Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating dialogue responses based on received utterances utilizing an independent gate context-dependent additive recurrent neural network. For example, the disclosed systems can utilize a neural network model to generate a dialogue history vector based on received utterances and can use the dialogue history vector to generate a dialogue response. The independent gate context-dependent additive recurrent neural network can remove local context to reduce computation complexity and allow for gates at all time steps to be computed in parallel. The independent gate context-dependent additive recurrent neural network maintains the sequential nature of a recurrent neural network using the hidden vector output.

Abstract: A dialogue processing apparatus and method monitor an intensity of an acoustic signal that is input in real time and determine that speech recognition has started, when the intensity of the input acoustic signal is equal to or greater than a reference value, allowing a user to start speech recognition by an utterance without an additional trigger. A vehicle can include the apparatus and method. The apparatus includes: a monitor to compare an input signal level with a reference level in real time and to determine that speech is input when the input signal level is greater than the reference level; a speech recognizer to output a text utterance by performing speech recognition on the input signal when it is determined that the speech is input; a natural language processor to extract a domain and a keyword based on the utterance; and a dialogue manager to determine whether a previous context is maintained based on the domain and the keyword.

Abstract: Provided are systems, methods, and devices for extracting unconscious meaning from media corpora. One or more corpora are received from one or more media databases. A number of phrases are extracted from the corpora, and then disambiguated according to natural language processing methods. One or more criteria are then selected to be used for phrase analysis, and the phrases are then analyzed to extract unconscious meaning based on the one or more criteria. The phrase analysis involves machine learning or predictive analysis methods. The results of the phrase analysis are then provided to one or more client devices, with the results containing findings of unconscious meaning for the phrases.

Abstract: One embodiment provides a method, including: receiving, at an information handling device, voice input; determining, using at least one sensor associated with the information handling device, whether the voice input comprises voice input provided proximate to the information handling device; and providing, based on determining that the voice input is provided proximate to the information handling device, output responsive to the voice input. Other aspects are described and claimed.

Abstract: Multi-turn conversation systems that are personalized to a user based on insights derived from big data are described. A computer-based conversation system for interacting with a user includes: a CPU, a computer readable memory, and a computer readable storage medium associated with a computer device; and program instructions defining a statement and question framer that is configured to: obtain insights about a user from a big data engine; and generate a response to an input from the user based on the insights and the input. The program instructions are stored on the computer readable storage medium for execution by the CPU via the computer readable memory.

Abstract: In some natural language understanding (NLU) applications, results may not be tailored to the user's query. In an embodiment of the present invention, a method includes tagging elements of automated speech recognition (ASR) data based on an ontology stored in a memory. The method further includes indexing tagged elements to an entity of the ontology. The method further includes generating a logical form of the ASR data based on the tagged elements and the indexed entities. The method further includes mapping the logical form to a query to a respective corresponding database stored in the memory. The method further includes issuing the query to the respective corresponding databases. The method further includes presenting results of the query to the user via a display or a voice response system.

Abstract: An electronic device and method are disclosed. The electronic device includes a touchscreen, microphone, speaker, wireless communication circuit, processor and memory. The memory stores instructions executable by the processor to: receive a first user utterance through the microphone, transmit, by the wireless communication circuit, the received first user utterance to an external server through the wireless communication circuit, receive, by the wireless communication circuit, first text data generated by the external server using automatic speech recognition (ASR), when the first text data includes at least one pre-stored word, phrase, and sentence, identifying a plurality of tasks mapped to the at least one pre-stored word, phrase, and sentence, and execute the identified plurality of tasks using at least one of sequential execution or parallel execution.

Abstract: The technology disclosed relates to computer-implemented conversational agents and particularly to detecting a point in the dialog (end of turn, or end of utterance) at which the agent can start responding to the user. The technology disclosed provides a method of incrementally parsing an input utterance with multiple parses operating in parallel. The technology disclosed includes detecting an interjection point in the input utterance when a pause exceeds a high threshold, or detecting an interjection point in the input utterance when a pause exceeds a low threshold and at least one of the parallel parses is determined to be interruptible by matching a complete sentence according to the grammar. The conversational agents start responding to the user at a detected interjection point.

