Abstract: Methods and apparatuses are described for intelligent dialogue recovery in virtual assistant communication sessions. A chat session is established between a virtual assistant (VA) and a remote device. A primary dialogue is created between the VA and the remote device, including (i) requesting from a first natural language processing (NLP) service an intent associated with user messages and (ii) waiting for a corresponding response. A secondary dialogue is created between the VA and the remote device that is synchronized to a state of the primary dialogue. When the response from the first NLP service succeeds, primary messages are generated and transmitted to the remote device in the primary dialogue. When the response from the first NLP service fails, an intent is requested from the second NLP service, and secondary messages are generated and transmitted to the remote device in the secondary dialogue.

Abstract: Systems and methods for efficient management of an audio/video conferences is disclosed. The method includes receiving an audio question from a first user of a plurality of users connected to a conference, recording the audio question and preventing an immediate transmission of the audio question to the plurality of users connected to the conference, analyzing the recorded question and a recorded portion of the conference to determine that the question has been answered during the recorded portion of the conference, and in response to the determining that the audio question has previously been answered, transmitting a relevant section of the recorded portion of the conference consisting of an answer to the audio question to the first user.

Abstract: A method includes applying, by at least one processor, a natural language understanding (NLU) model to an input utterance in order to obtain initial slot probability distributions. The method also includes performing, by the at least one processor, a confidence calibration by applying a calibration probability distribution to the initial slot probability distributions in order to generate calibrated slot probability distributions. The calibration probability distribution has a higher number of dimensions than the initial slot probability distributions. The method further includes identifying, by the at least one processor, uncertainties associated with words in the input utterance based on the calibrated slot probability distributions. In addition, the method includes identifying, by the at least one processor, a new concept contained in the input utterance that is not recognized by the NLU model based on the identified uncertainties.

Abstract: Methods and systems include sending recording data of a call to a first server and a second server, wherein the recording data includes a first voice of a first participant of the call and a second voice of a second participant of the call; receiving, from the first server, a first emotion score representing a degree of a first emotion associated with the first voice, and a second emotion score representing a degree of a second emotion associated with the first voice; receiving, from the second server, a first sentiment score, a second sentiment score, and a third sentiment score; determining a quality score and classification data for the recording data based on the first emotion score, the second emotion score, the first sentiment score, the second sentiment score, and the third sentiment score; and outputting the quality score and the classification data for visualization of the recording data.

Abstract: A method and system for training a text-to-content recommendation ML model includes training a first ML model using a first training data set, utilizing the trained first ML model to infer information about the data contained in the first training data set, collecting the inferred information to generate a second training data set, and utilizing the first training data set and the second training data set to train a second ML model. The second ML model may be a text-to-content recommendation ML model.

Abstract: Embodiments may process search input for different users based on classifications of information and based on emotional content of search commands from the users. For example, a method may comprise receiving, at a computer system, speech data from a client device, the speech data representing a voice command from a user, obtaining, at the computer system, a plurality of items of content responsive to the voice command by searching for content, determining, at the computer system, at least one class related to the voice command, classifying, at the computer system, each obtained item of content into at least one class, identifying, at the computer system, at least one item of content classified into at least one class related to the voice command, and transmitting, at the computer system, the at least one identified item of content.

Abstract: A system for parsing separate intents in natural language speech configured to (i) receive, from the user computer device, a verbal statement of the user including a plurality of words; (ii) translate the verbal statement into text; (iii) label each of the plurality of words in the verbal statement; (iv) detect one or more potential splits in the verbal statement; (v) divide the verbal statement into a plurality of intents based upon the one or more potential splits; and (vi) generate a response based upon the plurality of intents.

Abstract: A system and method to interpret natural language requests and handle natural language responses in conversation is disclosed. The system includes an intent creation subsystem to receive one or more predefined intents to create one or more corresponding intent databases; a natural language message handling subsystem to receive a plurality of natural language messages from a user to identify one or more intents, to match one or more identified intents associated with the plurality of received natural language messages with the one or more predefined intents, handle the one or more identified intents by using a first message handling scheme when a similar match is found and a second message handling scheme in case of a dissimilar match; a natural language response handling subsystem to extract information from plurality of received natural language messages, to rectify the plurality of received natural language messages to handle a structured natural language response.

Abstract: Based on a detection that a customer has arrived at an enterprise location to pick up a previously-placed order, an intelligent automated customer dialogue system generates an interface via which an intelligent customer dialogue application dialogues with the customer. The application generates and initially offers, at the interface using natural language, content which is contextual to one or more items of the order, e.g., by using a specially trained intelligent dialogue machine learning model. The application may intelligently respond to the customer's natural language responses and/or requests to refine, augment, or redirect subsequently-offered content and/or dialogue, e.g., by using the model. Offered content (e.g., product information, services, coupons, suggestions, recommendations, etc.) generally provides value-add to the customer as well as maintains customer engagement.

