Abstract: A task-oriented dialog system determines an endpoint in a user utterance by receiving incremental portions of a user utterance that is provided in real time during a task-oriented communication session between a user and a virtual agent (VA). The task-oriented dialog system recognizes words in the incremental portions using an automated speech recognition (ASR) model and generates semantic information for the incremental portions of the utterance by applying a natural language processing (NLP) model to the recognized words. An acoustic-prosodic signature of the incremental portions of the utterance is generated using an acoustic-prosodic model. The task-oriented dialog system can generate a feature vector that represents the incrementally recognized words, the semantic information, the acoustic-prosodic signature, and corresponding confidence scores of the model outputs. A model is applied to the feature vector to identify a likely endpoint in the user utterance.

Abstract: A natural language understanding (NLU) system generates in-place annotations for natural language utterances or other types of time-based media based on stand-off annotations. The in-place annotations are associated with particular sub-sequences of an annotation, which provides richer information than stand-off annotations, which are associated only with an utterance as a whole. To generate the in-place annotations for an utterance, the NLU system applies an encoder network and a decoder network to obtain attention weights for the various tokens within the utterance. The NLU system disqualifies tokens of the utterance based on their corresponding attention weights, and selects highest-scoring contiguous sequences of tokens between the disqualified tokens. In-place annotations are associated with the selected sequences.

Abstract: A high input impedance switched capacitor amplifier is disclosed. The switched capacitor amplifier includes at least a first buffer circuit configured to charge a first plurality of capacitors during a first time period. A switch circuit is configured to, during a second time period, cause a modification of an amount of charge stored on one of the first plurality of capacitors by coupling an input signal directly to the one of first plurality of capacitors. An amplifier circuit is configured to, based on a sampling voltage present on one of the first plurality of capacitors, generate an output signal.

Abstract: In described examples, a circuit includes an integrator. The integrator generates a first signal responsive to an input signal. A trigger circuit is coupled to the integrator and receives the first signal. A charge dump circuit is coupled to the integrator and the trigger circuit. The trigger circuit modifies configuration of the charge dump circuit and the integrator when the first signal is greater than a first threshold.

Abstract: In an embodiment of a messaging system, a method for presenting a commercial message to a user is provided. A target language in which the user is comfortable communicating may be determined based on at least one communication received by the user or at least one communication provided by the user. The commercial message may be presented to the user in the target language.

Abstract: In described examples, a circuit includes an integrator. The integrator generates a first signal responsive to an input signal. A trigger circuit is coupled to the integrator and receives the first signal. A charge dump circuit is coupled to the integrator and the trigger circuit. The trigger circuit modifies configuration of the charge dump circuit and the integrator when the first signal is greater than a first threshold.

Abstract: A method, computer program product, and/or system is disclosed for changing the events monitored by a processor including: determining whether a change in the monitoring of the first event to the second different event has been requested; copying, in response to a request to change the monitoring of the first event to the second different event, op-codes from memory into microcode executable by a general processing engine; and executing the op-codes from memory by the general processing engine to change the first event monitored by the counter to the second different event.

Abstract: Embodiments relate to a system, program product, and method for mitigating voltage overshoot in one or more cores in a multicore processing device including a plurality of cores. The method includes determining, in real-time, an indication of power consumption within each core of the one or more cores. The method also includes determining, through the indication of power consumption, a voltage overshoot condition in the one or more cores. The method further includes increasing, for the one or more cores, a power demand thereof. The method also includes increasing, subject to the increasing the power demand, power delivery to the one or more cores, thereby at least arresting the rate of increase of the voltage overshoot.

Abstract: A system, method and computer-readable storage devices are for processing natural language commands, such as commands to a robotic arm, using a Tag & Parse approach to semantic parsing. The system first assigns semantic tags to each word in a sentence and then parses the tag sequence into a semantic tree. The system can use statistical approach for tagging, parsing, and reference resolution. Each stage can produce multiple hypotheses, which are re-ranked using spatial validation. Then the system selects a most likely hypothesis after spatial validation, and generates or outputs a command. In the case of a robotic arm, the command is output in Robot Control Language (RCL).

Abstract: A method, computer program product, and/or system is disclosed for changing the events monitored by a processor including: determining whether a change in the monitoring of the first event to the second different event has been requested; copying, in response to a request to change the monitoring of the first event to the second different event, op-codes from memory into microcode executable by a general processing engine; and executing the op-codes from memory by the general processing engine to change the first event monitored by the counter to the second different event.

Abstract: A reference voltage generator comprises a comparator, a digital-to-analog converter (DAC) and a switched capacitor accumulator. The comparator receives a reference voltage input, a feedback input, and a control signal. The DAC is coupled to an output of the comparator, and the switched capacitor accumulator is coupled to an output of the DAC. In some implementations, a digital filter is coupled between the output of the comparator and the input of the DAC. The switched capacitor accumulator can be coupled to a buffer that outputs the feedback input and a reference voltage for an analog-to-digital converter (ADC). In some implementations, the feedback loop includes N one-bit DACs coupled to the output of the comparator and N switched capacitor accumulators, each of which is coupled to a unique one-bit DAC.