Abstract: An apparatus includes a memory and a hardware processor. The memory stores a threshold. The processor receives first, second, and third messages. The processor determines a number of occurrences of words in the messages. The processor also calculates probabilities that a word in the messages is a particular word and co-occurrence probabilities. The processor further calculates probability distributions of words in the messages. The processor also calculates probabilities based on the probability distributions. The processor compares these probabilities to a threshold to determine whether the first message is related to the second message and/or whether the first message is related to the third message.

Abstract: A technique is described for generating a knowledge graph that links names associated with a first subject matter category (C1) (such as brands) with names associated with a second subject matter category (C2) (such as products). In one implementation, the technique relies on two similarly-constituted processing pipelines, a first processing pipeline for processing the C1 names, and a second processing pipeline for processing the C2 names. Each processing pipeline includes three main stages, including a name-generation stage, a verification stage, and an augmentation stage. The generation stage uses a voting strategy to form an initial set of seed names. The verification stage removes noisy seed names. And the augmentation stage expands each verified name to include related terms. A final edge-forming stage identifies relationships between the expanded C1 names and the expanded C2 names using a voting strategy.

Abstract: A text-to-speech method includes outputting an instruction according to voice information entered by a user; obtaining text information according to the instruction; converting the text information to audio; and playing the audio. According to the embodiments of the present invention, news or other text content in a browser can be played by voice, which liberates hands and eyes of a user. The user can use the browser in some scenarios where the user cannot easily use the browser, such as driving a car, thereby improving user experience.

Abstract: A method to select a response in a multi-turn conversation between a user and a conversational bot. The conversation is composed of a set of events, wherein an event is a linear sequence of observations that are user speech or physical actions. Queries are processed against a set of conversations that are organized as a set of inter-related data tables, with events and observations stored in distinct tables. As the multi-turn conversation proceeds, a data model comprising an observation history, together with a hierarchy of events determined to represent the conversation up to at least one turn, is persisted. When a new input (speech or physical action) is received, it is classified using a statistical model to generate a result. The result is then mapped to an observation in the data model. Using the mapped observation, a look-up is performed into the data tables to retrieve a possible response.

Abstract: In one aspect, a computerized method useful for, with an ensemble of Natural Language Understanding and Processing methods converting a set of user actions into machine queries, includes the step of providing a knowledge model. The method includes the step of receiving a natural language user query; preprocesses the natural language user query for further processing as a preprocessed user query. The preprocessing includes the step of chunking a set of sentences of the natural language query into a set of smaller sentences and retaining the reference between chunks of the set of sentences. The method includes the step of, with the preprocessed user query. For each chunk of the chunked preprocessed user query the method implements the following steps.

Abstract: A system comprising: a processor; a data bus coupled to the processor; and a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus. The computer program code interacting with a plurality of computer operations and comprising instructions executable by the processor and configured for: receiving data from a data source; processing the data, the processing comprising performing a parsing operation on the data, the processing the data identifying a plurality of knowledge elements based upon the parsing operation, the parsing operation comprising ranking of parse options; and, storing the knowledge elements within the cognitive graph as a collection of knowledge elements, the storing universally representing knowledge obtained from the data.

Abstract: A method includes receiving a speech input from a user and obtaining context metadata associated with the speech input. The method also includes generating a raw speech recognition result corresponding to the speech input and selecting a list of one or more denormalizers to apply to the generated raw speech recognition result based on the context metadata associated with the speech input. The generated raw speech recognition result includes normalized text. The method also includes denormalizing the generated raw speech recognition result into denormalized text by applying the list of the one or more denormalizers in sequence to the generated raw speech recognition result.

