Abstract: A system for processing user utterances and/or text based queries that tracks entities and other context data of a current dialog between the system and the user and can fill slots for new intents of the dialog by performing statistical processing on previously mentioned entities with respect to current slots to be filled. The system may compare a previously mentioned entity to a current slot to be filled using vector representations, such as word embeddings, of the current utterance, dialog history, current intent, name of an entity under consideration, category of the current slot to be filled, distance between the current dialog turn and the dialog turn that mentioned the entity, and other considerations. The individual vectors may be weighted according to an attention operation and processed by a trained decoder to output a score indicating whether the entity in consideration is relevant to the particular slot.

Abstract: Provided is a user command processing method and system for adjusting an output volume of a sound to be output on the basis of an input volume of a received voice input. A user command processing method may comprise the steps of: receiving a voice input from a user; measuring an input volume of the received voice input; and adjusting an output volume of a sound to be output in response to the received voice input, according to the measured input volume.

Abstract: A computer method and system for providing information results in response to a natural language information request. The system and method include receiving a natural language information request from a user and compiling a computer executable query from the natural language information request from a user wherein the query is formatted to extract data from one or more computer databases. The query is then presented to the user prior to execution of the query so as to enable the user to change the query prior to its execution. The query is then executed to extract data from one or more computer databases whereby extracted data is presented to the user in a certain presentation format.

Abstract: A framework for testing media in a media enabled web application is described. A media enabled web application such as a voice over Internet protocol (“VOIP”) is initiated between an originating web browser window and terminating or receiving web browser window. A WebRTC module is initiated on the terminating or receiving web browser window to record testing media transferred from the originating web browser window. The captured media is compared to the testing media to determine the quality of service of the media enabled web application.

Abstract: An information processing apparatus includes a selector and an extending unit. The selector selects a word in question training data corresponding to a topic. The extending unit extends the question training data by replacing the word selected by the selector in the question training data by a word in answer data corresponding to the topic.

Abstract: A printing apparatus includes: a conveyor; a printing device; a first storage storing templates, in each of which objects are arranged on a printing medium; a voice input device; an output device; and a controller. The controller is configured to: accept designation of a particular template by voice; make an inquiry about a content of at least one particular character to be assigned to each of the objects in the particular template; accept the content of the at least one particular character to be assigned to each of the objects in response to the inquiry, by voice; and create print data for each of the objects based on character data created by character recognition of the voice indicating the accepted content and control the conveyor and the printing device to perform printing on the printing medium based on the created print data.

Abstract: A computer evaluates free-form text messages among members of a team, using natural language processing techniques to process the text messages and to assess psychological state of the team members as reflected it the text messages. The computer assembles the psychological state as reflected in the messages to evaluate team collective psychological state. The computer reports a trend of team collective psychological state in natural language text form.

Abstract: The embodiments of the present disclosure provide a device for recognizing speeches and a method for speech recognition. The device for recognizing speeches may comprise a processor, configured to execute instructions stored in the memory, to: perform speech recognition on the collected audio data to obtain a semantic content of the audio data; match the obtained semantic content with a semantic data stored in the database; determine whether the audio data contains ambient noise audio information and audio information of a user, in response to determining that the obtained semantic content does not match with the semantic data; and change conditions for collecting the audio data and control to collect the audio data with the changed conditions, in response to determining that the audio data contains the ambient noise audio information and the audio information of the user.

Abstract: Techniques for enabling a device to send to a speech processing server further input audio data following a completed utterance dialog to prevent the need for subsequent keywords to be spoken to invoke subsequent commands are described. A system receives input audio data corresponding to an utterance from a device upon the device detecting speech corresponding to a keyword. The system performs speech processing on the input audio data to determine a command. The system determines output data responsive to the command and sends same to the device, thus completing operations regarding the utterance. The system may also send an instruction to the device to: send to the system further input audio data corresponding to further input audio without the device first detecting a wake command.

