Abstract: Verbal language analysis is provided to users. The user enrolls or subscribes for verbal language analysis or analytics. The user carries out or conducts a conversation with a third party. An intelligence device associated with the user records the conversation. The intelligence device performs verbal language analysis on the conversation. The verbal language analysis generates individual metrics for verbal factors of energy, word count, inflection, tone (e.g. pitch and sentiment), rate, and/or the like. A verbal intelligence index is determined from the individual metrics using aggregation, averaging, weighted averaging, and/or the like. An interface component generates views to display to the user for review of the conversation to facilitate better verbal performance during current and in future conversations.

Abstract: Systems and methods for recording and transcribing conversations in real-time. Sentiment analysis is performed on each utterance to determine both an intent of the conversation along with sentiment. Annotated transcripts are provided. A machine learning model may be used to augment sentiment analysis.

Abstract: A device includes a processor, and a memory storing executable instructions which, when executed by the processor, cause the processor alone or in combination with other processors to perform the following functions: receive textual user input from a user describing a design to be generated; implement a first prompt generator to generate a first prompt for a Large Language Model (LLM) to restructure the user input; and implement a second prompt generator to generate a second prompt for a text-to-image model using output of the LLM to produce, the second prompt to prompt the text-to-image model to produce a proposed design based on the user input. The proposed design is provided to the user via an application comprising controls for further editing the proposed design.

Abstract: Devices and techniques are described for embedding-free speaker diarization. In some examples, a first speaker ID label is determined for a first frame and a second speaker ID label may be determined for a second frame of a first window of audio. A third speaker ID label may be determined for a third frame of a second window. First combined data representing at least the first frame and the third frame and second combined data representing at least the second frame and the third frame may be generated. First posterior data associated with the first frame and second posterior data associated with the third frame may be generated. Third posterior data associated with the second frame and fourth posterior data associated with the third frame may be generated. A determination may be made that the first speaker ID label and the third speaker ID label correspond to the same speaker.

Abstract: Methods and apparatuses for optimizing performance of conversational interface applications using example forgetting include a server that retrieves training data comprising utterances each mapped to one or more known intents. The server determines a forgetting count for each utterance and selects utterances from the training data that have a forgetting count above a predetermined threshold. The server identifies whether the predicted intent associated with each utterance is accurate. The server generates updated training data comprising the selected utterances and corresponding predicted intents, and trains conversational interface applications using the updated training data. The server validates performance of the trained conversational interface applications and saves the updated training data.

Abstract: The information processing device according to one embodiment includes: a setting part configured to pair and set, based on first information sent from a terminal that is connected via a communication network, user identification information with second information, the user identification information identifying a user using a given telephone machine, the second information being obtainable from a voice packet of a telephone call between the given telephone machine and another telephone machine, and the first information being predetermined information and the second information being predetermined information; and a specifying part configured to obtain, when a voice packet of a telephone call between the given telephone machine and another telephone machine arrives, the second information from the voice packet, and specify the user identification information paired with the second information obtained.

Abstract: A method of leveraging machine learning to predict empathy for improved contact center interactions according to an embodiment includes receiving, by a computing system, at least one user message from a real-time contact center interaction with a user, generating, by an artificial intelligence system of the computing system, at least one empathy score based on the at least one message using the machine learning, wherein each of the at least one empathy score is indicative of a real-time empathy of the user, generating, by the artificial intelligence system of the computing system, an empathetic text response to the at least one user message based on the at least one empathy score, and responding to the at least one user message in the real-time contact center interaction based on the empathetic text response generated by the artificial intelligence system of the computing system.

Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to receive a text comprising a plurality of sentences, by a machine learning model, extract a nonverbal message from one of the sentences and add an annotation to the text, the annotation indicating the nonverbal message, and output a version of the text including the annotation.

Abstract: Aspects of the disclosure are directed to a token aggregator for aggregating outputs from various generative models. The token aggregator can operate on a token-by-token basis, serving to aggregate several weighted generative model outputs to generate a joint output. By providing weights to the token aggregator as to what the preferred distribution may be, the weights can be used to tradeoff between generative model outputs to help determine the relative weight of the generative model outputs for creating the joint output as well as determining contribution amounts, e.g., bid payments, credits, or points, from respective model outputs.

Abstract: Techniques are described for performing automated operations that include analyzing computer-detected event activity to improve further computer processing, such as to determine tasks performed that cause the events, to use natural language processing (NLP) to generate textual descriptions of the tasks, and to use the generated descriptions to improve further processing related to the tasks.

