Abstract: Systems and methods for creating chatbot-enabled web forms and workflows, the method comprising, mapping web forms and workflows to intents, wherein the web forms have required fields to be completed and the workflows have required tasks to be performed; mapping the required fields and the required tasks to entities for the intents that map to the web forms and the workflows; mapping utterances to complete the required fields and perform the required tasks to the intents and the entities that map to the web forms and the workflows; and creating chatbots configured to assist users to complete the required fields and perform the required tasks using the utterances, the intents and the entities that map to the web forms and the workflows.

Abstract: A system includes one or more memory devices storing instructions, and one or more processors configured to execute the instructions to perform steps of providing automated natural dialogue with a customer. The system may generate one or more events and commands temporarily stored in queues to be processed by one or more of a dialogue management device, an API server, and an NLP device. The dialogue management device may create adaptive responses to customer communications using a customer context, a rules-based platform, and a trained machine learning model.

Abstract: A dialog apparatus and the like are provided which achieve a natural dialog in which topics minutely connect, starting from a user utterance, by making, after a robot's response to the user utterance, robots exchange additional questions and answers, which reflect the contents of the response, between them.

Abstract: A system and method are presented relating to emotion-based action recommendations. The present invention may include a recommender engine that analyzes several pieces of information and using artificial intelligence derived models, provides a course of action for a contact center agent and the probability and estimations behind the recommendation as a justification. System inputs include cost of the item or service being troubleshooted, estimated costs for different resolutions, cost of each escalation level of the interaction, history of previous interactions, agent costs, history of the current interaction, acoustic events and sentiment or primary detected emotions of the customer's transcript. The recommended course of action, rationale, and authorization can be provided as output. The system may record whether the agent followed the recommendation to improve further recommendations.

Abstract: A user device may include a first and second wakeword-detection components. If the first wakeword-detection component determines that first audio data includes a representation of a first wakeword, the user device communicates with a first speech-processing system corresponding to the first wakeword. While the communication is ongoing, if a second wakeword-detection component determines that second audio data includes a representation of a second wakeword, the second audio data is not send to a corresponding second speech-processing system.

Abstract: Attention weights in a hierarchical attention network indicate the relative importance of portions of a conversation between an individual at one terminal and a computer or a human agent at another terminal. Weighting the portions of the conversation after converting the conversation to a standard text format allows for a computer to graphically highlight, by color, font, or other indicator visible on a graphical user interface, which portions of a conversation led to an escalation of the interaction from an intelligent virtual assistant to a human customer service agent.

Abstract: Techniques for displaying comments relative to video frames are described herein. The disclosed techniques include sending message data comprising a comment on a video item by a first client computing device when the first client computing device is in a first state among a plurality of states; receiving bullet screen data comprising comments on the video item sent by the first client computing device and other client computing devices; determining echo bullet screens comprising a plurality of comments on the video item sent by the other client computing devices during a predetermined period; and displaying a bullet screen comprising the comment sent by the first client computing device and the echo bullet screens.

Abstract: Methods to build an open smart speaker to orchestrate voice services from multiple providers, and open smart speakers that orchestrate voice services from multiple providers.

Abstract: A computer device (100) for processing audio signals is described. The computer device (100) includes at least a processor and a memory. The computer device (100) is configured to receive a bitstream comprising a combined audio signal, the combined audio signal comprising a first audio signal including speech and a second audio signal. The computer device (100) is configured to compress the combined audio signal to provide a compressed audio signal. The computer device (100) is configured to control a dynamic range of the compressed audio signal to provide an output audio signal. In this way, a quality of the speech included in the output audio signal is improved.

Abstract: A system incorporating configurable keywords. The system can detect a keyword in audio data and execute one function for the keyword if a first application is operating, but a second function for the keyword if a second function is operating. Each keyword may be associated with multiple different functions. If a keyword is recognized during keyword detection, a function associated with that keyword is determined based on another application running on the system. Thus detection of a same keyword may result in a different function based on system context.