Abstract: Systems and methods for generating personalized navigation menus are disclosed. For example, the system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving account data associated with a plurality of accounts and receiving navigation menu data associated with the accounts. The operations may include training a model based on the account data and the navigation menu data. The operations may include receiving a request associated with a user and receiving user account data associated with the user. The operations may include generating, using the model, a navigation menu based on the request and the user account data. The operations may include providing the navigation menu.

Abstract: Features are disclosed for detecting words in audio using contextual information in addition to automatic speech recognition results. A detection model can be generated and used to determine whether a particular word, such as a keyword or “wake word,” has been uttered. The detection model can operate on features derived from an audio signal, contextual information associated with generation of the audio signal, and the like. In some embodiments, the detection model can be customized for particular users or groups of users based usage patterns associated with the users.

Abstract: Provided is a method, system, and non-transitory computer-readable recording medium for delivering audio feedback of a viewer to a caster during a live broadcast. A method implemented on a computer system includes providing a live broadcast by receiving broadcast content transmitted from an electronic device of a caster, and by streaming the received broadcast content to each of electronic devices of a plurality of users through a communication session established between an account of the caster and accounts of the plurality of users; receiving an audio feedback about the live broadcast from an electronic devices of a user during the live broadcast; and delivering the audio feedback to the electronic device of the caster.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, relating to synthetic call status updates. In some implementations, a method includes determining, by a task manager module, that a triggering event has occurred to provide a current status of a user call request. The method may then determine, by the task manager module, the current status of the user call request. A representation of the current status of the user call request is generated. Then, the generated representation of the current status of the user call request is provided to the user.

Abstract: Migration of a durable client in a publish/subscribe system from a first server of a cluster to a second server of the cluster. The method comprises the second server receiving subscription information of the durable client; the second server establishing a message queue for the durable client; the second server sending a switch command to all active servers of the cluster; in response to the second server obtaining, from an active server, an acknowledgement of the switch command, the second server inserting a marker to the message queue indicating switching point of the active server; and in response to the second server obtaining, from the first server, a message indicating the first server flushed all messages prior to respective switching points for all active servers, connecting the durable client to the second server and transmitting messages thereto by the second server.

Abstract: Examples of multi-user configuration are disclosed. An example method includes, at an electronic device: receiving a request; and in response to the request: if the voice input does not match a voice profile associated with an account associated with the electronic device: causing output of first information based on the request using a first account associated with the electronic device; if a setting of the electronic device has a first state, causing update of account data of the first account based on the request; and if the setting has a second state, forgoing causing update of the account data; and if the voice input matches a voice profile associated with an account associated with the electronic device: causing output of the first information using the account associated with the matching voice profile; and causing update of account data of the account based on the request.

Abstract: The present invention provides a method for generating a semantic expression for a standard question in a knowledge base.

Abstract: A system for integrating a telephone system and a computing system includes an interactive voice response (IVR) platform configured to: obtain a command based on an audio input from a user, determine a web application that corresponds to the command, determine a goal in the web application associated with the command, and obtain information indicating a shortest user interface path to the goal. The system includes a cobrowse client configured to receive a document object model (DOM) of a current state of the web application from a cobrowse session. The IVR platform is configured to, based on the DOM, determine a next user interface action along the shortest user interface path and generate a voice prompt for the user based on the next user interface action. The cobrowse client is configured to receive an updated DOM in response to execution by the user of the next user interface action.

Abstract: A device may receive a set of audio data files corresponding to a set of calls, wherein the set of audio data files includes digital representations of one or more segments of respective calls of the set of calls, and wherein the set of calls includes audio data relating to a particular industry. The device may receive a set of transcripts corresponding to the set of audio data files. The device may determine a plurality of text-audio pairs within the set of calls, wherein a text-audio pair, of the plurality of text-audio pairs, comprises: a digital representation of a segment a call of the set of calls, and a corresponding excerpt of text from the set of transcripts. The device may train, using a machine learning process, an industry-specific text-to-speech model, tailored for the particular industry, based on the plurality of text-audio pairs.

