Abstract: Natural language processing is enhanced by linguistically extracting intelligence about a user. A history of user queries is analyzed by a natural language classifier to determine various user intents, and these intents are combined to form a user intent profile. The profile includes elements of sentiment, emotion and tone. The profile can be used in various ways including restricting access to documents in a collection, or refining a cognitive analysis of a query. For access restriction, a determination is made that the user intent is inconsistent with a document, and the user is denied access to the document. This determination involves a user intent score which is compared to a score of the document. For cognitive analysis, searching of reference documents is filtered by excluding documents based on the user intent. The searching includes a comparison of meta-data tags of the documents to the user intent.

Abstract: Described embodiments include apparatus that includes a network interface (28) and a processor (30). The processor is configured to receive, via the network interface, speech of a subject (22) who suffers from a pulmonary condition related to accumulation of excess fluid, to identify, by analyzing the speech, one or more speech-related parameters of the speech, to assess, in response to the speech-related parameters, a status of the pulmonary condition, and to generate, in response thereto, an output indicative of the status of the pulmonary condition. Other embodiments are also described.

Abstract: In a method for evaluating the voice onset of a speaker, especially suited for treatment of a stuttering disorder, the analysis includes: a. determine a time of voice onset of the speaker; b. obtain a fundamental frequency at the time of voice onset; c. in a predetermined time interval, obtain the curve with respect to time of energy at the fundamental frequency; d. obtain the curve with respect to time of energy at at least one harmonic multiple of the fundamental frequency; and e. determine the temporal progression of the ratio of the energies obtained in steps c and d. A gentle voice onset is presumed if the energy ratio is initially dominated by the energy of the fundamental frequency, and only in the further course of the predetermined time interval in a time span of ?t the energy ratio shifts in favor of the energy/energies of the harmonic multiple(a) of the fundamental frequency.

Abstract: In a particular aspect, a speech generator includes a signal input configured to receive a first audio signal. The speech generator also includes at least one speech signal processor configured to generate a second audio signal based on information associated with the first audio signal and based further on automatic speech recognition (ASR) data associated with the first audio signal.

Abstract: Systems and methods are introduced to perform noise suppression of an audio signal. The audio signal includes foreground speech components and background noise. The foreground speech components correspond to speech from a user's speaking into an audio receiving device. The background noise includes babble noise that includes speech from one or more interfering speakers. A soft speech detector determines, dynamically, a speech detection result indicating a likelihood of a presence of the foreground speech components in the audio signal. The speech detection result is employed to control, dynamically, an amount of attenuation of the noise suppression to reduce the babble noise in the audio signal. Further processing achieves a more stationary background and reduction of musical tones in the audio signal.

Abstract: Mechanisms are provided for mitigating the effects of long term cognitive conditions on patient interactions by providing artificial intelligence mechanisms to assist with such interactions. The mechanisms perform a machine learning operation to learn, for a particular patient, associations between patient indicators and concepts that the patient is attempting to communicate or concepts representing actions that the patient would like to perform within a patient environment. The mechanisms receive, from a monitoring device in a patient environment, a patient input representing an attempt by the patient to communicate a concept or interact with the patient environment. The mechanisms perform a cognitive translation of one or more patient indicators in the patient input to one or more corresponding concepts based on results of the machine learning operation. The mechanisms then generate a translation output specifying the one or more corresponding concepts.

Abstract: Systems, methods and apparatus for invoking actions at a second user device from a first user device. A method includes determining that a first user device has an associated second user device; accessing specification data that specifies a set of user device actions that the second user device is configured to perform; receiving command inputs for the first user device; for each command input, determining whether the command input resolves to one of the user device actions; for each command input not determined to resolve any of the user device actions, causing the command input to be processed at the first user device; and for each command input determined to resolve one of the user device actions causing the first user device to display in a user interface a dialog by which a user may either accept or deny invoking the user device action at the second user device.

Abstract: Provided is a method of providing an unmanned dialogue service according to an embodiment of the inventive concept. The method includes transmitting or receiving text message data constituting a dialogue to or from a user terminal, analyzing the dialogue and determining whether an abnormal situation has occurred, transmitting an assistance request including information regarding the dialogue to a human agent management apparatus when it is determined that the abnormal situation has occurred, receiving dialogue advancement guide information, which is a response to the assistance request, from the human agent management apparatus, wherein the dialogue advancement guide information is configured using input data of a human agent input to a human agent terminal connected to the human agent management apparatus and configured to receive a task for processing the assistance request allocated by the human agent management apparatus, and continuing the dialogue using the dialogue advancement guide information.

Abstract: Aspects include learning object/action pairs for recipe ingredients. A method includes extracting an ingredient list that includes a plurality of entries from a recipe stored in an electronic format. Each of the plurality of entries includes one or more words. For each multi-word entry in the ingredient list, an ingredient associated with the entry is identified by comparing words contained in the entry to terms in a lexicon of cooking domain terms. It is determined whether an action corresponds to the identified ingredient. The determining includes parsing the entry to locate a verb that is associated with the identified ingredient. Based on determining that an action corresponds to the identified ingredient, a food item action pair that includes the identified ingredient and the located verb is output.

