Abstract: A method includes obtaining an input containing multiple tokens. The method also includes processing the input using a machine learning model. Processing the input includes performing attention over both (i) multiple dimensions of the tokens contained in the input and (ii) multiple dimensions of embedding vectors used to represent the tokens contained in the input so that different dimensions of each of at least some of the tokens are weighted differently. In addition, the method includes generating an output embedding vector for a query token of the multiple tokens based on the attention.

Abstract: A method includes providing embedding vectors representing tokens in an input to a transformer comprising multiple transformer layers arranged in a sequence, each transformer layer having a residual connection to each previous transformer layer. The method also includes, for each transformer layer, determining, for a first token, an input embedding vector based on a combination of output embedding vectors from previous transformer layers. The method further includes, for each transformer layer, processing, for the first token, the input embedding vector to generate an output embedding vector to be provided to each subsequent transformer layer.

Abstract: A method includes receiving an input utterance that is a continuation of a previous utterance. The method also includes, using a trained Siamese network, determining input utterance embeddings representing tokens from the input utterance, pooling the input utterance embeddings with a context token embedding representing a class associated with the previous utterance to generate a representative input utterance embedding, and determining a representative embedding associated with each of multiple possible classes. Each possible class is associated with first and second threshold boundaries. The method further includes, using the trained Siamese network, determining a similarity score for each possible class based on a distance between the representative input utterance embedding and a selected threshold boundary of the representative embedding for that possible class and identifying a class for the input utterance based on the determined similarity scores.

Abstract: A method includes determining, using at least one processing device of an electronic device, a target embedding vector for each class of a plurality of classes. The method also includes generating, using the at least one processing device, an utterance embedding vector using a pre-trained language model, where the utterance embedding vector represents an input utterance associated with an expected class. The method further includes obtaining, using the at least one processing device, a predicted class associated with the input utterance based on distances of the utterance embedding vector to spatial parameters representing the plurality of classes, where the spatial parameter of each class is based on the target embedding vector associated with that class. In addition, the method includes updating, using the at least one processing device, parameters of the language model based on a difference between the predicted class and the expected class.

Abstract: A method for performing one or more natural language understanding semantic tasks augmented with syntactic information includes parsing a written or spoken utterance comprising a plurality of tokens into a full syntactic tree for the utterance; encoding each token in the utterance using a word encoder based on deep-learning network; encoding using a graph-based neural network, for each token, a syntactic subtree in which the token is a head; fusing each encoded token with the encoded syntactic subtree corresponding to that encoded token; and providing the fused encodings to a semantic neural network for performing one or more semantic tasks.

Abstract: A method of training a model includes selecting a learning rate for the model, training the model based on the learning rate, determining a derivative of a loss for an objective function for the model with respect to the learning rate based on a result of the training, and based on the derivative of the loss being greater than a predetermined derivative threshold, determining at least one point of interest based on the result of the training, selecting a subsequent learning rate based on the at least one point of interest, training the model based on the subsequent learning rate, and selecting an optimal learning rate based on the training results.

Abstract: Technologies for managing a world model of a monitored area includes a roadway server configured to receive LIDAR sensing data from a LIDAR sensing system positioned to monitor the monitored area and generate a world map of the monitored area based on the LIDAR sensing data. The world model includes data that identifies objects located in the monitored area. The roadway server may distribute the world model to automated vehicles traveling through the monitored area via a stream or in response to directed requests. The roadway server may also receive sensor data from the automated vehicles, which may be used to generate the world model. The roadway server may distribute the world model to other interested devices located in or near the monitored area.

Abstract: According to one embodiment, an apparatus includes an interface to receive sensor data from a plurality of sensors of an autonomous vehicle. The apparatus also includes processing circuitry to apply a sensor abstraction process to the sensor data to produce abstracted scene data, and to use the abstracted scene data in a perception phase of a control process for the autonomous vehicle. The sensor abstraction process may include one or more of: applying a Sensor data response normalization process to the sensor data, applying a warp process to the sensor data, and applying a filtering process to the sensor data.

Abstract: An apparatus comprising at least one interface to receive sensor data from a plurality of sensors of a vehicle; and one or more processors to autonomously control driving of the vehicle according to a path plan based on the sensor data; determine that autonomous control of the vehicle should cease; send a handoff request to a remote computing system for the remote computing system to control driving of the vehicle remotely; receive driving instruction data from the remote computing system; and control driving of the vehicle based on instructions included in the driving instruction data.

Abstract: Sensor data is received from a plurality of sensors, where the plurality of sensors includes a first set of sensors and a second set of sensors, and at least a portion of the plurality of sensors are coupled to a vehicle. Control of the vehicle is automated based on at least a portion of the sensor data generated by the first set of sensors. Passenger attributes of one or more passengers within the autonomous vehicles are determined from sensor data generated by the second set of sensors. Attributes of the vehicle are modified based on the passenger attributes and the sensor data generated by the first set of sensors.

Abstract: An electronic device includes an audio sensor, a memory, and at least one processor coupled to the audio sensor and the memory. The at least one processor is configured to receive, via the audio sensor an audio input. The at least one processor is further configured to perform, using an automatic speech recognition (ASR) model and an entity prediction model, out-of-vocabulary prediction of an entity. The at least one processor is further configured to receive an ASR hypothesis including the predicted entity. The at least one processor is further configured to output text including the predicted entity.

Abstract: Technologies for managing a world model of a monitored area includes a roadway server configured to receive LIDAR sensing data from a LIDAR sensing system positioned to monitor the monitored area and generate a world map of the monitored area based on the LIDAR sensing data. The world model includes data that identifies objects located in the monitored area. The roadway server may distribute the world model to automated vehicles traveling through the monitored area via a stream or in response to directed requests. The roadway server may also receive sensor data from the automated vehicles, which may be used to generate the world model. The roadway server may distribute the world model to other interested devices located in or near the monitored area.

Abstract: Systems, apparatuses and methods for secure audio acquisition. The method includes receiving audio data via a digital microphone. The digital microphone outputs a single bit at a high sampling rate. The digital microphone output is converted to a full range audio signal. The full range audio signal is filtered to provide a band limited audio output that avoids capture of enough of a spectral range of speech for the speech to be intelligible.

Abstract: Systems, apparatuses and methods for technology to perform gait detection and identification. The system includes a pre-processing pipeline to process audio input data from one or more microphones to combine and strengthen an audio gait signal. The pre-processing pipeline is coupled to a gait detector to detect the sound of one or more footsteps from the audio gait signal. The system also includes a person evaluator (e.g., identifier/verifier) to identify the person associated with the one or more footsteps using a set of trained footstep identification (ID) classifiers. Each trained footstep ID classifier is mapped to the gait of a specific person in the home based on a particular combination of person, footwear, and floor surface within the home.