Abstract: A method of dynamically rendering cognitive contacts that includes: identifying transitory contacts of interest to a user of a mobile device in various contexts; identifying various contexts applicable to the user; sorting the transitory contacts of interest into transitory contact types; mapping the various contexts to the transitory contact types into a mapping table; deriving a present context pertaining to a user of the mobile device; querying the mapping table for transitory contact types applicable to the present context; dynamically rendering the applicable transitory contact types to the user in a transitory contacts screen on the mobile device; and responsive to the user selecting one of the applicable transitory contact types, displaying the transitory contacts of interest in the transitory contacts screen on the mobile device corresponding to the transitory contact type.

Abstract: A system includes network interface, processor operatively connected to the network interface, and memory operatively connected to the processor. The memory stores a plurality of language models of a first language. The plurality of language models be different from one another. Each of the plurality of language models is provided for speakers whose native language is different from the first language. The memory further stores instructions that cause the processor to receive a user's speech data associated with a plurality of sample texts from an external electronic device, to perform automatic speech recognition (ASR) on the speech data using the plurality of language models, to select one language model from the plurality of language models based on results from the performed ASR, and to use the selected one language model as a default language model for speech of the user.

Abstract: Provided is a device including a display, an audio inputter, and a controller. The display displays at least one screen page of an application that is being executed. The audio inputter receives a voice command of a user. The controller performs an operation corresponding to the voice command by using screen page transition information for transition between application screen pages corresponding to the voice command, which is obtained from information about user interface (UI) elements included in the application screen pages of the application. Each of the UI elements performs a predetermined function when selected by the user.

Abstract: Automatically identifying speakers in real-time through media processing with dialog understanding. A plurality of audio streams may be received, an audio stream representing a speech of a participant speaking during an online meeting. A voice characteristic of a voice corresponding to the speech of the participant in the audio stream may be determined. The plurality of audio streams may be converted into text and a natural language processing may be performed to determine content context of the dialog. The natural language processing infers a name to associate with the voice in the audio stream based on the determined content context. A data structure linking the name with the voice may be created and stored in a knowledge base. A user interface associated with the online meeting application is triggered to present the name or identity of the speaker.

Abstract: The present invention discloses a system, apparatus, and method that obtains audio and metadata information from voice calls, generates textual transcripts from those calls, and makes the resulting data searchable via a user interface. The system converts audio data from one or more sources (such as a telecommunications provider) into searchable usable text transcripts. One use of which is law enforcement and intelligence work. Another use relates to call centers to improve quality and track customer service history. Searches can be performed for callers, callees, keywords, and/or other information in calls across the system. The system can also generate automatic alerts based on callers, callees, keywords, phone numbers, and/or other information.

Abstract: Systems, methods, and software can be used to populate contact information. In some aspect, a search term for a contact is received at an electronic device. A query for contact information is sent from the electronic device to a server. The query includes the search term. A query response is received from the server. Contact information for the contact is identified based on the query response. A contact record for the contact is populated using the identified contact information.

Abstract: The present disclosure provides a method for adding contact information, and user equipment. The method includes: receiving gesture information input by a user on a communication interface of an instant messaging application, recognizing contact information in communication information according to the gesture information, and adding the contact information to an address book of user equipment.

Abstract: Methods and systems for performing contact resolution are described herein. When initiating a communications session using a voice activated electronic device, a contact name may be resolved to determine an appropriate contact with which the communications session may be directed to. Contacts from an individual's contact list may be queried to determine a listing of probable contacts associated with the contact name, and contact identifiers associated with the contact may be determined. Using one or more rules for disambiguating between similar contact names, a single contact may be identified, and a communications session with that contact may be initiated.

