Abstract: A method, computer system, and a computer program product for personalized voice responses is provided. The present invention may include gathering a plurality of user data from an Internet of Things (IoT) connected sensor. The present invention may include identifying a personalized vocabulary based on the gathered plurality of user data. The present invention may include training a voice response system based on the gathered plurality of user data and the identified personalized vocabulary. The present invention may include receiving a verbal request. The present invention may include responding to the received verbal request using the trained voice response system.

Abstract: Systems and methods for dynamically generating object models corresponding to regulations. According to certain aspects, a server computer may access a regulation and automatically generate a summary of the regulation based on a specific set of sentences. The server computer may additionally determine a set of topics and named-entity attributes for text within a regulation object model, as well as a probability that a topic or attribute is applicable to the regulation. Further, the server computer may generate and enrich object models according to the various analyses and avail the enriched object models for review by entities and users of regulatory compliance services.

Abstract: A voice analysis (VA) computer system for processing verbally inputted data into an online insurance claim submission application is provided. The VA computer system is configured to receive a first set of digital sound data in connection with a request to submit a virtual insurance claim for an applicant, and enable a voice-input tool on a user computing device for the applicant to input registration data, the registration data included in a second set of digital sound data. The VA computer system is configured to retrieve a text-based template based upon a portion of the registration data, the text-based template including descriptor phrases and blank data fields. The VA computer system may be configured to receive the registration data as the second set of digital sound data, translate the received second set into text inputs, and store within a database, each descriptor phrase linked to the corresponding response associated therewith.

Abstract: A computer-implemented method is provided for estimating output confidence of a black box Application Programming Interface (API). The method includes generating paraphrases for an input text. The method further includes calculating a distance between the input text and each respective one of the paraphrases. The method also includes sorting the paraphrases in ascending order of the distance. The method additionally includes selecting a top predetermined number of the paraphrases. The method further includes inputting the input text and the selected paraphrases into the API to obtain an output confidence score for each of the input text and the selected paraphrases. The method also includes estimating, by a hardware processor, the output confidence of the input text from a robustness of output scores of the input text and the selected paraphrases.

Abstract: Techniques for synchronizing communication across devices are described. A system receives an input command corresponding to an announcement and sends data representing the announcement to devices of the system. The system receives responses from the devices and causes the device that originated the announcement to output content corresponding to the responses.

Abstract: Systems and techniques are generally described for anomaly detection in text. In some examples, text data comprising a plurality of words may be received. An image of a first word of the plurality of words may be generated. A feature representation of the first word may be generated using a variational autoencoder. A score may be generated based at least in part on the feature representation. In various examples, the score may indicate a likelihood that an appearance of the first word in the image of the first word is anomalous with respect to at least some other words of the plurality of words.

Abstract: Embodiments are provided to recognize features and activities from an audio signal. In one embodiment, a model is generated from sound effect data, which is augmented and projected into an audio domain to form a training dataset efficiently. Sound effect data is data that has been artificially created or from enhanced sounds or sound processes to provide a more accurate baseline of sound data than traditional training data. The sound effect data is augmented to create multiple variants to broaden the sound effect data. The augmented sound effects are projected into various audio domains, such as indoor, outdoor, urban, based on mixing background sounds consistent with these audio domains. The model is installed on any computing device, such as a laptop, smartphone, or other device. Features and activities from an audio signal are then recognized by the computing device based on the model without the need for in-situ training.

Abstract: A system, apparatus, and method for processing a natural language, and a computer readable recording medium are provided. The system includes a user device configured to receive a compound or complex sentence and a natural language processing apparatus configured to generate a plurality of control commands for the user device based on whether operations intended by a user are sequentially performable in the compound or complex sentence received from the user device.

Abstract: A system and related method exchange medical information with a medical management system. The method comprises receiving, using a processor of a code point resolver, from the medical management system, medical text via a network interface. A code point is a single standardized medical terminology code (SMTC) that corresponds to a medical concept contained within the medical text. The method further applies rule-based logic to process the medical text to form a localized mapping of a text portion of the medical text to a plurality of candidate SMTCs (CSMTCs) that are related to at least one metathesaurus concept entity (MCE) in a metathesaurus, and to determines the code point from the CSMTCs. The method transmits, via the network interface, to the medical management system, the code point.

Abstract: A transformer-transducer model for unifying streaming and non-streaming speech recognition includes an audio encoder, a label encoder, and a joint network. The audio encoder receives a sequence of acoustic frames, and generates, at each of a plurality of time steps, a higher order feature representation for a corresponding acoustic frame. The label encoder receives a sequence of non-blank symbols output by a final softmax layer, and generates, at each of the plurality of time steps, a dense representation. The joint network receives the higher order feature representation and the dense representation at each of the plurality of time steps, and generates a probability distribution over possible speech recognition hypothesis. The audio encoder of the model further includes a neural network having an initial stack of transformer layers trained with zero look ahead audio context, and a final stack of transformer layers trained with a variable look ahead audio context.