Abstract: Systems and methods are disclosed herein for training a model to accurately determine whether two phrases are conversationally connected. A media guidance application may detect a first phrase and a second phrase, translate each phrase to a string of word types, append each string to the back of a prior string to create a combined string, determine a degree to which any of the individual strings matches any singleton template, and determine a degree to which the combined string matches any conversational template. Based on the degrees to which the individual and combination strings match the singleton and conversational templates, respectively, strengths of association are correspondingly updated.

Abstract: A method for electronically utilizing content in a communication between a customer and a customer representative is provided. An audible conversation between a customer and a service representative is captured. At least a portion of the audible conversation is converted into computer searchable data. The computer searchable data is analyzed during the audible conversation to identify relevant meta tags previously stored in a data repository or generated during the audible conversation. Each meta tag is associated with the customer. Each meta tag provides a contextual item determined from at least a portion of one of a current or previous conversation with the customer. A meta tag determined to be relevant to the current conversation between the service representative and the customer is displayed in real time to the service representative currently conversing with the customer.

Abstract: An electronic device for generating a personalized response from a virtual assistant includes a network communication circuitry; a memory; and at least one processor configured to, when receiving a user query including a wake-word, parse the user query to separate the wake-word from the user query; process the wake-word; extract wake-word related information from a wake-word database; parse the extracted wake-word related information along with a plurality of user preference information; classify information received from a wake-word parser; produce a wake-word context from the classified information; process the user query; and retrieve a query response from at least one knowledge base based on a plurality of action steps.

Abstract: A method, an electronic device, and non-transitory machine-readable medium are provided. The method includes receiving, on an electronic device, a request to perform an action. The method also includes deriving an aggregated predicted confidence level using one or more confidence levels. The one or more confidence levels are based on usage information and context of the electronic device. The method further includes determining an execution engine to process the request based on the aggregated predicted confidence level. The method additionally includes providing at least a portion of the request to the execution engine for processing.

Abstract: Various embodiments of the technology described herein alleviate the need to specifically request enrollment information from a user to enroll the user in a passive voice authentication program. The system can receive one or more spoken words from a user. The system can determine that a voice profile is usable for user authentication. The system can select at least one word from the one or more spoken words to enroll the user into a voice authentication program without requiring further interaction from the user. The voice authentication program enables access to secure data in response to receiving the at least one word spoken by the user. After enrollment of the user into the voice authentication program, at least one word spoken by the user is received, and the user is authenticated based on the at least one word.

Abstract: Methods and systems are presented for providing automated online chat assistance in multiple languages. A query in a first language is received via a chat robot from a user device. The query is machine-translated into a second language and transmitted to an artificial intelligence system that includes a dialog tree configured in the second language. The artificial intelligence system determines a response in the second language to the query by locating a node corresponding to an intent based on the query in the dialog tree. The node includes a node ID and response text in the second language. The artificial intelligence system transmits the second-language response including the node ID to the chat robot. The second-language response is intercepted, and first-language response text corresponding to the second-language response text is determined based on the node ID. The second-language response text is then provided to the user device by the chat robot.

Abstract: Systems and methods of conducting a dialogue sequence between at least two user devices using one or more provider applications that facilitates a dialogue sequence between the at least two user devices are disclosed. A method includes sending to first and second user devices authorizations to enable the first and second user devices to conduct first and second portions of a dialogue sequence, respectively. The method includes receiving, from the first user device, second code that supplements first code associated with a provider application to produce first updated code, the first updated code adapting the provider application to be able to facilitate the dialogue sequence between the first and second user devices. The method includes determining that the second user device satisfies criteria associated with the dialogue sequence and sending, to the second user device, third code that facilitates the second portion of the dialogue sequence.