Abstract: Systems and methods for establishing a communications system between multiple electronic devices are described herein. In some embodiments, first audio data representing a first utterance may be received from an initiating device. A first user account associated with the initiating device may be determined. After determining that the utterance comprises an intent to communicate with a target, a list of entity names associated with the user account may be generated. Each entity name may represent a user contact associated with the first user account, a user device corresponding to the first user account, and/or a set of entity names representing user contacts and devices. Based on a relative comparison of each entity name to the target's name, an entity name may be selected from the plurality of entity names. A communications session may then be established between the initiating device and a device represented by the selected entity name.

Abstract: The subject matter of this specification can be embodied in, among other things, a method that includes receiving an audio signal and initiating speech recognition tasks by a plurality of speech recognition systems (SRS's). Each SRS is configured to generate a recognition result specifying possible speech included in the audio signal and a confidence value indicating a confidence in a correctness of the speech result. The method also includes completing a portion of the speech recognition tasks including generating one or more recognition results and one or more confidence values for the one or more recognition results, determining whether the one or more confidence values meets a confidence threshold, aborting a remaining portion of the speech recognition tasks for SRS's that have not generated a recognition result, and outputting a final recognition result based on at least one of the generated one or more speech results.

Abstract: A method for facilitating computer-generated communication with a user, the method including: receiving one or more inputs from the user during a first session; creating a profile of the user based on the received one or more inputs during the first session; determining if the first session is interrupted; and establishing a second session with the user, in case of the first session being interrupted, based on the profile of the user.

Abstract: The present disclosure relates to a system, a method, and a product for an artificial intelligence based virtual agent trainer. The system includes a processor in communication with a memory storing instructions. When the processor executes the instructions, the instructions are configured to cause the processor to obtain input data and generate a preliminary set of utterances based on the input data, process the preliminary set of utterances to generate a set of utterance training data, generate a set of conversations based on the set of utterance training data, simulate the set of conversations on a virtual agent to obtain a conversation result, verify an intent and a response based on the conversation result, verify a use case flow and flow hops based on the conversation result, and generate recommendation information and maturity report based on verification results.

Abstract: A method for identifying communicators as wanted or unwanted based on messages from such communicators comprising receiving, by the data processing system, an inbound message from a communicator, comparing, by the data processing system, the inbound message to fingerprints stored in a database accessible to the data processing system, determining, by the data processing system, at least one match to the fingerprints, determining, by the data processing system, an identity of the communicator by determining whether and how likely the communicator is wanted or unwanted based on the at least one match to the fingerprints, and configuring, by the data processing system, handling of calls from the communicator based on the identity.

Abstract: Systems and methods for managing models for call data are disclosed. For example, the system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving, from a user device, an input indicating a segment of a first recorded call and an attribute associated with the segment. The operations may include determining a parameter of a model, wherein the model is associated with the attribute. The operations may include changing the parameter based on the input. The operations may include generating an updated model based on the changed parameter, wherein the updated model may be configured to analyze recorded calls having one or more segments with the same attribute.

Abstract: A computer-implemented method according to one embodiment includes identifying a plurality of communications each having an associated objective, automatically determining a plurality of dialog acts within the plurality of communications, utilizing a classifier, determining a plurality of features within each of the plurality of communications, training the model, utilizing the plurality of communications and associated objectives, the plurality of dialog acts, and the plurality of features, receiving textual data associated with a real-time conversation between a first participant and a second participant, receiving an objective of the first participant for the real-time conversation between the first participant and the second participant, determining a dialog act to be entered by the first participant at a current point in the real-time conversation that meets the objective, utilizing the model, and determining the dialog act to be entered, based on the scoring, and returning the dialog act to the first pa

