Abstract: In one aspect, a playback device is configured to identify in an audio stream, via a second wake-word engine, a false wake word for a first wake-word engine that is configured to receive as input sound data based on sound detected by a microphone. The first and second wake-word engines are configured according to different sensitivity levels for false positives of a particular wake word. Based on identifying the false wake word, the playback device is configured to (i) deactivate the first wake-word engine and (ii) cause at least one network microphone device to deactivate a wake-word engine for a particular amount of time. While the first wake-word engine is deactivated, the playback device is configured to cause at least one speaker to output audio based on the audio stream. After a predetermined amount of time has elapsed, the playback device is configured to reactivate the first wake-word engine.

Abstract: A method for multi-channel audio or speech signal processing includes receiving a reference channel and a target channel, determining a variation between a first mismatch value and a second mismatch value, and comparing the variation with a first threshold that may have a pre-determined value or may be adjusted based on a frame type or a smoothing factor. The method also includes adjusting a set of target samples of the target channel based on the variation and based on the comparison to generate an adjusted set of target samples. Adjusting the set of target samples includes selecting one among a first interpolation and a second interpolation based on the variation. The method further includes generating at least one encoded channel based on a set of reference samples and the adjusted set of target samples. The method also includes transmitting the at least one encoded channel to a second device.

Abstract: A voice dialog device includes a sight line detection unit configured to detect a sight line of a user, a voice acquiring unit configured to acquire voice pronounced by the user, and a processor. The processor is configured to perform a step of acquiring a result of recognizing the voice, a step of determining whether or not the user is driving, and a step of determining whether or not the voice dialog device has a dialog with the user. When the detected sight line of the user is in a certain direction, and a start keyword has been detected from the voice, the processor determines that the user has started a dialog. The processor switches the certain direction based on whether the user is driving.

Abstract: An electronic device and method for text processing, the electronic device comprises a processor (100), and the processor is configured to: determine a correlation between a first text vector and a second text vector, wherein the first text vector and the second text vector are multi-dimensional, real number vectors generated on the basis of a same text, respectively; obtain, according to the correlation, a third text vector representing the text, wherein a vector space in which the third text vector is located is correlated to vector spaces in which first text and second text vectors are located. The electronic device and method of the present invention can be used to create a text-feature representation model which represents text features by combining a plurality of view angles, thereby improving the performance of natural language processing.

Abstract: A control platform that involves a natural language engine with a risk-based corpora, a rules engine with feature vectors from labelled change records, and topic model to generate an expected label for an additional change record based on training data generated from the labelled change records and the risk-based corpora.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for language models using domain-specific model components. In some implementations, context data for an utterance is obtained. A domain-specific model component is selected from among multiple domain-specific model components of a language model based on the non-linguistic context of the utterance. A score for a candidate transcription for the utterance is generated using the selected domain-specific model component and a baseline model component of the language model that is domain-independent. A transcription for the utterance is determined using the score the transcription is provided as output of an automated speech recognition system.

Abstract: In non-limiting examples of the present disclosure, systems, methods and devices for providing personalized experiences to a computing device based on user input such as voice, text and gesture input are provided. Acoustic patterns associated with voice input, speech patterns, language patterns and natural language processing may be used to identify a specific user providing input from a plurality of users, identify user background characteristics and traits for the specific user, and topically categorize user input in a tiered hierarchical index. Topically categorized user input may be supplemented with user data and world knowledge and personalized responses and feedback for an identified specific user may be provided reactively and proactively.

Abstract: A spoken dialogue system comprising: an input for receiving data relating to speech signals originating from a user, where the speech signals form part of a dialogue; an output for outputting information specified by an action; and a processor configured to: extract one or more acoustic features from the input speech signal; determine an action using a dialogue model, wherein the input to the dialogue model is generated using the input speech signal; output information specified by the action at the output; generate a success measure using the acoustic features.

Abstract: Apparatus for mapping a user utterance onto a plurality of intents is provided. The apparatus may include an intent training database that includes a plurality of tokens and intents. The apparatus may include a processor. The processor may utilize a token-intent map to generate a token-row map and an intent-column map. The processor may map the plurality of tokens onto a token-intent matrix. The processor may generate a token-cognitive matrix, a cognitive-comprehension matrix and an intent-cognitive matrix from the decomposition. The cognitive-comprehension matrix may be the space of entanglement between the token-cognitive matrix and the intent-cognitive matrix. The processor may reduce the rank of the cognitive-comprehension matrix. The processor may compute a plurality of token vectors from a computation of the token-cognitive matrix and the cognitive-comprehension matrix.

