Abstract: Techniques for processing a user input are described. Text data representing a user input is processed with respect to at least one finite state transducer (FST) to generate at least one FST hypothesis. Context information may be required to traverse one or more paths of the at least one FST. The text data is also processed using at least one statistical model (e.g., perform intent classification, named entity recognition, and/or domain classification processing) to generate at least one statistical model hypothesis. The at least one FST hypothesis and the at least one statistical model hypothesis are input to a reranker that determines a most likely interpretation of the user input.

Abstract: Apparatus and methods for training and operating of robotic devices. Robotic controller may comprise a predictor apparatus configured to generate motor control output. The predictor may be operable in accordance with a learning process based on a teaching signal comprising the control output. An adaptive controller block may provide control output that may be combined with the predicted control output. The predictor learning process may be configured to learn the combined control signal. Predictor training may comprise a plurality of trials. During initial trial, the control output may be capable of causing a robot to perform a task. During intermediate trials, individual contributions from the controller block and the predictor may be inadequate for the task. Upon learning, the control knowledge may be transferred to the predictor so as to enable task execution in absence of subsequent inputs from the controller. Control output and/or predictor output may comprise multi-channel signals.

Abstract: A method includes performing, using at least one processor, feature extraction of input audio data to identify extracted features associated with the input audio data. The method also includes detecting, using the at least one processor, a language associated with each of multiple portions of the input audio data by processing the extracted features using a plurality of language models, where each language model is associated with a different language. In addition, the method includes directing, using the at least one processor, each portion of the input audio data to one of a plurality of automatic speech recognition (ASR) models based on the language associated with the portion of the input audio data.

Abstract: Example embodiments described herein relate to an interactive interface system to maintain a user support profile, wherein the user support profile comprises a plurality of media content that includes user support content, receive a message request from a client device wherein the message request includes an identification of the user support profile and corresponding message content that includes a natural language request, convert the natural language request to a query term, perform a query upon the plurality of media content associated with the user support profile based on the query term, identify relevant media content based on the query, and cause display of the relevant media content within a chat interface at the client device. The interfaces generated and displayed by the interactive interface system therefore enable a user to access user support without having to navigate to a separate interface.

Abstract: The present disclosure provides an intelligent interaction processing method and apparatus, a device and a computer storage medium. The method comprises: performing intention recognition for a preceding feedback item already returned to the user; continuing to return a subsequent feedback item to the user based on the intention of the preceding feedback item. According to the present disclosure, it is possible to guess the user's subsequent intention based on the preceding feedback item, and continue to return the desired subsequent feedback item to the user without the user's operations, so that the present disclosure is more intelligentized and richer and simplifies the user's operations.

Abstract: An artificial intelligence apparatus for recognizing speech of a user includes a microphone, and a processor configured to receive, via the microphone, a sound signal corresponding to the speech of the user, acquire personalize identification information corresponding to the speech, recognize the speech from the sound signal using a global language model, calculate a reliability for the recognition, and if the calculated reliability exceeds a predetermined first reference value, update a personalized language model corresponding to the personalize identification information using the recognition result.

Abstract: An instrument such as an assessment or survey is enhanced using multi-stem definitions to allow a respondent to request alternative versions of a question. The rephrase item is formulated using a rephrase engine which accesses a bank having preexisting rephrases that are equivalent to phrases found in the instrument. The candidate selects a particular complexity level for the rephrase such as simple or elaborate. Rephrasing can be provided automatically based on a timer for answering the item. The system may set a maximum number of allowable rephrases. An analytical engine can be utilized in conjunction with the present invention to analyze requests from multiple candidates. This analysis may show that a particular item is difficult to understand, and the engine can correspondingly suggest to a moderator of the instrument that it be modified by replacing the particular item with a rephrase item.

Abstract: Systems and methods for monitoring and assessing crop health and performance can provide rapid screening of individual plants. The systems and methods have an automated component, and rely primarily on the detection and interpretation of plant-based signals to provide information about crop health. In some cases knowledge from human experts is captured and integrated into the automated crop monitoring systems and methods. Predictive models can also be developed and used to predict future health of plants in a crop.