Abstract: Implementations herein relate to pre-caching data, corresponding to predicted interactions between a user and an automated assistant, using data characterizing previous interactions between the user and the automated assistant. An interaction can be predicted based on details of a current interaction between the user and an automated assistant. One or more predicted interactions can be initialized, and/or any corresponding data pre-cached, prior to the user commanding the automated assistant in furtherance of the predicted interaction. Interaction predictions can be generated using a user-parameterized machine learning model, which can be used when processing input(s) that characterize a recent user interaction with the automated assistant. The predicted interaction(s) can include action(s) to be performed by third-party application(s).

Abstract: Described herein are systems and methods that search videos and other media content to identify items, objects, faces, or other entities within the media content. Detectors identify objects within media content by, for instance, detecting a predetermined set of visual features corresponding to the objects. Detectors configured to identify an object can be trained using a machine learned model (e.g., a convolutional neural network) as applied to a set of example media content items that include the object. The systems provide user interfaces that allow users to review search results, pinpoint relevant portions of media content items where the identified objects are determined to be present, review detector performance and retrain detectors, providing search result feedback, and/or reviewing video monitoring results and analytics.

Abstract: A method, a device, and a computer-readable storage medium having instructions for processing a speech input. A speech input from a user is received and preprocessed for at least one of two or more available speech-processing services. The preprocessed speech inputs are transferred to one or more of the available speech-processing services.

Abstract: Systems and methods for data processing in an optimized analytics environment are disclosed. The system may enable users to create data processing requests, interact with various data sources and datasets, and generate data processing outputs. The system may receive a data processing request from an audio-enabled input source or a UI-based input source. The system may determine whether the data processing request at least partially matches a stored data processing request. The system may receive a data processing request selection comprising the data processing request or the stored data processing request. The system may execute the data processing request selection on a data source.

Abstract: In an embodiment, cognitive adjustment of responses from a virtual assistant includes detecting verbal content in an audio signal, determining that the verbal content includes a voice command associated with a task by correlating the verbal content with voice command data stored in memory, determining a state of the user from the audio signal by cognitively comparing aspects of the verbal content with aspects of profile data associated with the user, and retrieving task data associated with the task for preparing a response to the voice command.

Abstract: Systems and methods include activation of a first voice assistant application to execute a first user dialog session, the first application associated with a first voice keyword and, while the first application is active and executing the first session, reception of second audio signals representing a second voice keyword associated with a second voice assistant application, determination, in response to reception of the second audio signals, that the first application is uninterruptable, wherein the second application remains inactive in response to reception of the second audio signals, reception of a signal from the first application indicating that the first application is interruptable, reception of third audio signals representing the second keyword and, in response to reception of the third audio signals, determination that the first application is interruptable and transmission of an activation signal to the second application to activate the second application and execute a second user dialog session

Abstract: A method for optimizing speech recognition includes receiving a first acoustic segment characterizing a hotword detected by a hotword detector in streaming audio captured by a user device, extracting one or more hotword attributes from the first acoustic segment, and adjusting, based on the one or more hotword attributes extracted from the first acoustic segment, one or more speech recognition parameters of an automated speech recognition (ASR) model. After adjusting the speech recognition parameters of the ASR model, the method also includes processing, using the ASR model, a second acoustic segment to generate a speech recognition result. The second acoustic segment characterizes a spoken query/command that follows the first acoustic segment in the streaming audio captured by the user device.

Abstract: A first data that identifies a first device is used to identify within a data store a one or more capabilities of the first device. When a voice input having one or more keywords that have been pre-associated within the data store to an operational problem associated with at least the first device is received, a system causes a state of at least the first device at a time at which the voice input is received to be identified, causes the one or more keywords, the one or more capabilities of the first device, and the state of at least the first device to be used to identify within the data store a set of instructions for interacting with at least the first device to solve the operational problem, and causes the set of instructions to be presented to a user.