Abstract: Embodiments relate to a system, program product, and method for proactively initiating throttle action on one or more cores in a multicore processing device to mitigate voltage droop therein. The method includes determining, in real-time, an indication of stall events within the core and determining one or more resolutions of the stall events. The method also includes determining, in real-time, a timing margin value for the core and predicting inducement of a voltage droop on the core. The method further includes integrating the resolutions of the stall events and the timing margin value for the core, determining, subject to the predicting, a throttle action for the core, and executing the throttle action on the core.

Abstract: A method for managing memory within a computing system. The method includes one or more computer processors identifying a range of physical memory addresses that store a first data. The method further includes determining whether a second data is stored within the range of physical memory addresses that stores the first data. The method further includes responding to determining that the second data is stored within the range of physical memory addresses that store the first data, by determining whether a process accessing the second data is identified as associated with a side-channel attack. The method further includes responding to determining that the process accessing the second data is associated with the side-channel attack, by initiating a response associated with the process accessing the second data.

Abstract: Embodiments relate to a system, program product, and method for mitigating voltage overshoot in one or more cores in a multicore processing device including a plurality of cores. The method includes determining, in real-time, an indication of power consumption within each core of the one or more cores. The method also includes determining, through the indication of power consumption, a voltage overshoot condition in the one or more cores. The method further includes increasing, for the one or more cores, a power demand thereof. The method also includes increasing, subject to the increasing the power demand, power delivery to the one or more cores, thereby at least arresting the rate of increase of the voltage overshoot.

Abstract: Embodiments relate to a system, program product, and method for proactively initiating throttle action on one or more cores in a multicore processing device to mitigate voltage droop therein. The method includes determining, in real-time, an indication of stall events within the core and determining one or more resolutions of the stall events. The method also includes determining, in real-time, a timing margin value for the core and predicting inducement of a voltage droop on the core. The method further includes integrating the resolutions of the stall events and the timing margin value for the core, determining, subject to the predicting, a throttle action for the core, and executing the throttle action on the core.

Abstract: Systems and methods are disclosed herein for discerning aspects of user speech to determine user intent and/or other acoustic features of a sound input without the use of an ASR engine. To this end, a processor may receive a sound signal comprising raw acoustic data from a client device, and divides the data into acoustic units. The processor feeds the acoustic units through a first machine learning model to obtain a first output and determines a first mapping, using the first output, of each respective acoustic unit to a plurality of candidate representations of the respective acoustic unit. The processor feeds each candidate representation of the plurality through a second machine learning model to obtain a second output, determines a second mapping, using the second output, of each candidate representation to a known condition, and determines a label for the sound signal based on the second mapping.

Abstract: A reference voltage generator comprises a comparator, a digital-to-analog converter (DAC) and a switched capacitor accumulator. The comparator receives a reference voltage input, a feedback input, and a control signal. The DAC is coupled to an output of the comparator, and the switched capacitor accumulator is coupled to an output of the DAC. In some implementations, a digital filter is coupled between the output of the comparator and the input of the DAC. The switched capacitor accumulator can be coupled to a buffer that outputs the feedback input and a reference voltage for an analog-to-digital converter (ADC). In some implementations, the feedback loop includes N one-bit DACs coupled to the output of the comparator and N switched capacitor accumulators, each of which is coupled to a unique one-bit DAC.

Abstract: Disclosed herein are systems, computer-implemented methods, and computer-readable media for dialog modeling. The method includes receiving spoken dialogs annotated to indicate dialog acts and task/subtask information, parsing the spoken dialogs with a hierarchical, parse-based dialog model which operates incrementally from left to right and which only analyzes a preceding dialog context to generate parsed spoken dialogs, and constructing a functional task structure of the parsed spoken dialogs. The method can further either interpret user utterances with the functional task structure of the parsed spoken dialogs or plan system responses to user utterances with the functional task structure of the parsed spoken dialogs. The parse-based dialog model can be a shift-reduce model, a start-complete model, or a connection path model.

Abstract: In described examples, a circuit includes an integrator. The integrator generates a first signal responsive to an input signal. A trigger circuit is coupled to the integrator and receives the first signal. A charge dump circuit is coupled to the integrator and the trigger circuit. The trigger circuit modifies configuration of the charge dump circuit and the integrator when the first signal is greater than a first threshold.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for collecting web data in order to create diverse language models. A system configured to practice the method first crawls, such as via a crawler operating on a computing device, a set of documents in a network of interconnected devices according to a visitation policy, wherein the visitation policy is configured to focus on novelty regions for a current language model built from previous crawling cycles by crawling documents whose vocabulary considered likely to fill gaps in the current language model. A language model from a previous cycle can be used to guide the creation of a language model in the following cycle. The novelty regions can include documents with high perplexity values over the current language model.