Abstract: An artificial intelligence apparatus for recognizing speech of a user includes a microphone and a processor configured to acquire, via the microphone, first speech data including speech of a user, generate a first speech recognition result corresponding to the first speech data, perform control corresponding to the generated first speech recognition result, generate an alternative speech recognition result corresponding to the first speech data if negative feedback is acquired from the user, and perform control corresponding to the generated alternative speech recognition result.

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 and systems for contextually based fulfillment of communication requests are provided herein. In some embodiments, a method for contextually based fulfillment of a communication request via a telephony platform, comprises receiving via a telephony-based communication, at a fulfillment center, a user request for a service; determining a service provider capable of fulfilling the user request; translating the user request into one or more user intents; creating a contextual framework based on the user intent; requesting additional information regarding details of the user intent based on the contextual framework; and fulfilling the user request using the user intents when the contextual framework is complete.

Abstract: Techniques for determining a command or intent likely to be subsequently invoked by a user of a system are described. A user inputs a command (either via a spoken utterance or textual input) to a system. The system determines content responsive to the command. The system also determines a second command or corresponding intent likely to be invoked by the user subsequent to the previous command. Such determination may involve analyzing pairs of intents, with each pair being associated with a probability that one intent of the pair will be invoked by a user subsequent to a second intent of the pair. The system then outputs first content responsive to the first command and second content soliciting the user as to whether the system to execute the second command.

Abstract: Systems, methods, devices, and other techniques are described herein for determining dialog states that correspond to voice inputs and for biasing a language model based on the determined dialog states. In some implementations, a method includes receiving, at a computing system, audio data that indicates a voice input and determining a particular dialog state, from among a plurality of dialog states, which corresponds to the voice input. A set of n-grams can be identified that are associated with the particular dialog state that corresponds to the voice input. In response to identifying the set of n-grams that are associated with the particular dialog state that corresponds to the voice input, a language model can be biased by adjusting probability scores that the language model indicates for n-grams in the set of n-grams. The voice input can be transcribed using the adjusted language model.

Abstract: Systems and methods are provided in which a speaker profile-data inquiry is transmitted to a mobile device associated with a first speaker. In response to the speaker-profile-data inquiry, speaker profile data associated with the first speaker is received. Audio data representing a voice input is received. The first speaker is identified as providing the voice input, the identification being based on a comparison of characteristics of the received audio data with the speaker profile data of a plurality of speakers for whom speaker profile data is stored. An instruction, which includes a speaker-relative signifier, is determined from the received audio data, and determining the instruction includes determining a referent of the speaker-relative signifier based on the first speaker profile data. An action indicated by the instruction is performed.

Abstract: A network computer system for managing a network service (e.g., a transport service) can include a voice-assistant subsystem for generating dialogues and performing actions for service providers of the network service. The network computer system can receive, from a user device, a request for the network service. In response, the network computer system can identify a service provider and transmit an invitation to the provider device of the service provider. In response to the identification of the service provider for the request, the voice-assistant subsystem can trigger an audio voice prompt to be presented on the provider device and a listening period during which the provider device monitors for an audio input from the service provider. Based on the audio input captured by the provider device, the network computer system can determine an intent corresponding to whether the service provider accepts or declines the invitation.

Abstract: A computer-implemented method for managing a dialog between a contact center system and a user thereof, comprising the steps of: hosting a dialog over a communication channel between an automated dialog engine of said contact center and said user thereof, said dialog comprising messages sent between said automated dialog engine and said user in both directions; said automated dialog engine receiving input messages from said user, and determining response messages in response to said inputs; detecting from said messages of said dialog a trigger event matching a rule; in response to detection of said trigger event: providing said agent station with a summary of said dialog; and providing control of said automated dialog engine to said agent station.

Abstract: A service, in response to receiving a question in a natural language format, identifies one or more selected passages from a corpus that are relevant to a focus of the question from among multiple passages in the corpus. The service aligns one or more answer grammatical properties of one or more answers, selected from the one or more selected passages, to one or more question grammatical properties of the focus of the question. The service returns the one or more answers in response to the question.