Abstract: Embodiments describe a method for decoding speech including receiving speech input at an audio input device, generating speech data that is a digital representation of the speech input; extracting acoustic features of the speech data, assigning acoustic scores to the acoustic features, receiving data representing the acoustic features and the acoustic scores, decoding the data representing the acoustic features into a word, having a word score, by referencing a WFST language model, modifying the word score into a new word score based on a personalized grammar model stored in the external memory device, the processor is separate from and external to the WFST accelerator, and determining an intent represented by a plurality of words outputted by the WFST accelerator, where the plurality of words include the word and the new word score.

Abstract: Systems, methods, and computer-readable storage media for generating a quantifiable communication profile of a participant, then using that communication profile to identify fake media and/or verify media as authentic. An exemplary system can receive communications in which a participant was one of the parties communicating, perform natural language processing and statistical analyses on the received communications, and generate a participant communication profile which details how the participant communicates and prefers to be communicated with. The system can also receive media purported to be from the participant, perform natural language processing on the purported media, compare the syntax of the purported media to the participant's communication profile, and identify, based on word usage, the media as a fake.

Abstract: A method, computer program, and computer system is provided for extracting relations between one or more entities in a sentence. A forest corresponding to probabilities of relations between each pair of the entities is generated, and the generated forest generated forest is encoded with relation information for each of the pairs of entities. One or more features are extracted based on the generated forest and the encoded relation information, and a relation is predicted between the entities of each pair of entities based on the extracted features.

Abstract: The present disclosure is generally directed to the generation of voice-activated data flows in interconnected network. The voice-activated data flows can include input audio signals that include a request and are detected at a client device. The client device can transmit the input audio signal to a data processing system, where the input audio signal can be parsed and passed to the data processing system of a service provider to fulfill the request in the input audio signal. The present solution is configured to conserve network resources by reducing the number of network transmissions needed to fulfill a request.

Abstract: An automated natural dialogue system provides a combination of structure and flexibility to allow for ease of annotation of dialogues as well as learning and expanding the capabilities of the dialogue system based on natural language interactions.

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

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech endpointing based on word comparisons are described. In one aspect, a method includes the actions of obtaining a transcription of an utterance. The actions further include determining, as a first value, a quantity of text samples in a collection of text samples that (i) include terms that match the transcription, and (ii) do not include any additional terms. The actions further include determining, as a second value, a quantity of text samples in the collection of text samples that (i) include terms that match the transcription, and (ii) include one or more additional terms. The actions further include classifying the utterance as a likely incomplete utterance or not a likely incomplete utterance based at least on comparing the first value and the second value.

Abstract: A device comprises a transcription unit for transcribing an audio message received from the air traffic control into a text message, a processing unit for extracting first indications from the text message, a transcription unit for transcribing, into a restated text message, a restated audio message transmitted by the pilot to the air traffic control after the reception of the audio message, a processing unit for extracting second indications from the restated text message, a comparison unit for comparing the first and second indications and a warning unit for transmitting a warning to the pilot if a difference between the first and second indications is detected, so as to notify the pilot that they have misunderstood the audio message from air traffic control.

Abstract: An analyzing apparatus according to an embodiment includes a memory and a hardware processor coupled to the memory. The hardware processor is configured to: calculate a first similarity between a first word representing a category and a second word; apply, to one or more template sentences, each of one or more second words having the first similarity higher than a first threshold; analyze the one or more template sentences each including the second word and classify the second word into one or more first categories; and display, for each of the first categories, the second word used in the classification into the first categories on a display device.

Abstract: Methods and systems for dynamically updating machine learning models that provide conversational responses through the use of a configuration file that defines modifications and changes to the machine learning model are disclosed. For example, the configuration file may be used to define an expected behavior and required attributes for instituting modifications and changes (e.g., via a mutation algorithm) to the machine learning model.

Abstract: A communication system is provided that generates human emotion metadata during language translation of verbal content. The communication system includes a media control unit that is coupled to a communication device and a translation server that receive verbal content from the communication device in a first language. An adapter layer having a plurality of filters determines emotion associated with the verbal content, wherein the adapter layer associates emotion metadata with the verbal content based on the determined emotion. The plurality of filters may include user-specific filters and non-user-specific filters. An emotion lexicon is provided that links an emotion value to the corresponding verbal content. The communication system may include a display that graphically displays emotions alongside the corresponding verbal content.