Abstract: A discriminator trained on labeled samples of speech can compute probabilities of voice properties. A speech synthesis generative neural network that takes in text and continuous scale values of voice properties is trained to synthesize speech audio that the discriminator will infer as matching the values of the input voice properties. Voice parameters can include speaker voice parameters, accents, and attitudes, among others. Training can be done by transfer learning from an existing neural speech synthesis model or such a model can be trained with a loss function that considers speech and parameter values. A graphical user interface can allow voice designers for products to synthesize speech with a desired voice or generate a speech synthesis engine with frozen voice parameters. A vector of parameters can be used for comparison to previously registered voices in databases such as ones for trademark registration.

Abstract: A system and method for automatically generating a narrative story receives data and information pertaining to a domain event. The received data and information and/or one or more derived features are then used to identify a plurality of angles for the narrative story. The plurality of angles is then filtered, for example through use of parameters that specify a focus for the narrative story, length of the narrative story, etc. Points associated with the filtered plurality of angles are then assembled and the narrative story is rendered using the filtered plurality of angles and the assembled points.

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: Methods, systems, and apparatus, including computer programs encoded on computer storage media for evaluating and improving live translation captioning systems. An exemplary method includes: displaying a word in a first language; receiving a first audio sequence, the first audio sequence comprising a verbal description of the word; generating a first translated text in a second language; displaying the first translated text; receiving a second audio sequence, the second audio sequence comprising a guessed word based on the first translated text; generating a second translated text in the first language; determining a matching score between the word and the second translated text; determining a performance score of the live translation captioning system based on the matching score.

Abstract: Techniques for using a dynamic wakeword detection threshold are described. A device detects a wakeword in audio data using a first wakeword detection threshold value. Thereafter, the device receives audio including speech. If the device receives the audio within a predetermined duration of time after detecting the previous wakeword, the device attempts to detect a wakeword in second audio data, corresponding to the audio including the speech, using a second, lower wakeword detection threshold value.

Abstract: Embodiments provide for improved data sequence validity processing, for example to determine validity of sentences or other language within a particular language domain. Such improved processing is useful at least for arranging data sequences based on determined validity, and/or making determinations and/or performing actions based on the determined validity. A determined probability (e.g., transformed into the perplexity space) of each token appearing in a data sequence is used in any of a myriad of manners to perform such data sequence validity processing. Example embodiments provide for generating a perplexity value set for each data sequence in a plurality of data sequences, generating a probabilistic ranking set for the plurality of data sequences based on the perplexity value sets and at least one sequence ranking metric, and generating an arrangement of the plurality of data sequences based on the probabilistic ranking set.

Abstract: A method for coordinating actions between an audio channel and a synchronized non-audio channel includes receiving an indication of a start of a session associated with a user and having an audio channel that is synchronized with a non-audio channel. Thereafter, repeated determinations are made as to whether a prompt on the non-audio channel has been received from the user. In response to each determination that the prompt on the non-audio channel has not been received from the user, a signal is sent to cause an inaudible output on the audio channel to the user. In response to a determination that the prompt on the non-audio channel has been received from the user, an audible output is selected based on an activity by the user on the non-audio channel, and a signal is sent to cause the audible output to be output on the audio channel.

Abstract: A computer-implemented interaction control method includes determining, based on a first requirement, a first category from one or more categories estimated from each of a plurality of pieces of information input by a user, selecting, based on the determined first category, a first conversation topic for interaction with the user from conversation topics, executing, by using the first conversation topic, the interaction with the user via a user interface, determining, when detecting that the first conversation topic is inappropriate in accordance with a result of the interaction executed by using the first conversation topic, based on a second requirement, a second category from the one or more categories, selecting, based on the determined second category, a second conversation topic for the interaction with the user from the conversation topics, executing, by using the second conversation topic, the interaction with the user via the user interface.

Abstract: An electronic device is provided. The electronic device includes a first memory configured to operate at a first speed and store compressed vectors corresponding to words, and scaling factors corresponding to the compressed vectors; a second memory that is faster than the first memory and is configured to store a first group of the compressed vectors, and store a first group of the scaling factors; and a processor configured to obtain a first compressed vector and a first scaling factor corresponding to an input word from the first memory or the second memory and process the obtained first compressed vector and the obtained first scaling factor by using a neural network.

Abstract: In some implementations, a language proficiency of a user of a client device is determined by one or more computers. The one or more computers then determines a text segment for output by a text-to-speech module based on the determined language proficiency of the user. After determining the text segment for output, the one or more computers generates audio data including a synthesized utterance of the text segment. The audio data including the synthesized utterance of the text segment is then provided to the client device for output.