Abstract: Systems and methods for e-commerce systems using natural language understanding are described. A computing device is configured receive a user utterance and identify at least one semantic element within the user utterance. An intent associated with the at least one semantic element is identified and an intent flow associated with the identified intent is executed. The intent flow includes a set of tasks executed in a predetermined order. A system utterance is generated by instantiating a response template selected from a plurality of response templates associated with the executed intent.

Abstract: An apparatus displays, on a terminal that enables a touch operation, an edit screen on which a text including word blocks is edited, where the word blocks are generated by performing morphological analysis on a character string obtained by speech recognition. Upon reception of a scroll instruction to scroll the text, the apparatus shifts each of the word blocks displayed on the edit screen in a description direction of the text, based on the scroll instruction.

Abstract: A command-processing server receives a natural language command from a user. The command-processing server has a set of domain command interpreters corresponding to different domains in which commands can be expressed, such as the domain of entertainment, or the domain of travel. Some or all of the domain command interpreters recognize user commands having a verbal prefix, an optional pre-filter, an object, and an optional post-filter; the pre- and post-filters may be compounded expressions involving multiple atomic filters. Different developers may independently specify the domain command interpreters and the sub-structure interpreters on which they are based.

Abstract: Disclosed are a method and an apparatus for speech recognition. In a method for processing speech recognition according to an embodiment of the disclosure, a relationship of a named entity is extracted and each named entity is clustered based on the extracted relationship of the named entity. An utterance intent is grasped by considering not only information about the named entity itself, but also relationship information of the clustered named entity tagged in the named entity, which may result in improvement of accuracy of speech recognition in the apparatus for speech recognition. A user equipment of the present disclosure can be associated with artificial intelligence modules, drones (unmanned aerial vehicles (UAVs)), robots, augmented reality (AR) devices, virtual reality (VR) devices, devices related to 5G service, etc.

Abstract: Techniques for speech recognition are described. For example, a speech recognition service is to receive a request to perform speech recognition on speech data from a chatbot using a particular speech recognition service; determine a group of hosts to route the speech data to, the group of hosts to host a plurality of speech recognition services including the particular speech recognition service; determine a path to the determined group of hosts using a set of one or more rules; determine a particular host of the group of hosts to perform speech recognition on the speech data, the particular host having the speech recognition service in memory to process the request and being preferred for performing the speech recognition on the speech data; route the speech data to the particular host; perform speech recognition on the speech data using the particular host; and provide a text result of the speech recognition.

Abstract: Implementations relate to dynamically, and in a context-sensitive manner, biasing voice to text conversion. In some implementations, the biasing of voice to text conversions is performed by a voice to text engine of a local agent, and the biasing is based at least in part on content provided to the local agent by a third-party (3P) agent that is in network communication with the local agent. In some of those implementations, the content includes contextual parameters that are provided by the 3P agent in combination with responsive content generated by the 3P agent during a dialog that: is between the 3P agent, and a user of a voice-enabled electronic device; and is facilitated by the local agent. The contextual parameters indicate potential feature(s) of further voice input that is to be provided in response to the responsive content generated by the 3P agent.

Abstract: The present invention is a masterbot architecture in a scalable multi-service virtual assistant platform that can construct a fluid and dynamic dialogue by assembling responses to end user utterances from two kinds of agents, information agents and action agents. A plurality of information agents obtain at least one information value from a parsed user input and/or contextual data. A plurality of action agents perform one or more actions in response to the parsed user input, the contextual data, and/or the information value. A masterbot arbitrates an activation of the plurality of information agents and the plurality of action agents. The masterbot comprises an action agent selector module to select an appropriate action agent; a prerequisite validator module to validate that one or more prerequisite conditions of the selected action agent have been met; and an action invocation module to perform one or more selected actions of the selected action agent.