Abstract: In an example embodiment, a method includes determining an attitudinal negativity score associated with a contact center agent, among a plurality of contact center agents, based on an interaction between the contact center agent and a user during a communication session, receiving data associated with an incoming user communication, determining a user ease score associated with the incoming user communication based on the data, and blocking routing of the incoming user communication to the contact center agent based on the attitudinal negativity score being above a first threshold score and the user ease score being below a second threshold score.

Abstract: A system that enables synchronized interaction between voice input and a visual user interface is described. The system receives, by a network site via a first user interaction channel, a user request to perform an action with a listing network platform. The system establishes, by the network site, a session associated with a session identifier for the user request and provides an option for the user to continue interacting with the listing network platform through a second user interaction channel. The system, in response to receiving input that selects the option, uses the session identifier associated with the session to synchronize a first set of inputs received through the first user interaction channel with a second set of inputs received through the second user interaction channel to complete the action on the listing network platform.

Abstract: A neural TTS system is trained to generate key acoustic frames at variable rates while omitting other frames. The frame skipping depends on the acoustic features to be generated for the input text. The TTS system can interpolate frames between the key frames at a target rate for a vocoder to synthesis audio samples.

Abstract: A telephony system generates a graphical user interface (GUI) keypad that includes one or more options detected in an audio stream from an interactive voice response (IVR) system. The telephony system detects speech associated with the IVR system in the audio stream and parses the speech to determine one or more options. The telephony system maps each option to a respective key on the GUI keypad. The system generates the GUI keypad such that it includes a representation of each option on a respective key of the GUI keypad.

Abstract: Aspects of the present disclosure are directed to receiving a user phone call and triggering user interactions via an alternative channel in response to the user phone call. Users may call an account service provider with issues related to a user account. To service such a call, the account service provider may prompt the user for information. This information can be analyzed to determine whether the conditions for the user's call are aligned with a shift to a more efficient alternative channel. For example, a guided user workflow via a webpage, application, chat agent, etc. may represent a more efficient deployment of organizational resources. When such conditions are aligned, the account service provider may trigger a selected user interaction workflow for the user call via an alternative channel. The user interaction workflow can comprise a guided workflow that is configured to resolve the user's issue related to the call.

Abstract: Various embodiments of the present disclosure provide summarization techniques for summarizing complex documents, such as long unstructured call transcripts. The summarization techniques include generating a plurality of interaction topics for an interaction transcript and iteratively summarizing each interaction topic based on a preceding partial summary for the interaction transcript that corresponds to a preceding interaction topic that precedes the interaction topic in the interaction transcript. An abstractive summary is generated using a recursive abstractive model that is trained using training data generated based on holistic similarity scores between interaction topics of a call transcript and summary sentences of a corresponding target summary.

Abstract: Provided is a one-shot solution to visual language reasoning. Example systems described herein decompose the challenge of visual language reasoning into two steps: translation of a graphical depiction of data (e.g., a plot or chart) into text; followed by reasoning over the translated text. In particular, example systems described herein can include a machine-learned visual-to-language conversion model that translates a graphical depiction of a dataset to a set of text descriptive of the dataset. The output of visual-to-language conversion model can then be directly used to prompt a language model, (e.g., a pretrained large language model (LLM)), exploiting the few-shot reasoning capabilities of the language model.

Abstract: Certain aspects of the disclosure are directed to apparatuses and methods involving a data-communication apparatus that includes a data-communications server and processing circuitry in communication therewith. The data-communication server interfaces with a plurality of remotely-situated client entities for providing data communication services. The processing circuitry accesses an archive of digital voice data indicative of transcribed audio conversations for at least one of the plurality of remotely-situated client entities, calendar information, and a client data-communications server for geographic information of the agents and system parameters. The processing circuitry analyzes the digital voice data associated with the agents, the calendar information, and the system parameters to predict relevant routing data including, as examples, a call answer rate for agents of a geographic region of the at least one remotely-situated client entity for a period of time.

Abstract: A computer acquires training data including first text, first class information indicating a class mapped to a single word contained in the first text, first position information indicating a position of the single word in the first text, and first range information indicating a range of a first named entity that includes the single word in the first text. The computer executes, based on the training data, machine learning of a machine learning model which is used to estimate, from text, class information, and position information, range information of a named entity included in the text.

Abstract: A speech recognition device includes a sound input section, a sound output section, a communication control section that performs data transmission and reception with at least one of other recognition devices, a conversation-mode executing section that transmits sound data input to each of the other recognition devices and outputs sound data received from each of the other recognition devices, a speech recognition section that converts the sound input into text data, a hot word detecting section that detects a conversation activation hot word from the text data to activate the conversation-mode executing section, and a command transmitting section that transmits a control command to each of the other recognition devices. If the hot word detecting section detects the conversation activation hot word, the command transmitting section transmits the control command to activate a conversation-mode executing section provided in each of the other recognition devices.