Abstract: A method, system, and/or computer program product for identifying and replacing a deficient component in a product. One or more processors deconstruct a text product review into multiple n-grams, where each of the multiple n-grams is a review of a particular component from components of a product. The processor(s) generate a component numeric rating value (CNRV) for each of the multiple n-grams, where the CNRV is based on an analysis of each of the multiple n-grams. The processor(s) identify a deficient component of the product. The processor(s) identify a cause of the deficiency in the deficient component and identify a replacement component that does not cause the deficiency in the deficient component. The processor(s) direct a manufacturing device that manufactures the product to replace the deficient component with the replacement component.

Abstract: A voice control processing method and apparatus, where the method includes enabling, by a terminal in a data service disabled state, a data service after the terminal receives a voice instruction using a first application, where the first application is an application program used for voice control in the terminal, prohibiting, by the terminal, another application other than the first application in the terminal from using the data service, and controlling, by the terminal, the first application to execute the voice instruction using the data service, after the terminal enables the data service. The terminal in a data service disabled state receives the voice instruction. Then, the terminal enables the data service and prohibits another application from using the data service.

Abstract: A lyrics analyzer generates tags and explicitness indicators for a set of tracks. These tags may indicate the genre, mood, occasion, or other features of each track. The lyrics analyzer does so by generating an n-dimensional vector relating to a set of topics extracted from the lyrics and then using those vectors to train a classifier to determine whether each tag applies to each track. The lyrics analyzer may also generate playlists for a user based on a single seed song by comparing the lyrics vector or the lyrics and acoustics vectors of the seed song to other songs to select songs that closely match the seed song. Such a playlist generator may also take into account the tags generated for each track.

Abstract: One or more factors associated with consuming digital content on at least one device associated with at least one user are assessed. One or more ameliorative actions for consuming the digital content are performed based on the assessment. Performing the one or more ameliorative actions comprises delivering a summarization of the digital content to the at least one device based on the assessment.

Abstract: Various embodiments generally relate to systems and methods for creation of voice memos while an electronic device is in a driving mode. In some embodiments, a triggering event can be used to indicate that the electronic device is within a car or about to be within a car and that text communications should be translated (e.g., via an application or a conversion platform) into a voice memo that can be played via a speaker. These triggering events can include a manual selection or an automatic selection based on a set of transition criteria (e.g., electronic device moving above a certain speed, following a roadway, approaching a location in a map of a marked car, etc.).

Abstract: Applied Artificial Intelligence Technology for Using Natural Language Processing and Concept Expression Templates To Train a Natural Language Generation System Disclosed herein is computer technology that applies natural language processing (NLP) techniques to training data to generate information used to train a natural language generation (NLG) system to produce output that stylistically resembles the training data. In this fashion, the NLG system can be readily trained with training data supplied by a user so that the NLG system is adapted to produce output that stylistically resembles such training data. In an example, an NLP system detects a plurality of linguistic features in the training data. These detected linguistic features are then aggregated into a specification data structure that is arranged for training the NLG system to produce natural language output that stylistically resembles the training data.

Abstract: Aspects of the subject disclosure may include, for example, a system that performs operations including receiving one or more media processor commands generated by a voice processing system that synthesizes the one or more media processor commands according to voice data provided by a portable device by way of an adapter, and executing the one or more media processor commands to generate an updated presentation of media content. The adapter converts a first radio frequency (RF) signal to a second RF signal comprising the voice data, the first RF signal generated by the portable device according to a first RF protocol, the second RF signal conforming to a second RF protocol that differs from the first RF protocol, and the second RF signal comprising routing information to route the voice data to the voice processing system. Other embodiments are disclosed.

Abstract: Techniques for implementing dynamic volume adjustment by a virtual assistant are provided. In one embodiment, the virtual assistant can receive a voice query or command from a user, recognize the content of the voice query or command, process the voice query or command based on the recognized content, and determine an auditory response to be output to the user. The virtual assistant can then identify a plurality of criteria for automatically determining an output volume level for the response, where the plurality of criteria including content-based criteria and environment-based criteria, calculate values for the plurality of criteria, and combine the values to determine the output volume level. The virtual assistant can subsequently cause the auditory response to be output to the user at the determined output volume level.

Abstract: It is inter alia disclosed to determine a first quantized representation of an input vector, and to determine a second quantized representation of the input vector based on a codebook depending on the first quantized representation.

Abstract: A system, article, and method provide temporal-domain feature extraction for automatic speech recognition.

Abstract: Apparatus for mapping a user utterance onto a plurality of intents is provided. The apparatus may include an intent training database that includes a plurality of tokens and intents. The apparatus may include a processor. The processor may utilize a token-intent map to generate a token-row map and an intent-column map. The processor may map the plurality of tokens onto a token-intent matrix. The processor may generate a token-cognitive matrix, a cognitive-comprehension matrix and an intent-cognitive matrix from the decomposition. The cognitive-comprehension matrix may be the space of entanglement between the token-cognitive matrix and the intent-cognitive matrix. The processor may reduce the rank of the cognitive-comprehension matrix. The processor may compute a plurality of token vectors from a computation of the token-cognitive matrix and the cognitive-comprehension matrix.