query from a context consuming device, and tailors services it offers to the context consuming device based on the responses. In another aspect, a context providing device indicates in its response to a discovery query which services or local context information it can provide to the context consuming device, and also a cost associated with providing the service or the local context information. In some aspects, the cost is in units of monetary currency. In other aspects, the cost is in units of user interface display made available to an entity associated with the context providing device in exchange for the services or local context information offered to the context consuming device.
Abstract:
Methods, systems, computer-readable media, and apparatuses for inferring context are provided. In one potential implementation, first context information associated with a first duration is identified, second context information is accessed to determine a context segmentation boundary; and the first context information and the second context information is then aggregated to generate an inferred segmented aggregated context. In a further implementation, the first context information is used to average inferred contexts, and the context segmentation boundary is used to reset a start time for averaging the first context information.
Abstract:
Certain aspects of the present disclosure provide techniques for improved machine learning using gradient pruning, comprising computing, using a first batch of training data, a first gradient tensor comprising a gradient for each parameter of a parameter tensor for a machine learning model; identifying a first subset of gradients in the first gradient tensor based on a first gradient criteria; and updating a first subset of parameters in the parameter tensor based on the first subset of gradients in the first gradient tensor.
Abstract:
A method of operating a shared resource in a mobile device includes extracting a set of features from a plurality of subsystems of the mobile device. The set of features may be extracted from each subsystem of the plurality of subsystems requesting services from one or more shared resources of the mobile device. One or more parameter of the shared resource(s) may be determined based on the extracted set of features from the plurality of subsystems. The shared resource(s) may be operated based on the determined parameter(s).