Abstract: Disclosed embodiments are directed an application program configured to run on a user's mobile device can allow voice-activated call pick-up to the user, without the user having to use his or her hands for picking up the call. For example, the application program can initially be trained to a user's voice command. When an incoming call is received at the mobile device, the user can pick up the call by issuing a voice command. In some embodiments, the application program can determine whether to allow voice-activated pick-up of calls based on data collected from multiple sensors associated with the vehicle, the mobile device, or a remote source.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable storage media for utilizing a virtual assistant to assist a user with a communication session between the user and a third party service. A user can use a communication application to enter a message directed to the virtual assistant and request assistance to communicate with a 3rd party service. In response, the virtual assistant can access a set of communication instructions associated with the 3rd party service. The set of communication instructions can include a set of commands for communicating with the 3rd party service, services provided by the 3rd party service and data needed by the 3rd party service to facilitate communication. The virtual assistant can use the communication instructions to gather data needed by the 3rd party service, communicate with the 3rd party service and present the user with data received from the 3rd party service.

Abstract: Disclosed herein are systems, methods, and computer-readable media to connecting to addresses received in spoken communications. The method for connecting to addresses received in spoken communications comprises receiving at least one spoken communication containing a spoken address, extracting each address automatically from the at least one spoken communication, displaying to a user at least one extracted address, and receiving from the user a selection of at least one extracted address to initiate communication.

Abstract: Systems and methods for providing services to customers in response to customer requests received through one or more channels are disclosed. The present invention provides for a central fulfillment hub in which all requests from banking customers may be processed by applying a library of policies to systematically resolve the customer requests or engage resources necessary to resolve such requests. The disclosed fulfillment system, thus, may open a request, prefetch the necessary information, take steps to resolve the request, and close the request accordingly in a dynamic and efficient manner on a request-by-request basis. In addition, the system may provide security mechanisms to secure access to resources, including applications and data, based on applications, assigned user roles or user, activities, and access control configurations. Further, the system may dynamically allocate employees across teams based on system demand and provide secured access to the resources accordingly.

Abstract: Techniques related to a virtual agent conversation service are disclosed. The techniques include a method for improving performance of a virtual agent conversation system, comprising receiving one or more conversation trees, receiving a message from a user including a natural language description of an intended task, providing the message to a conversation provider, receiving an indication of an intent of the message and textual information related to the indication of the intent, determining an action to take based on the indication of the intent, perform the action to obtain an action result, determining a set of responses based on the action result, and providing a response of the set of responses to the virtual agent based on the action result for output to the user.

Abstract: A computer-implemented method according to one embodiment includes receiving, utilizing a processor, textual data associated with a conversation between a first participant and a second participant, receiving, utilizing the processor, an objective of the first participant for the conversation between the first participant and the second participant, receiving, utilizing the processor, a proposed dialog act to be entered in the conversation from the first participant, determining, utilizing the processor, an impact of the proposed dialog act on the objective of the first participant, utilizing a model, and performing, utilizing the processor, one or more actions based on the impact of the proposed dialog act.

Abstract: System and method of generating an executable action item in response to natural language dialogue are disclosed herein. A computing system receives a dialogue message from a remote client device of a customer associated with an organization, the dialogue message comprising an utterance indicative of an implied goal. A natural language processor of the computing system parses the dialogue message to identify one or more components contained in the utterance. The planning module of the computing system identifies the implied goal. The computing system generates a plan within a defined solution space. The computing system generates a verification message to the user to confirm the plan. The computing system transmits the verification message to the remote client device of the customer. The computing system updates an event queue with instructions to execute the action item according to the generated plan upon receiving a confirmation message from the remote client device.

Abstract: There is provided an information processing device that appropriately presents a topic in consideration of a behavior of a user presenting the topic. The information processing device includes: a topic generation unit configured to generate topics with a conversation partner on the basis of a comparison result between a certain behavior of a user and comparison information regarding the behavior; and a topic suggestion unit configured to decide a topic candidate to be suggested to the user from the generated topics.