Abstract: Methods, programming, and system for modifying a slot value are described herein. In a non-limiting embodiment, an intent may be determined based on a first utterance. A first slot-value pair may be obtained for the first utterance based on the intent, the first slot-value pair including a first slot and a first value associated with the first slot. A second value associated with the first slot may be identified, the second value being identified from a second utterance that was previously received. Based on the intent and the first slot, a type of update to be performed with respect to the second value may be determined. The second value may then be updated based on the first value and the type of update.

Abstract: A method for processing a recognition result of an automatic online speech recognizer for a mobile end device by a communication exchange device, wherein the recognition result for a phrase spoken by a user is received from the online speech recognizer as a text. A language model of permitted phrases is received from the mobile end device. A specification of meaning relating to a meaning of the phrase is assigned to each permitted phrase by the language model, and, through a decision-making logic of the communication exchange device, the text of the recognition result is compared with the permitted phrases defined by the language model and, for a matching permitted phrase in accordance with a predetermined matching criterion, the specification of meaning thereof is determined and the specification of meaning is provided to the mobile end device.

Abstract: A computer system, computer program product, and computer-implemented method for communicating electronic messages over a communication network coupled thereto are provided. The computer system comprises a network interface for receiving messages sent over the network and addressed to a user of the computer system; and computer executable electronic message processing software. The software comprises instructions for directing the computer system to receive a message over the network, and to identify whether a sender of the received electronic message is a human or a machine. The identifying includes first and second phases of operation. The first phase includes an offline phase employing information and activities resident on the computer system. The second phase includes an online phase employing resources remotely accessible over the network.

Abstract: [Object] To provide an information processing system and an information processing method capable of auditing the utterance data of an agent more flexibly. [Solution] An information processing system including: a storage section that stores utterance data of an agent; a communication section that receives request information transmitted from a client terminal and requesting utterance data of a specific agent from a user; and a control section that, when the request information is received through the communication section, replies to the client terminal with corresponding utterance data, and in accordance with feedback from the user with respect to the utterance data, updates an utterance probability level expressing a probability that the specific agent will utter utterance content indicated by the utterance data, and records the updated utterance probability level in association with the specific agent and the utterance content in the storage section.

Abstract: An embodiment provides a method, including: receiving, via an audio receiver of an information handling device, user voice input; identifying a first word based on the user voice input; accessing a word association data store; selecting an equivalent based on an association with the first word within the word association data store; committing an action based on the equivalent; receiving feedback input from the user regarding the equivalent; and updating the selecting based on the feedback. Other aspects are described and claimed.

Abstract: A system or method for aligning in time a first transcript to audio data used to create the first transcript. The system or method performs the following actions. Receiving the first transcript. The first transcript includes a first plurality of words that are in the audio data. Transcribing the audio data to make a second transcript. The second transcript includes a second plurality of words that are in the audio data and a respective time of a location in the audio data of each word of the second plurality. For each word of the second plurality found in the first plurality, assigning the respective time of the location of the word of the second plurality to the word of the first plurality thereby aligning in time the first transcript to the audio data.

Abstract: Systems and processes for rule-based natural language processing are provided. In accordance with one example, a method includes, at an electronic device with one or more processors, receiving a natural-language input; determining, based on the natural-language input, an input expression pattern; determining whether the input expression pattern matches a respective expression pattern of each of a plurality of intent definitions; and in accordance with a determination that the input expression pattern matches an expression pattern of an intent definition of the plurality of intent definitions: selecting an intent definition of the plurality of intent definitions having an expression pattern matching the input expression pattern; performing a task associated with the selected intent definition; and outputting an output indicating whether the task was performed.

Abstract: The exemplary embodiments described herein are related to techniques for automatically generating narratives about data based on communication goal data structures that are associated with configurable content blocks. The use of such communication goal data structures facilitates modes of operation whereby narratives can be generated in real-time and/or interactive manners.

Abstract: A cooperative conversational voice user interface is provided. The cooperative conversational voice user interface may build upon short-term and long-term shared knowledge to generate one or more explicit and/or implicit hypotheses about an intent of a user utterance. The hypotheses may be ranked based on varying degrees of certainty, and an adaptive response may be generated for the user. Responses may be worded based on the degrees of certainty and to frame an appropriate domain for a subsequent utterance. In one implementation, misrecognitions may be tolerated, and conversational course may be corrected based on subsequent utterances and/or responses.

