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

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

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

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

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

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: Feature extraction is described for speech recognition using a neural network accelerator. In one example an audio clip is received for feature extraction. A plurality of feature extraction operations are performed on the audio clip using matrix-matrix multiplication of a hardware neural network accelerator, and features are produced for speech recognition.

Abstract: A processing system includes a processor to execute a neural network application comprising an operation associated with a weight parameter and an input value, and an accelerator circuit, associated with the processor, to perform the operation, the accelerator circuit comprising a weight storage device to store a bit stream encoding the weight parameter, a controller to request a bit from the bit stream, an input data storage to store the input value, and an arithmetic logic unit (ALU) comprising an accumulator circuit to store an accumulation value and an operator circuit to receive the bit and the input value, receive a control signal from the controller, and responsive to determining that the control signal is set to a first value corresponding to a first operation and that that the bit encodes a first status, increase the accumulation value, stored in the accumulation circuit, by the input value.

Abstract: A system, article, and method of automatic speech recognition using parallel processing for weighted finite state transducer-based speech decoding.