Abstract: Disclosed are devices, systems, apparatus, methods, products, and other implementations, including a method comprising obtaining, by a device, a combined sound signal for signals combined from multiple sound sources in an area in which a person is located, and applying, by the device, speech-separation processing (e.g., deep attractor network (DAN) processing, online DAN processing, LSTM-TasNet processing, Conv-TasNet processing), to the combined sound signal from the multiple sound sources to derive a plurality of separated signals that each contains signals corresponding to different groups of the multiple sound sources. The method further includes obtaining, by the device, neural signals for the person, the neural signals being indicative of one or more of the multiple sound sources the person is attentive to, and selecting one of the plurality of separated signals based on the obtained neural signals. The selected signal may then be processed (amplified, attenuated).

Abstract: User input handling by a virtual assistant includes receiving a sequence of natural language statements provided by a user to a virtual assistant, applying a cognitive model to the sequence of statements and determining whether the sequence of statements provides a complete problem description, by the user, to which the virtual assistant is to respond in assisting the user address a problem that the user experiences, prompting the user to provide an additional one or more statements to complete the problem description, based on completing the problem description, formulating and providing a response to the user based on a determined intent of the complete problem description, and monitoring input by the user based on providing the response, the input informing feedback for further training of the cognitive model to identify whether statement sequences provide complete or incomplete problem descriptions.

Abstract: In one embodiment, a method includes receiving a user request from a client system associated with a user, determining that the user request corresponds to a first suspended task, retrieving a first dialog state of the first suspended task from a dialog history associated with the user, generating a summary of the first suspended task based on the first dialog state using a natural-language generating (NLG) module, and sending instructions to the client system for providing the summary of the first suspended task to the user.

Abstract: A computer system includes processor hardware configured to execute instructions that include joining at least a portion of multiple call transcription data entries with at least a portion of multiple agent call log data entries according to timestamps associated with the entries to generate a set of joined call data entries, and validating the joined call data entry by determining whether a transcribed entity name matches with entity identifier information associated with the agent call log data entry. The instructions include preprocessing the joined call data entry according to word confidence score data entries associated with the call transcription data entry to generate preprocessed text, performing natural language processing vectorization on the preprocessed text to generate an input vector, and supplying the input vector to an unsupervised machine learning model to assign an output topic classification of the model to the joined call data entry associated with the input vector.

Abstract: Systems, apparatuses, and methods are described for wireless communications. A wireless device may select a reference signal and/or random access channel resource based on configuration parameters for a beam failure recovery procedure. A base station may send configuration parameters using a medium access control (MAC) control element (CE).

Abstract: In an approach for routing a user analytic request to a registry of analytics models and data sources and operationalizing the user analytic request, a processor receives a user analytic request. A processor applies natural language processing to the user analytic request. A processor associates a first set of vectors and a second set of vectors from the user analytic request to one or more analytics models and data sources by utilizing a plurality of domain-specific ontologies and a plurality of knowledge bases. A processor performs a semantic search for one or more concepts in the one or more analytics models and data sources. A processor receives the one or more concepts found in the one or more analytics models and data sources. A processor selects an analytics model to process the user analytic request. A processor executes the analytics model. A processor outputs a result to the user.

Abstract: According to an aspect, an apparatus may include a media streaming device including electronic circuitry configured to receive media content wirelessly from a media content source, and an output cord segment having a first end portion integrally coupled to a structure of the media streaming device, and a second end portion configured to be coupled to a receiving device, where the electronic circuitry is further configured to transmit the received media content through the output cord segment to the receiving device. The apparatus may include a power cord segment having a first end portion configured to be coupled to the media streaming device, and a second end portion configured to be coupled to a power source.

Abstract: Systems and methods provide input and output mode control for audio processing on a user device. Audio processing may be configured by monitoring audio activity on a device having at least one microphone and a digital audio processing unit, collecting information from the monitoring of the activity, including an identification of at least one application utilizing audio processing, and determining a context for the audio processing, the context including at least one of a hardware, software, audio signal and/or environmental context. An audio signal processing configuration is determined based on the application and determined context, an associated audio signal processing mode is selected, and an optimized audio signal generated.

Abstract: A method for operating a transmitting device to communicate with a receiving device is described herein. The method includes the step of the transmitting device selecting a root index value from a set of root index values. The method further includes the step of the transmitting device generating a frequency domain Constant Amplitude Zero Auto-Correlation sequence based on the selected root index value. The method further includes the step of the transmitting device modulating the Constant Amplitude Zero Auto-Correlation sequence by a pseudo-noise sequence. The method further includes the step of the transmitting device generating an Orthogonal Frequency Division Multiplexing symbol, wherein the frequency domain Constant Amplitude Zero Auto-Correlation sequence modulated by the pseudo-noise sequence defines subcarrier values for the Orthogonal Frequency Division Multiplexing symbol.

Abstract: A communication device includes a power amplifier that generates power signals according to one or more operating bands of communication data, with the amplitude being driven and generated in output stages of the power amplifier. The final stage can include an output passive network that suppresses suppress an amplitude modulation-to-phase modulation (AM-PM) distortion. During a back-off power mode a bias of a capacitive unit of the output power network component can be adjusted to minimize an overall capacitance variation. An output passive network can further generate a flat-phase response between dual resonances of operation.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed for source classification using HDMI audio metadata. An example apparatus includes a metadata extractor to extract values of audio encoding parameters from HDMI metadata obtained from a monitored HDMI port of a media device, the HDMI metadata corresponding to media being output from the monitored HDMI port; map the extracted values of the audio encoding parameters to a first unique encoding class (UEC) in a set of defined UECs, different ones of the set of defined UECs corresponding to different combinations of possible values of the audio encoding parameters capable of being included in the HDMI metadata; and identify a media source corresponding to the media output from the HDMI port based on one or more possible media sources mapped to the first UEC.