Abstract: An electronic health record compatible dictation transcription system records and edits audio in an encrypted format. The system delineates audio for different electronic health record fields during dictation (i.e., recording and editing of the audio in the encrypted format), and the system inserts large predetermined text portions into transcriptions of dictated text in response to verbal prompts in the dictation audio.

Abstract: Example embodiments are disclosed where a narrative generation platform is integrated with a conversational interface such as a Chatbot to support interactive and dynamic narrative generation in response to speech inputs from users. Such a system can be further integrated with a visualization platform to allow the speech input through the conversational interface to interactively and dynamically focus and control visualizations and/or narratives that accompany the visualizations.

Abstract: A playback device comprises a network interface configured to communicate with a network microphone device. A processor of the playback device comprises instructions, which when executed, cause the processor to receive a message associated with the network microphone device; and adjust a volume of audio content below a volume of content associated with the network microphone device based on the message.

Abstract: A neural paraphrase generator receives a sequence of tuples comprising a source sequence of words, each tuple comprising word data element and structured tag element representing a linguistic attribute about the word data element. An RNN encoder receives a sequence of vectors representing a source sequence of words, and RNN decoder predicts a probability of a target sequence of words representing a target output sentence based on a recurrent state in the decoder. An input composition component includes a word embedding matrix and a tag embedding matrix, and receives and transforms the input sequence of tuples into a sequence of vectors by 1) mapping word data elements to word embedding matrix to generate word vectors, 2) mapping structured tag elements to tag embedding matrix to generate tag vectors, and 3) concatenating word vectors and tag vectors.

Abstract: The present disclosure describes systems and methods of fraud protection. A listening device may monitor ambient sound and detect one or more triggering sound patterns. The listening device may record the one or more triggering sound patterns and record a person's voice, and send the recordings to a server, wherein the server is configured to calculate a confidence level of fraud based on the one or more triggering sound patterns and the recording of the person's voice using a speech pattern model of the person, and to output an alert if the confidence level of fraud is greater than a threshold value.

Abstract: The present disclosure generally relates to using voice interaction to access call functionality of a companion device. In an example process, a user utterance is received. Based on the user utterance and contextual information, the process causes a server to determine a user intent corresponding to the user utterance. The contextual information is based on a signal received from the companion device. In accordance with the user intent corresponding to an actionable intent of answering the incoming call, a command is received. Based on the command, instructions are provided to the companion device, which cause the companion device to answer the incoming call and provide audio data of the answered incoming call. Audio is outputted according to the audio data of the answered incoming call.

Abstract: A question answering system that determines whether a question is off-topic by performing the following steps: (i) receiving, by a question answering system, a set of documents; (ii) identifying topical subset(s) for each document of the set of documents using named entity recognition, where each topical subset relates to a corresponding topic; (iii) assigning a set of topic score(s) for each topical subset using natural language processing, where each topic score relates to a corresponding probability associated with the respective topical subset under a probabilistic language model; and (iv) determining, based, at least in part, on the topic score(s) corresponding to the topical subset(s), whether a question input into the question answering system is off-topic.

Abstract: Methods, systems, and apparatus for performing speech recognition. In some implementations, acoustic data representing an utterance is obtained. The acoustic data corresponds to time steps in a series of time steps. One or more computers process scores indicative of the acoustic data using a recurrent neural network to generate a sequence of outputs. The sequence of outputs indicates a likely output label from among a predetermined set of output labels. The predetermined set of output labels includes output labels that respectively correspond to different linguistic units and to a placeholder label that does not represent a classification of acoustic data. The recurrent neural network is configured to use an output label indicated for a previous time step to determine an output label for the current time step. The generated sequence of outputs is processed to generate a transcription of the utterance, and the transcription of the utterance is provided.