Abstract: A text entity extraction method, apparatus, and storage medium are provided. The method includes determining candidate text entities in a target text. Portions of the candidate text entities are combined to generate candidate segmentation combinations corresponding to the target text, the candidate text entities in each candidate segmentation combination being different. A combination probability corresponding to each candidate segmentation combination is calculated, where the combination probability is a probability that grammar is correct when the target text uses the candidate segmentation combination. A target segmentation combination corresponding to the target text is determined according to the combination probabilities. A text entity is extracted from the target text according to the target segmentation combination.

Abstract: A system including at least one memory, and at least one processor operatively connected to the memory is provided. The memory may store instructions that, when executed, cause the processor to receive an input of selecting at least one domain from a user and store the input in the memory, recognize, at least partially based on data regarding a user utterance received after the input is stored, the utterance, determine, when the utterance does not comprise a domain name, whether or not the utterance corresponds to the selected domain, and generate a response by processing the utterance by using the selected domain when the utterance corresponds to the selected domain.

Abstract: A filtering model training method includes obtaining N original syllables, obtaining N recognized syllables, and obtaining N syllable distances based on the N original syllables and the N recognized syllables, where the N syllable distances are in a one-to-one correspondence with N syllable pairs, the N original syllables and the N recognized syllables form the N syllable pairs, each syllable pair includes an original syllable and a recognized syllable that correspond to each other, and each syllable distance is used to indicate a similarity between an original syllable and a recognized syllable that are included in a corresponding syllable pair.

Abstract: Systems, methods, and computer-readable media provide entity relation extraction across sentences in a document using distant supervision. A computing device can receive an input, such as a document comprising a plurality of sentences. The computing device can identify syntactic and/or semantic links between words in a sentence and/or between words in different sentences, and extract relationships between entities throughout the document. A knowledge base (e.g., a table, chart, database etc.) of entity relations based on the extracted relationships can be populated. An output of the populated knowledge base can be used by a classifier to identify additional relationships between entities in various documents. Machine learning can be applied to train the classifier to predict relations between entities. The classifier can be trained using known entity relations, syntactic links and/or semantic links.

Abstract: A conversation apparatus includes an audio speaker and a processor. The audio speaker makes an utterance to users. The processor acquires a feature of each of the users, selects, based on the acquired feature of each of the users, a target user to tune to or to not tune to from among the users, and executes utterance control that controls the audio speaker so as to make an utterance that corresponds to the selected target user.

Abstract: A system comprising: an input configured to receive input speech data originating from a user; an output configured to output speech or text information; and a processor configured to: provide first input data to a character sequence determination module to determine a character sequence from the first input data, wherein determining a character sequence comprises: obtaining a first list of one or more candidate character sequences from the first input data; selecting a first candidate character sequence from the first list; generating a first confirm request to confirm the selected first candidate character sequence, wherein the first confirm request is outputted by way of the output; if second input data indicating that the first candidate character sequence is not confirmed is received, selecting a second candidate character sequence and generating a second confirm request to confirm the selected second candidate if the second candidate character sequence is different from the first candidate character s

Abstract: A method comprising recognizing a user utterance including an ambiguity. The method further comprises using a previously-trained code-generation machine to produce, from the user utterance, a data-flow program including a search-history function. The search-history function is configured to select a highest-confidence disambiguating concept from one or more candidate concepts stored in a context-specific dialogue history.

Abstract: A method for configuring an automated dialogue system uses traces of interactions via a graphical user interface (GUI) for an application. Each trace includes interactions in the context of a plurality of presentations of the GUI. Elements of one or more presentations of the GUI are identified, and templates are associated with portions of the trace. Each template has one or more defined inputs and a defined output. For each template of the plurality of templates, the portions of the traces are processed to automatically configure the template by specifying a procedure for providing values of inputs to the template via the GUI and obtaining a value of an output. The automated dialogue system is configured with the configured templates, thereby avoiding manual configuration of the dialogue system.

Abstract: Embodiments may include collection of a first batch of acoustic feature frames of an audio signal, the number of acoustic feature frames of the first batch equal to a first batch size, input of the first batch to a speech recognition network, collection, in response to detection of a word hypothesis output by the speech recognition network, of a second batch of acoustic feature frames of the audio signal, the number of acoustic feature frames of the second batch equal to a second batch size greater than the first batch size, and input of the second batch to the speech recognition network.