Abstract: Methods and apparatuses are described in which unstructured computer text is analyzed for generation of customized digital documents. A server tokenizes and encodes historical user interactions and historical digital documents into multidimensional vectors. The server trains an interaction classification model using the multidimensional vectors as input to generate a classification for an input user interaction, and trains a language generation model using the multidimensional vectors as input to generate a customized digital document based upon an input user interaction. The server receives a new user interaction and encodes the new user interaction into a new multidimensional vector. The server executes the trained interaction classification model using the new vector as input to generate a digital document classification. The server executes the trained language generation model using the new vector and the classification as input to generate a customized digital document.

Abstract: Certain embodiments involve using a gated convolutional encoder-decoder framework for applying affective characteristic labels to input text. For example, a method for identifying an affect label of text with a gated convolutional encoder-decoder model includes receiving, at a supervised classification engine, extracted linguistic features of an input text and a latent representation of an input text. The method also includes predicting, by the supervised classification engine, an affect characterization of the input text using the extracted linguistic features and the latent representation. Predicting the affect characterization includes normalizing and concatenating a linguistic feature representation generated from the extracted linguistic features with the latent representation to generate an appended latent representation. The method also includes identifying, by a gated convolutional encoder-decoder model, an affect label of the input text using the predicted affect characterization.

Abstract: Disclosed are an artificial intelligence (AI) system using a machine learning algorithm such as deep learning, and an application thereof. The present disclosure provides an electronic device comprising: an input unit for receiving content data; a memory for storing information on the content data; an audio output unit for outputting the content data; and a processor, which acquires a plurality of data keywords by analyzing the inputted content data, matches and stores time stamps, of the content data, respectively corresponding to the plurality of acquired keywords, based on a user command being inputted, searches for a data keyword corresponding to the inputted user command among the stored data keywords, and plays the content data based on the time stamp corresponding to the searched data keyword.

Abstract: A base station or an associated control entity determines when base station's air interface is threshold highly loaded or is predicted to be threshold highly loaded, and the base station responsively reduces the number of transmit antennas that the base station uses. Further, the base station or associated control entity could determine when the base station's air interface is no longer actually or predicted to be threshold highly loaded, and the base station could responsively increase the number of transmit antennas that the base station uses, such as by reverting to use a default number of antennas. Reducing the number of transmit antennas that the base station uses when its air interface is threshold highly loaded may help to increase air-interface capacity by reducing resource consumption from transmission of reference signals associated with the transmit antennas.

Abstract: Described herein are systems, apparatus, methods and computer program products for machine learning intent classification. In various embodiments, historical utterances provided by users may be utilized for bot training. Context and personally identifiable information may be removed from the utterances. The utterances may be associated with vectors. The utterances and vectors may be used to determine recommendations.

Abstract: A computer system that classifies audio content is described. During operation, the computer system may receive audio content. Then, the computer system may determine a representation of the audio content (such as a signal-processing representation) by performing a transformation on the audio content. In some embodiments, the transformation may include a neural network and/or the representation may include word embedding or sense embedding of words in the audio content. Moreover, the computer system may analyze the representation using a predetermined neural network. Next, the computer system may classify, based at least in part on an output of the predetermined neural network, the audio content as being fake or real, where the fake audio content is, at least in part, computer-generated. Furthermore, the computer system may selectively perform a remedial action based at least in part on the classification.

Abstract: The present disclosure discloses a VAD method and system based on a joint DNN. The method includes: acquiring original audio data and a first frame-level label based on an open-source audio data set, adding noise on the original audio data to obtain first audio data, recording an environment sound to obtain second audio data, and performing clip-level label on the second audio data to obtain a clip-level label; inputting the first audio data, the second audio data and the corresponding labels into a first neural network to obtain a first-stage network model; obtaining a second frame-level label through the first-stage network model, and inputting the second audio data and the second frame-level label into a second neural network to obtain a second-stage network model; and performing VAD on an audio signal based on the first-stage network model and the second-stage network model.

Abstract: A system, method and computer program is provided for generating customized text representations of audio commands. A first speech recognition module may be used for generating a first text representation of an audio command based on a general language grammar. A second speech recognition module may be used for generating a second text representation of the audio command, the second module including a custom language grammar that may include contacts for a particular user. Entity extraction is applied to the second text representation and the entities are checked against a file containing personal language. If the entities are found in the user-specific language, the two text representations may be fused into a combined text representation and named entity recognition may be performed again to extract further entities.

Abstract: A set of documents related to a particular topic, industry, or entity are received. Sentences are extract from each document. The sentences are grouped into tuples of one, two, or three consecutive sentences (i.e., short text sequences). The sentence tuples are clustered based on vector representations of the sentences. For each cluster, a set of tuples that best represents or best fits the cluster is selected. These sentence tuples are fed to an ontology to determine ontological entities associated with each tuple. These determined ontological entities are associated with the clusters corresponding to each tuple. The sentence tuples associated with each cluster are labeled based on the ontological entities associated with the cluster. The labeled sentence tuples may then be used for a variety of purposes such as training a model to determine the topic of short text sequences.