Abstract: The present disclosure discloses a method and a device for locating an answer based on question and answer, in which the method includes: receiving a query sentence; parsing the query sentence, to generate a semantic parse tree corresponding to the query sentence; matching the semantic parse tree with a pre-established matching base, to obtain an alignment probability between each of candidate answers in the pre-established matching base and the semantic parse tree; and determining a final answer according to the alignment probability.

Abstract: A system of multi-modal transmission of packetized data in a voice activated data packet based computer network environment is provided. A natural language processor component can parse an input audio signal to identify a request and a trigger keyword. Based on the input audio signal, a direct action application programming interface can generate a first action data structure, and a content selector component can select a content item. An interface management component can identify first and second candidate interfaces, and respective resource utilization values. The interface management component can select, based on the resource utilization values, the first candidate interface to present the content item. The interface management component can provide the first action data structure to the client computing device for rendering as audio output, and can transmit the content item converted for a first modality to deliver the content item for rendering from the selected interface.

Abstract: Electronic reading devices provide readers with text on a display, and enhancements to their functionality and efficiency are discussed herein. Text is provided to the reader in an enhanced contrast mode that highlights the active word and line of the text as well as words of interest in the text so as to improve the functionality of the electronic reading device itself as a provider of textual content.

Abstract: A device detects a wake-up keyword from a received speech signal of a user by using a wake-up keyword model, and transmits a wake-up keyword detection/non-detection signal and the received speech signal of the user to a speech recognition server. The speech recognition server performs a recognition process on the speech signal of the user by setting a speech recognition model according to the detection or non-detection of the wake-up keyword.

Abstract: Topics of potential interest to a user, useful for purposes such as targeted advertising and product recommendations, can be extracted from voice content produced by a user. A computing device can capture voice content, such as when a user speaks into or near the device. One or more sniffer algorithms or processes can attempt to identify trigger words in the voice content, which can indicate a level of interest of the user. For each identified potential trigger word, the device can capture adjacent audio that can be analyzed, on the device or remotely, to attempt to determine one or more keywords associated with that trigger word. The identified keywords can be stored and/or transmitted to an appropriate location accessible to entities such as advertisers or content providers who can use the keywords to attempt to select or customize content that is likely relevant to the user.

Abstract: A method for receiving processed information at a remote device is described. The method includes transmitting from the remote device a verbal request to a first information provider and receiving a digital message from the first information provider in response to the transmitted verbal request. The digital message includes a symbolic representation indicator associated with a symbolic representation of the verbal request and data used to control an application. The method also includes transmitting, using the application, the symbolic representation indicator to a second information provider for generating results to be displayed on the remote device.

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 for estimating a quality of semantic match of a first sentence to a second sentence comprises outputting a first hierarchy of representations of the first sentence at increasing degrees of semantic compression, outputting a second hierarchy of representations of the second sentence at increasing degrees of semantic compression, comparing a selected representation in the first hierarchy to each of a plurality of representations in the second hierarchy, comparing a selected representation in the second hierarchy to each of a plurality of representations in the first hierarchy, and outputting a match value indicating a quality of semantic match between the first sentence and the second sentence, the match value based at least on the comparisons.

Abstract: An information processing system, a computer program product, and methods for modeling multi-party dialog interactions. A method includes learning, directly from data obtained from a multi-party conversational channel, to identify particular multi-party dialog threads as well as participants in one or more conversations. Each participant utterance being converted to a continuous vector representation updated in a model of the multi-party dialog relative to each participant utterance and according to each participant's role selected from the set of: sender, addressee, or observer. The method trains the model to choose a correct addressee and a correct response for each participant utterance, using a joint selection criterion. The method learns directly from the data obtained from the multi-party conversational channel, which dialog turns belong to each particular multi-party dialog thread.