Abstract: The present invention relates to a real-time voice recognition apparatus equipped with an application-specific integrated circuits (ASIC) chip and a smartphone, capable, by using one smartphone and one ASIC chip and without using a cloud computer, of assuring personal privacy, and, due to a short delay time, enabling real-time conversion of voice input signals into text for output. When one DRAM chip is optionally added to the real-time voice recognition apparatus, the number of neural network layers is increased thereby significantly improving accuracy of conversion of voice input signals into text.

Abstract: Method and apparatus improves the quality of responses from an automatic dialogue system by dynamically adjusting response thresholds. More particularly, the automatic dialogue system may dynamically determine response threshold values in response to user feedback. The response threshold values may be used to evaluate a confidence value. The confidence value may be assigned to or otherwise associated with an input class, or user intent. The system may automatically adjust the response threshold values to provide a better user experience as the amount of user-interaction with the system increases.

Abstract: A method for enhancing dialog systems is disclosed herein. The method may include maintaining an online marketplace that may have a plurality of dialog system extension elements. The plurality of dialog system extension elements may include at least one of a dialog system plugin, a dialog system add-on, a dialog system update, and a dialog system upgrade. The method may further include receiving a selection of one of the plurality of dialog system extension elements from an end user. The end user may be associated with a dialog system. The method may continue with associating the one of the plurality of dialog system extension elements with the dialog system of the end user.

Abstract: Systems, methods and software are disclosed for processing requests from users of an infotainment system. The method includes receiving a request from a user of the infotainment system. The method includes determining a domain for the received request based on information contained in the received request. The domain specifies one or more categories for the request. The method includes routing the received request to a virtual assistant assigned to handle requests for the determined domain. The virtual assistant is one of a plurality of virtual assistants respectively assigned to handle requests for a plurality of respectively assigned domains. The method includes transmitting a response to the request to the user.

Abstract: A method, apparatus, and computer program product are disclosed for updating a structure database. The method includes accessing a corpus of machine readable text generated based on a plurality of promotions, wherein each of the plurality of promotions comprises at least one promotion option associated with at least one service, and extracting features from the promotion options, the features being mapped to services associated with respective promotion options from which the features are extracted. The method further includes identifying one or more components associated with the extracted features, tagging, using a processor, each promotion option with every component associated with at least one feature of the promotion option, and updating a structure database using the tagged promotion options. A corresponding apparatus and computer program product are also provided.

Abstract: Conversational virtual assistance for delivering relevant query solutions is provided. A virtual assistant system comprises various components associated with developing a knowledge database that can be searched for finding documents that fulfill the user's intent. The virtual assistant system further comprises components for receiving a query from a user, extracting entities for understanding the user's intent, and for searching a knowledge database for documents responsive to the query. When additional information is needed for determining more relevant results, a conversation strategy is determined, and a question is formulated for generating a conversation with the user for clarifying the user's intent, confirming a solution, or obtaining additional information. The user is enabled to provide a follow-up response that is related to a previously identified entity. The entity is edited in the query, and responses are refined responsive to the edited query.

Abstract: A system for handling errors during automatic speech recognition by processing a potentially defective utterance to determine an alternative, potentially successful utterance. The system processes the N-best ASR hypotheses corresponding to the defective utterance using a trained model to generate a word-level feature vector. The word-level feature vector is processed using a sequence-to-sequence architecture to determine the alternate utterance.

