Intel Corporation

Samsung Electronics Co., Ltd.

Suhel Jaber

Gokcen Cilingir

Paulo Lopez Meyer

Adam Kupryjanow

David Pearce

Petrus Van Beek

Anil Sunder Yadav

Naissa Conde

Melvin Lobo

Pragya Agrawal

Darshana Salvi

Dat Quoc Ngo

Sukrat Gupta

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.

Method of natural language processing by performing semantic analysis using syntactic information, and an apparatus for the same

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.

System and method for out-of-vocabulary phrase support in automatic speech recognition

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.

Technologies for managing a world model of a monitored area

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.

Secure audio acquisition system with limited frequency range for privacy

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.

Audio gait detection and identification

Growing community of inventors

San Jose, CA, United States of America

Suhel Jaber