Abstract: Method and system for providing secured access to services rendered by digital voice assistants are disclosed. In an example, the method includes generating, by the digital voice assistant in a set-up mode, hierarchical access levels for a plurality of services rendered by the digital voice assistant, based on an input from a super user. The method further includes generating, by the digital voice assistant in an operational mode and upon receiving a voice command from a user for a first time, a unique voice directive corresponding to the voice command. The unique voice directive comprises language tags and voice tags extracted from the voice command. The method further includes assigning an access level from among the hierarchical access levels to the unique voice directive and rendering a service from among the plurality of services based on the access level and the voice directive.

Abstract: The computer receives a group of conversation data associated with the escalation node, identifies agent responses in the conversation data, and clusters them into agent response types. The computer identifies dialog state feature value sets for the conversations. The computer identifies feature value set associations with response types, and generates, Boolean expressions representing the feature value sets associated with each of the response types. The computer makes a recommendation to add to at least one child node for the escalation node, with the child node corresponding to one of the response types. The child node has, as an entry condition, the Boolean expression for the response type to which the child node corresponds. The child node has as an action, which according to some aspects, provides a response representative of the cluster of agent responses for the response type to which the child node corresponds.

Abstract: When a caller initiates a conversation with an interactive voice response (“IVR”) system, the caller may be transferred to a live agent. Apparatus and methods are provided for integrating automated tools and artificial intelligence (“AI”) into the interaction with the IVR system. The automated tools and AI may track the conversation to decipher when to transfer the caller to the agent. The agent may determine which machine generated responses are appropriate for the caller. AI may be leveraged to suggest responses for both caller and agent while they are interacting with each other. The agent may transfer back the caller to the IVR system along with the appropriate machine generated response to maintain efficiency and shorten time of human agent interaction.

Abstract: A method to transcribe communications may include obtaining, at a first device, an audio signal that originates at a remote device during a communication session. The audio signal may be shared between the first device and a second device. The method may also include obtaining an indication that the second device is associated with a remote transcription system and in response to the second device being associated with the remote transcription system, directing the audio signal to the remote transcription system by one of the first device and the second device instead of both the first device and the second device directing the audio signal to the remote transcription system when the second device is not associated with the remote transcription system.

Abstract: Presented herein are embodiments of state-of-the-art speech recognition systems developed using end-to-end deep learning. In embodiments, the model architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments. In contrast, embodiments of the system do not need hand-designed components to model background noise, reverberation, or speaker variation, but instead directly learn a function that is robust to such effects. Neither a phoneme dictionary, nor even the concept of a “phoneme,” is needed. Embodiments include a well-optimized recurrent neural network (RNN) training system that can use multiple GPUs, as well as a set of novel data synthesis techniques that allows for a large amount of varied data for training to be efficiently obtained.

Abstract: In accordance with some embodiments, an apparatus that controls sensor paths for privacy protection is provided. The apparatus includes a housing arranged to hold a second device. The apparatus obtains first sensor data that includes a biometric marker associated with a user. The apparatus controls sensor paths by obtaining the first sensor data using sensors on the second device, on the apparatus, and/or on a supplemental functional device. The apparatus further generates second sensor data by masking the biometric marker associated with the user in the first sensor data. The apparatus additionally controls the sensor paths by providing the second sensor data from the first apparatus to the second device.

Abstract: Systems and methods of facilitating transactions related to targeted or customized commercial offerings based on derived sentiment states are provided. The sentiment states are derived from digital representations such as images, videos and sound recordings.

Abstract: An electronic device and a method for controlling the same are provided. The electronic device includes a microphone, a memory storing at least one instruction and dialogue history information, and a processor configured to be connected to the microphone and the memory and control the electronic device, in which the processor, by executing the at least one instruction, is configured to, based on a user's voice being input via the microphone, obtain response information for generating a response sentence to the user's voice, select at least one template phrase for generating the response sentence to the user's voice based on the stored dialogue history information, generate the response sentence using the response information and the at least one template phrase, and output the generated response sentence.

