Intel Corporation

Piotr Rozen

Georg Stemmer

Joachim Hofer

Josef G Bauer

Tobias Bocklet

David Pearce

Piotr Majcher

Munir Georges

Tomasz Dorau

Jacek Ossowski

Maciej Muchlinski

Andrzej Mialkowski

Jakub Nowicki

Tomasz Szmelczynski

Lukasz M Malinowski

Sagar Koorapati

A system, article, and method of automatic speech recognition with highly efficient decoding is accomplished by frequent beam width adjustment.

Method and system of automatic speech recognition with highly efficient decoding

A mechanism is described for facilitating continuous topic detection and adaption in audio environments, according to one embodiment. A method of embodiments, as described herein, includes detecting a term relating to a topic in an audio input received from one or more microphones of the computing device including a voice-enabled device; analyzing the term based on the topic to determine an action to be performed by the computing device; and triggering an event to facilitate the computing device to perform the action consistent with the term and the topic.

Continuous topic detection and adaption in audio environments

Systems, apparatuses and methods may provide for technology that assigns a plurality of data portions associated with a workload to a plurality of cores, wherein each data portion from the plurality of data portions is only modifiable by a respective one of the plurality of cores. The technology may further pass a message between the plurality of cores to modify one or more of the data portions in response to an identification that the one or more of the data portions are unmodifiable by one or more of the plurality of cores.

Workload scheduling and coherency through data assignments

Techniques related to implementing neural networks for speech recognition systems are discussed. Such techniques may include processing a node of the neural network by determining a score for the node as a product of weights and inputs such that the weights are fixed point integer values, applying a correction to the score based on a correction value associated with at least one of the weights, and generating an output from the node based on the corrected score.

Fixed point integer implementations for neural networks

Techniques are disclosed for client-side analysis of audio samples to identify one or more characteristics associated with captured audio. The client-side analysis may then allow a user device, e.g., a smart phone, laptop computer, in-car infotainment system, and so on, to provide the one or more identified characteristics as configuration data to a voice recognition service at or shortly after connection with the same. In turn, the voice recognition service may load one or more recognition components, e.g., language models and/or application modules/engines, based on the received configuration data. Thus, latency may be reduced based on the voice recognition engine having 'hints' that allow components to be loaded without necessarily having to process audio samples first. The reduction of latency may reduce processing time relative to other approaches to voice recognitions systems that exclusively perform server-side context recognition/classification.

Techniques for client-side speech domain detection using gyroscopic data and a system using the same

A method and system are directed to autonomous neural network keyphrase detection and includes generating and using a multiple element state score vector by using neural network operations and without substantial use of a digital signal processor (DSP) to perform the keyphrase detection.

Method and system of neural network keyphrase detection

Techniques are provided for calculating reset parameters for recurrent neural networks (RNN). A methodology implementing the techniques according to an embodiment includes generating a sequence of statistics. The calculation of each statistic is based on outputs of an RNN that is periodically re-initialized at a selected RNN reset time such that each of the calculated statistics is associated with a unique RNN reset time selected from a pre-determined range of reset times. The method further includes analyzing the sequence to identify a maximum interval during which the sequence remains relatively constant. The method further includes selecting a reset time parameter and reset context duration parameter, for re-initialization of the RNN during operation. The reset time parameter is based on the duration of the identified maximum interval and the reset context duration parameter is based on a time associated with the starting point of the identified maximum interval.

Statistical-analysis-based reset of recurrent neural networks for automatic speech recognition

A computer-implemented method of speech recognition comprises forming a weighted finite state transducer (WFST) having nodes associated with states and interconnected by arcs, and to identify at least one word or word sequence hypothesis, identifying multiple sub-graphs on the WFST, each sub-graph having the same arrangement of multiple states and at least one arc, and propagating tokens in parallel through the sub-graphs, where each sub-graph is stored as a supertoken each having an array of tokens.

System and method of automatic speech recognition using parallel processing for weighted finite state transducer-based speech decoding

Techniques related to implementing neural networks for speech recognition systems are discussed. Such techniques may include implementing frame skipping with approximated skip frames and/or distances on demand such that only those outputs needed by a speech decoder are provided via the neural network or approximation techniques.

Growing community of inventors

Gdansk, Poland

Piotr Rozen