Abstract: In general, techniques are described for performing codebook selection when coding vectors decomposed from higher-order ambisonic coefficients. A device comprising a memory and a processor may perform the techniques. The memory may be configured to store a plurality of codebooks to use when performing vector dequantization with respect to a vector quantized spatial component of a soundfield. The vector quantized spatial component may be obtained through application of a decomposition to a plurality of higher order ambisonic coefficients. The processor may be configured to select one of the plurality of codebooks.

Abstract: A noise suppression system includes an a priori S/N ratio estimated value and expectation calculation unit that acquires an expectation of a priori S/N ratio, by correcting an estimated value of the a priori S/N ratio relating to a signal and a noise based on a priori S/N ratio model or based on a signal model and a noise model, the signal and the noise being estimated from an input signal in which the signal and the noise are mixed; a noise suppression coefficient calculation unit that calculates a noise suppression coefficient with use of the expectation of the a priori S/N ratio; and a noise suppression unit that suppresses the noise included in the input signal by multiplying the input signal by the noise suppression coefficient.

Abstract: A method includes receiving a set of documents related to data discovery issues, wherein at least a first data discovery issue is unrelated to a second data discovery issue. The method further includes generating a map of terms and words for the set of documents that correspond to concepts. The method further includes providing a user interface that includes a search analytics tool to a user associated with the first data discovery issue.

Abstract: A sampler module divides an audio signal into a series of sequential samples. A signal quality detector module identifies, over a plurality of samples at an outset of the audio signal, a spectral variance of a first range of frequencies of the audio signal below a predetermined threshold frequency as being consistently greater than a spectral variance of a second range of frequencies of the audio signal above the predetermined threshold frequency and determines a signal treatment indication responsive to the identification. A signal enhancer module sequentially receives and analyzes one or more sample components of the audio signal to identify lost parts of the audio signal in the one or more sample components of respective sequential samples, and generates, in accordance with the signal treatment indication, a corresponding signal treatment for each of the one or more sample components of respective sequential samples having a corresponding identified lost part.

Abstract: An embodiment provides a method, including: accepting, at an audio receiver of an information handling device, voice input of a user; interpreting, using a processor, the voice input; identifying, using a processor, at least one ambiguity in interpreting the voice input; thereafter accessing stored non-audible input associated in time with the at least one ambiguity; and adjusting an interpretation of the voice input using non-audible input. Other aspects are described and claimed.

Abstract: Data bus systems and methods include a device controller coupled to a first interface for digital audio data communications in accordance with a first communications protocol, the device controller including a master bus controller for controlling a multi-drop bus in accordance with a second communications protocol; and a first slave device coupled to the multi-drop bus and configured to transmit and receive digital audio data communications with the device controller in accordance with the second communications protocol. Each transmission line end is terminated using the device attached at one end of the transmission line and by another device attached at the other end and reflections due to mismatches in impedance by inclusion of intermediate signaling nodes are controlled to allow multi-drop device support and high speed signaling. The second communications protocol supports multiple audio data rates using a fixed frame format.

Abstract: Artificial intelligence (AI) technology can be used in combination with composable communication goal statements and an ontology to facilitate a user's ability to quickly structure story outlines in a manner usable by an NLG narrative generation system without any need for the user to directly author computer code. This AI technology permits NLG systems to determine the appropriate content for inclusion in a narrative story about a data set in a manner that will satisfy a desired communication goal. The AI NLG computer system can also build and update the ontology concurrently with a user's composition of communication goal statements.

Abstract: A device may identify a plurality of sources for outputs that the device is configured to provide. The plurality of sources may include at least one of a particular application in the device, an operating system of the device, a particular area within a display of the device, or a particular graphical user interface object. The device may also assign a set of distinct voices to respective sources of the plurality of sources. The device may also receive a request for speech output. The device may also select a particular source that is associated with the requested speech output. The device may also generate speech having particular voice characteristics of a particular voice assigned to the particular source.

Abstract: A device, system, and method whereby a speech-driven system can distinguish speech obtained from users of the system from other speech spoken by background persons, as well as from background speech from public address systems. In one aspect, the present system and method prepares, in advance of field-use, a voice-data file which is created in a training environment. The training environment exhibits both desired user speech and unwanted background speech, including unwanted speech from persons other than a user and also speech from a PA system. The speech recognition system is trained or otherwise programmed to identify wanted user speech which may be spoken concurrently with the background sounds. In an embodiment, during the pre-field-use phase the training or programming may be accomplished by having persons who are training listeners audit the pre-recorded sounds to identify the desired user speech. A processor-based learning system is trained to duplicate the assessments made by the human listeners.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting hotwords using a server. One of the methods includes receiving an audio signal encoding one or more utterances including a first utterance; determining whether at least a portion of the first utterance satisfies a first threshold of being at least a portion of a key phrase; in response to determining that at least the portion of the first utterance satisfies the first threshold of being at least a portion of a key phrase, sending the audio signal to a server system that determines whether the first utterance satisfies a second threshold of being the key phrase, the second threshold being more restrictive than the first threshold; and receiving tagged text data representing the one or more utterances encoded in the audio signal when the server system determines that the first utterance satisfies the second threshold.

Abstract: A text analytics platform includes instructions embodied in one or more non-transitory machine accessible storage media configured to cause a computing device to retrieve text from at least one text source and implement one or more algorithms to determine a quantitative linguistics assessment for the retrieved text and provide as output a numeric value corresponding to the quantitative linguistics assessment. The quantitative linguistics assessment is based at least in part on a trained model.