Abstract: A speech recognition system and method thereof are provided. The speech recognition system connects to an external general-purpose speech recognition system, and including a storage unit and a processing unit. The storage unit stores a specific application speech recognition module, a comparison module and an enhancement module. The specific application speech recognition module converts a speech signal into a first phonetic text. The general-purpose speech recognition system converts the speech signal into a written text. The comparison module receives the first phonetic text and the written text, converts the written text into a second phonetic text, and aligns the second phonetic text with the first phonetic text according to similarity of pronunciation to output a phonetic text alignment result. The enhancement module receives the phonetic text alignment result, and constructs with the written text and the first phonetic text after path weighting to form an outputting recognized text.

Abstract: A system for automating testing of an accessibility screen-reader for a software application includes an accessibility testing module. The accessibility testing module communicates a set of input commands to a user device in which the software application is installed. The set of input commands emulates a set of actions being performed on the software application. For each input command, an audio of a string of utterances is received when the accessibility screen-reader produces the audio. The audio is converted to a text of the string of utterances. The text is compared with a corresponding test string that is expected to be uttered by the accessibility screen-reader when a corresponding action is performed on the software application. If it is determined that the text matches the corresponding test string, it is concluded that the accessibility screen-reader uttered the corresponding test string that was expected to be uttered.

Abstract: Provided are a system and method for modifying a speech recognition result. The method includes: receiving, from a device, text output from an automatic speech recognition (ASR) model of the device; identifying at least one domain related to the received text; selecting, from among a plurality of text modification models included in the server, at least one text modification model corresponding to the identified at least one domain; and modifying the received text by using the selected at least one text modification model.

Abstract: A voice command system according to a first disclosure comprises a gateway apparatus having an interface configured to receive a voice command, and a controller configured to perform a registration process of registering a speaker permitted to receive the voice command. The controller is configured to perform an authentication process of rejecting a reception of the voice command when a speaker of the voice command is not registered, and permitting a reception of the voice command when a speaker of the voice command is registered. The controller is configured to perform the authentication process for each voice command.

Abstract: A refrigerator comprises a storage compartment configured to store food, a temperature detector configured to detect an internal temperature of the storage compartment, a cooler configured to supply cool air to the storage compartment, a microphone configured to receive a speech, a display configured to display information, at least one processor configured to be electrically connected to the temperature detector, the microphone, and the display; and a memory configured to be electrically connected to the at least one processor.

Abstract: A system for identifying a speaker in a multi-speaker environment comprises a processor operably coupled with a memory. The system receives a request to identify a first speaker in an audio file. The system splits the audio file into audio snippets based on a probability of each audio snippet comprising one or more utterances being above a threshold percentage. For each audio snippet, the system generates a frequency representation of the audio snippet in a time domain. The system generates a feature vector of numerical values representing voice features associated with one or both of the first speaker and the second speaker. The system determines whether the feature vector corresponds to the target vector labeled with the first speaker. In response to determining that the feature vector corresponds to the target vector, the system determines that one or more utterances in the audio snippet are spoken by the first speaker.

Abstract: Techniques are described for training and executing a machine learning model using data derived from a database. A dialog system uses data from the database to generate related training data for natural language understanding applications. The generated training data is then used to train a machine learning model. This enables the dialog system to leverage a large amount of available data to speed up the training process as compared to conventional labeling techniques. The dialog system uses the trained machine learning model to identify a named entity from a received spoken utterance and generate and output a speech response based upon the identified named entity.

Abstract: Techniques to dynamically customize a menu system presented to a user by a voice interaction system are provided. Audio data from a user that includes the speech of a user can be received. Features can be extracted from the received audio data, including a vocabulary of the speech of the user. The extracted features can be compared to features associated with a plurality of user group models. A user group model to assign to the user from the plurality of user group models can be determined based on the comparison. The user group models can cluster users together based on estimated characteristics of the users and can specify customized menu systems for each different user group. Audio data can then be generated and provided to the user in response to the received audio data based on the determined user group model assigned to the user.