Abstract: Maintaining adequate audio quality is very important for creating fast and accurate transcriptions, especially in a hybrid transcription setting, in which human transcribers review transcriptions generated by automatic speech recognition (ASR) systems. Some embodiments described herein involve detecting low-quality audio intended for transcription. In one embodiment, a server receives an audio recording that includes speech. The server generates feature values based on a segment of the audio recording and utilizes a model to calculate, based on the feature values, a certain value indicative of expected hybrid transcription quality of the segment. The model is generated based on training data that includes feature values generated based on previously recorded segments of audio, and values of transcription-quality metrics generated based on transcriptions of the previously recorded segments, which were generated at least in part by human transcribers.

Abstract: A system and method for facilitating access to requested information in building. The system includes a database, a server having a central processing unit, a wireless network, video displays disposed in rooms, and a sensing unit in communication with the server over the wireless network. The sensing unit has a microphone and disposed in each of the rooms. The sensing units are configured to detect the presence of a user and actuate an associated video display. The microphone is configured to receive requested information from the user. The central processing unit processes the requested information so as to retrieve the requested information from the database and display the requested information on the associated video display. In one embodiment, the sensing unit is a beacon and a portable electronic device. In another embodiment, the sensing unit is a wireless voice command device.

Abstract: A method and device for automatically changing or updating a configuration or setting of a communication system is disclosed. In one aspect, the method includes providing information to the communication system, the information comprising natural human language, storing the information in a digital storage device, detecting a triggering event in the information, and changing the configuration or setting of the communication system automatically using a processor. The information is an input to the communication system, an input from at least one alternate communication system, or a combination of an input to the communication system and an input from the at least one alternate communication system.

Abstract: Responsive to receipt of a first instant message during a first mode operation of an instant messaging program while a computer is driving an exposed output device, the first instant message is blocked. Responsive to receipt of a second instant message during a second mode operation while the computer is driving the exposed output device, an identification of a sender of the second instant message is displayed and a query is issued to determine whether instant message content should be displayed on the exposed output device. Responsive to receipt of a third instant message during a third mode operation while the computer is driving the exposed output device, it is determined that a sender of the third instant message is on a priority list, an identification of the sender is displayed, and a query is issued to determine whether instant message content should be displayed on the exposed output device.

Abstract: A conversation meter comprises a memory storage comprising instructions and one or more processors in communication with the memory storage. The one or more processors execute the instructions to perform: accessing audio data representing a conversation among a plurality of people; analyzing the audio data to associate one or more portions of the audio data with each person of the plurality of people; analyzing the portions of the audio data to determine one or more conversation metrics for each person of the plurality of people; and causing presentation of at least one of the determined conversation metrics.

Abstract: Certain aspects of the present disclosure relate to a computer implemented method for executing application code to connect with a social networking website, the method including analyzing information from at least a user that is in conversation. At least a word is filtered from the analyzed information. A tag is generated from the filtered word. The tag is connected with at least a media file, and a link is added to the media file and the tag to the display of the conversation in the social networking website.

Abstract: Among other things, a developer of an interaction application for an enterprise can create items of content to be provided to an assistant platform for use in responses to requests of end-users. The developer can deploy the interaction application using defined items of content and an available general interaction model including intents and sample utterances having slots. The developer can deploy the interaction application without requiring the developer to formulate any of the intents, sample utterances, or slots of the general interaction model.

Abstract: One embodiment provides a method, including: receiving, at an information handling device, a query from a user; receiving an indication of a time associated with provision of a result associated with the query; and adjusting a characteristic associated with an audible output based upon the indicated time. Other aspects are described and claimed.

Abstract: Certain embodiments of the present disclosure are related to an apparatus and a method for executing a function corresponding to pattern data generated using a plurality of microphones. An electronic device may include a plurality of microphones and a processor. The processor may be configured to detect a user input at the plurality of the microphones, to generate pattern data based on the user input, and to execute a function corresponding to the pattern data.