Abstract: Systems, methods, and computer-readable media for providing for display an estimated breadth indicator and/or search terms proximity for a result set of documents are disclosed. A method includes receiving a natural language search query including a plurality of search concepts, determining the plurality of search concepts from the natural language query, searching a database using the natural language search query to identify the result set of documents, where the result set of documents are identified based on the plurality of search concepts, calculating a breadth of the result set of documents, where the breadth is calculated from an estimated relevance score that is indicative of a degree to which the result set of documents are relevant to the search query, and providing for display, the breadth as a feedback meter element. The feedback meter element provides a visual indication of the breadth of the natural language search query.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for isolating at least one device, from multiple devices in an environment, for being responsive to assistant invocations (e.g., spoken assistant invocations). A process for isolating a device can be initialized in response to a single instance of a spoken utterance, of a user, that is detected by multiple devices. One or more of the multiple devices can be caused to query the user regarding identifying a device to be isolated for receiving subsequent commands. The user can identify the device to be isolated by, for example, describing a unique identifier for the device. Unique identifiers can be generated by each device of the multiple devices and/or by a remote server device. The unique identifiers can be presented graphically and/or audibly to the user, and user interface input. Any device that is not identified can become temporarily unresponsive to certain commands, such as spoken invocation commands.

Abstract: A speech interface device is configured to perform natural language understanding (NLU) processing in a manner that optimizes the use of resources on the speech interface device. In an example process, a domain classifier(s) is used to generate domain classifier scores associated with multiple candidate domains, and the candidate domains can then be evaluated, one candidate domain at a time, in accordance with the domain classifier scores (e.g., starting with a highest scoring candidate domain). For each candidate domain undergoing the evaluation, input data is by that domain's NLU model(s), and, as soon as a domain-specific NLU model(s) produces a NLU result with a confidence score that satisfies a threshold confidence score, the evaluation can be stopped for any remaining candidate domains.

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: An online version of a sentence representation generation module updated by training a first sentence representation generation module using first labeled data of a first corpus. After training the first sentence representation generation module using the first labeled data, a second corpus of second labeled data is obtained. The second corpus is distinct from the first corpus. A subset of the first labeled data is identified based on similarities between the first corpus and the second corpus. A second sentence representation generation module is trained using the second labeled data of the second corpus and the subset of the first labeled data.

Abstract: Techniques are provided to allow a user to interact with a computer to automatically analyze a transcript and provide interactive feedback pertaining to interactions between the user and other parties. This may be accomplished by dividing the transcript into text sequences, such as sentences, and matching each text sequence against a set of rules that define patterns that relate text sequences to particular characteristic categories. These matches can be further scored and ranked to allow particular text sequences to be interactively displayed to the user in response to selection of a particular categorization.

Abstract: Embodiments for building domain models from dialog interactions by a processor. A domain knowledge may be elicited from one or more dialog interactions with one or more users according to one or more dialog strategies. One or more domain models may be built and/or enhanced according to the domain knowledge.

Abstract: The present disclosure provides a method and an apparatus for semantic recognition, and a system for human-machine dialog. In the method, a Pinyin sequence of a sentence to be recognized is obtained. The Pinyin sequence includes a plurality of Pinyin segments. Then, word vectors of the plurality of Pinyin segments are obtained. Next, the word vectors of the plurality of Pinyin segments are combined into a sentence vector of the sentence to be recognized. Based on the sentence vector of the sentence to be recognized, an output vector of the sentence to be recognized is obtained by using a neural network. Based on the output vector of the sentence to be recognized, a reference sentence semantically similar to the sentence to be recognized is determined. Then, a semantic meaning of the sentence to be recognized is recognized as a semantic meaning of the reference sentence.

Abstract: A method, a system, and a computer program product are provided. Speech signals from a medical conversation between a medical provider and a patient are converted to text based on a first domain model associated with a medical scenario. The first domain model is selected from multiple domain models associated with a workflow of the medical provider. One or more triggers are detected, each of which indicates a respective change in the medical scenario. A corresponding second domain model is applied to the medical conversation to more accurately convert the speech signals to text in response to each of the detected one or more triggers. The corresponding second domain model is associated with a respective change in the medical scenario of the workflow of the medical provider. A clinical note is provided based on the text produced by converting the speech signals.

Abstract: Validating belief states of an artificial intelligence system includes providing a question answering service; detecting a negative sentiment of a user to an answer transmitted to a device associated with the user; and responsive to detecting the negative sentiment, detecting that the answer relates to a topic on which there is controversy. Next, a new belief state is added to the question answering service based on the controversy, and an updated answer is transmitted to the device, wherein the updated answer is based on the new belief state.