Abstract: The invention relates to a method for an efficient dialogue configuration and interpretation in a computer-supported automated dialogue system. The invention offers, inter alia, the advantage that the work complexity when generating dialogues, and thus also the error propensity, is reduced. Furthermore, it is possible to take the context of sub-dialogs into consideration and dynamically generate a dialogue depending on said context. Furthermore, the method can automatically initiate a dialogue with a human user. The invention further relates to a correspondingly designed system assembly and to a computer program product with control commands which carry out the method or operate the system assembly.

Abstract: It is an aspect of the present disclosure to provide a dialogue system capable of providing an extended function to the user by registering a new vocabulary that matches the user's preference and by changing the pre-stored conversation pattern.

Abstract: An audio control system can control interactions with an application or device using keywords spoken by a user of the device. The audio control system can use machine learning models (e.g., a neural network model) trained to recognize one or more keywords. Which machine learning model is activated can depend on the active location in the application or device. Responsive to detecting keywords, different actions are performed by the device, such as navigation to a pre-specified area of the application.

Abstract: This relates to intelligent automated assistants and, more specifically, to the intelligent coordination of audio signal output adjustments among multiple electronic devices.

Abstract: A device, such as Network Microphone Device or a playback device, receives an indication of a track change associated with a playback queue output by a media playback system. In response, an input detection window is opened for a given time period. During the given time period the device is arranged to receive an input sound data stream representing sound detected by a microphone. The input sound data stream is analyzed for a plurality of command keywords and/or a wake-word for a Voice Assistant Service (VAS) and, based on the analysis, it is determined that the input sound data stream includes voice input data comprising a command keyword or a wake-word for a VAS. In response, the device takes appropriate action such as causing the media playback system to perform a command corresponding to the command keyword or sending at least part of the input sound data stream to the VAS.

Abstract: A method for providing natural language conversation is implemented by an interactive agent system. The method for providing natural language conversation, according to an embodiment of the present invention includes receiving a natural language input; determining a user intent based on the natural language input by processing the natural language input, and providing a natural language response corresponding to the natural language input, based on at least one of the natural language input and the determined user intent. The natural language response may be provided by determining whether a predetermined first condition is satisfied, providing a natural language response belonging to a category of substantial replies when the first condition is satisfied, determining whether a predetermined second condition is satisfied when the first condition is not satisfied, and providing a natural language response belonging to a category of interjections when the second condition is satisfied.

Abstract: Embodiments of the present disclosure disclose a method and apparatus for processing information. A specific embodiment of the method comprises: determining whether to enable a scenario mode based on received voice information; in response to determining to enable the scenario mode, determining a target scenario according to an analysis result of the voice information; acquiring resource information related to the target scenario; and feeding back the acquired resource information to a user. In the scenario mode, the embodiment may s provide many kinds of information resources at the same time for the user to select. This helps to improve the efficiency of the user in acquiring the information and may improve the efficiency of the human-machine interaction.

Abstract: Systems described herein may use transformer-based machine classifiers to perform a variety of natural language understanding tasks including, but not limited to sentence classification, named entity recognition, sentence similarity, and question answering. The exceptional performance of transformer-based language models is due to their ability to capture long-term temporal dependencies in input sequences. Machine classifiers may be trained using training data sets for multiple tasks, such as but not limited to sentence classification tasks and sequence labeling tasks. Loss masking may be employed in the machine classifier to jointly train the machine classifier on multiple tasks simultaneously. The user of transformer encoders in the machine classifiers, which treat each output sequence independently of other output sequences, in accordance with aspects of the invention do not require joint labeling to model tasks.

Abstract: A voice recognition device includes a memory that stores dictionary data in which likelihoods that each of registered words precedes other registered words are stored, and digital voice data corresponding to a voice signal input through a microphone, and a processor configured to perform voice recognition and acquire a first character string corresponding to the digital voice data, when a first letter of the first character string is a vowel letter, generate a plurality of first words that precede a second word in the first character string according to the dictionary data, each of the first words having a different first letter, and select one of the first words based on the likelihoods and output the second character string that is a combination of the selected first word and the second word.