Abstract: A method, system and computer program product for finding groups of potential duplicates in attribute values. Each attribute value of the attribute values is converted to a respective set of bigrams. All bigrams present in the attribute values may be determined. Bigrams present in the attribute values may be represented as bits. This may result in a bitmap representing the presence of the bigrams in the attribute values. The attribute values may be grouped using bitwise operations on the bitmap, where each group includes attribute values that are determined based on pairwise bigram-based similarity scores. The pairwise bigram-based similarity score reflects the number of common bigrams between two attribute values.

Abstract: One or more computing devices, systems, and/or methods for dynamically selecting a personality for a digital assistant are provided. For example, audio associated with a conversation with a digital assistant may be received from a user. The audio may be converted into a request comprising text. A task may be determined based upon the request. One or more sentences associated with information associated with the task may be determined. A context of the conversation may be determined based upon the request and a user profile of the user. A first personality may be selected for the digital assistant from one or more personalities based upon the context of the conversation. The first personality may be used to generate audio of the one or more sentences. The audio of the one or more sentences may be presented as part of the conversation to the user.

Abstract: Aspects herein provide third party application authors with a user interface authoring platform that automates and simplifies a task definition process while also providing the ability to leverage pre-existing language understanding models and canonicalization and resolution modules that are provided by the operating system on which the CU system resides or as provided by other third parties. In particular, the present disclosure provides a method and system for authoring a task using a user interface authoring platform.

Abstract: Embodiments for training a conversational system using intent classification are provided. Example utterances recommended to be associated with a particular semantic scope of intent are received from a plurality of sources. Respective ones of the example utterances from the plurality of sources are portioned and stored in a plurality of pools. The respective example utterances from the plurality of pools are collated into a unified pool according to weighting assigned to each one of the plurality of pools, the weighting associated with user actions taken on the respective example utterances. A unified set of the example utterances from the unified pool is output for selection by the user to train an intent classifier associated with the semantic scope of intent for the conversational system.

Abstract: Methods and systems for information retrieval include analyzing audio data to produce one or more word hypotheses, each word hypothesis having an associated confidence value. The one or more word hypotheses are displayed in motion across a graphical display. Information retrieval is performed in accordance with one or more selected terms from the displayed word hypotheses.

Abstract: One embodiment provides a method, including: receiving user voice input comprising a user command to perform an action; determining whether the user command comprises a high risk command or a low risk command; providing a first audible query and a second audible query, wherein the first audible query and the second audible query are related to a verification request for verifying that the user voice input is provided by a user and wherein an answer corresponding to one of the first audible query and the second audible query is stored in a system; receiving a first voice answer input responsive to the first audible query and a second voice answer input responsive to the second audible query; and performing, responsive to determining that at least one of the first voice answer input and the second voice answer input matches the answer stored in the system, the action.

Abstract: A control method improves a user's ability to navigate in speech-containing audio data during playback of the audio data on a computing device. The control method is executed by a processor in the computing device and comprises operating (51) a media player on the computing device to play the audio data, detecting (52) a user-initiated time-shift command to step forward or backward in the audio data, and, after detecting the time-shift command at a current time in the audio data, identifying (55) a starting point of a sentence in the audio data and operating (56) the media player to play the audio data from the starting point.

Abstract: A system and method for facilitating transactions utilizing phrase tokens are provided. Individual entities can be associated with unambiguous transaction phrase tokens, such as multiple word phrases. The transaction phrase tokens are associated with transaction accounts by a service provider such that the entities can complete a transaction without having to exchange transaction account information. In a transaction, a transaction phrase token is offered to an accepting party, which tenders the offered transaction phrase token to the service provider. The service provider processes the offered transaction phrase token according to configuration information specified for the transaction phrase token. The service provider can automatically process the transaction request or request additional information.

Abstract: Systems and methods are provided for implementing an educational dialog system. An initial task model is accessed that identifies a plurality of dialog states associated with a task, a language model configured to identify a response meaning associated with a received response, and a language understanding model configured to select a next dialog state based on the identified response meaning. The task is provided to a plurality of persons for training. The task model is updated by revising the language model and the language understanding model based on responses received to prompts of the provided task, and the updated task is provided to a student for development of speaking capabilities.