Systems and methods for enhanced speaker diarization

    公开(公告)号:US12165650B2

    公开(公告)日:2024-12-10

    申请号:US18634155

    申请日:2024-04-12

    Abstract: A system, method, and computer-program product includes receiving speech audio of a multi-turn conversation, generating, via a speech-to-text process, a transcript of the speech audio, wherein the transcript of the speech audio textually segments speech spoken during the multi-turn conversation into a plurality of utterances, generating a speaker diarization prompt that includes contextual information about a plurality of speakers participating in the multi-turn conversation, inputting, to a large language model, the speaker diarization prompt and the transcript of the speech audio, and obtaining, from the large language model, an output comprising an enhanced transcript of the speech audio, wherein the enhanced transcript of the speech audio textually segments the speech spoken during the multi-turn conversation into a plurality of refined utterances and associates a speaker identification value with each of the plurality of refined utterances.

    Systems and methods for dynamic allocation of compute resources via a machine learning-informed feedback sequence

    公开(公告)号:US12147838B1

    公开(公告)日:2024-11-19

    申请号:US18627375

    申请日:2024-04-04

    Abstract: A system, method, and computer-program product includes obtaining an analytical request that specifies an analytical task to be performed using computing resources of an adaptive analytics compute service, determining, by the adaptive analytics compute service, an initial set of compute resources for executing the analytical request based on identifying a type of the analytical request, deploying, by the adaptive analytics compute service, a compute environment for executing the analytical request based on the initial set of compute resources, observing utilization data of the initial set of compute resources during a period of executing the analytical request within the compute environment, and commencing a machine learning-informed feedback sequence for autonomously adapting the compute environment, wherein one iteration of the machine learning-informed feedback sequence includes: generating a proposed set of compute resources, and encoding, based on the proposed set of compute resources, a set of instructions for automatically adapting the compute environment.

    Method and system for digital traffic campaign management

    公开(公告)号:US12051087B2

    公开(公告)日:2024-07-30

    申请号:US18513882

    申请日:2023-11-20

    CPC classification number: G06Q30/0246 G06Q30/0201

    Abstract: The computing device receives data for a plurality of events that includes a timestamp associated with a digital traffic campaign in an event processing system. Based on the timestamp of the data for each event, the computing device executes operations comprising: applying filtering using digital signal processing to the event count for the combined data for each of the one or more intervals, executing a model to compute one or more backward difference approximations for the one or more candidate systems time constants from the evaluated exponential curve, and selecting a system time constant that predicts a first time instant wherein the data for the plurality of events approaches a point on a horizontal asymptote for the evaluated exponential curve. The computing device determines an epoch for the selected system time constant and outputs the determined epoch for the selected system time constant in the graphical user interface.

    SYSTEMS AND METHODS FOR CONFIGURING AND USING A MULTI-STAGE OBJECT CLASSIFICATION AND CONDITION PIPELINE

    公开(公告)号:US20240193917A1

    公开(公告)日:2024-06-13

    申请号:US18528685

    申请日:2023-12-04

    CPC classification number: G06V10/764 G06V10/94

    Abstract: A system, method, and computer-program product includes detecting, via a localization machine learning model, a target object within target image data of a scene, classifying, via an object classification machine learning model, the target object to a probable object class of a plurality of distinct object classes, routing, via the one or more processors, the target image data of the scene to a target object-condition machine learning classification model of a plurality of distinct object-condition machine learning classification models based on a mapping between the plurality of distinct object classes and the plurality of distinct object-condition machine learning classification models, classifying, via the target object-condition machine learning classification model, the target object to a probable object-condition class of a plurality of distinct object-condition classes, and displaying, via a graphical user interface, a representation of the target object in association with the probable object-condition class.

    Systems and methods for configuring and using a multi-stage object classification and condition pipeline

    公开(公告)号:US12002256B1

    公开(公告)日:2024-06-04

    申请号:US18528685

    申请日:2023-12-04

    CPC classification number: G06V10/764 G06V10/94

    Abstract: A system, method, and computer-program product includes detecting, via a localization machine learning model, a target object within target image data of a scene, classifying, via an object classification machine learning model, the target object to a probable object class of a plurality of distinct object classes, routing, via the one or more processors, the target image data of the scene to a target object-condition machine learning classification model of a plurality of distinct object-condition machine learning classification models based on a mapping between the plurality of distinct object classes and the plurality of distinct object-condition machine learning classification models, classifying, via the target object-condition machine learning classification model, the target object to a probable object-condition class of a plurality of distinct object-condition classes, and displaying, via a graphical user interface, a representation of the target object in association with the probable object-condition class.

    FLOW MODEL COMPUTATION SYSTEM WITH DISCONNECTED GRAPHS

    公开(公告)号:US20240070116A1

    公开(公告)日:2024-02-29

    申请号:US18207432

    申请日:2023-06-08

    CPC classification number: G06F15/825 G06F11/3495

    Abstract: A computing device determines a node traversal order for computing a computational parameter value for each node of a data model of a system that includes a plurality of disconnected graphs. The data model represents a flow of a computational parameter value through the nodes from a source module to an end module. A flow list defines an order for selecting and iteratively processing each node to compute the computational parameter value in a single iteration through the flow list. Each node from the flow list is selected to compute a driver quantity for each node. Each node is selected from the flow list in a reverse order to compute a driver rate and the computational parameter value for each node. The driver quantity or the computational parameter value is output for each node to predict a performance of the system.

    Multithreaded speech data preprocessing

    公开(公告)号:US11862171B2

    公开(公告)日:2024-01-02

    申请号:US17993385

    申请日:2022-11-23

    Abstract: An apparatus includes a processor to: receive, from a requesting device, a request to perform speech-to-text conversion of a speech data set; within a first thread of a thread pool, perform a first pause detection technique to identify a first set of likely sentence pauses; within a second thread of the thread pool, perform a second pause detection technique to identify a second set of likely sentence pauses; perform a speaker diarization technique to identify a set of likely speaker changes; divide the speech data set into data segments representing speech segments based on a combination of at least the first set of likely sentence pauses, the second set of likely sentence pauses, and the set of likely speaker changes; use at least an acoustic model with each data segment to identify likely speech sounds; and generate a transcript based, at least in part, on the identified likely speech sounds.

    Automated job flow generation to provide object views in container-supported many task computing

    公开(公告)号:US11775341B2

    公开(公告)日:2023-10-03

    申请号:US17733196

    申请日:2022-04-29

    CPC classification number: G06F9/4881 G06F9/485

    Abstract: An apparatus includes a processor to receive a request to provide a view of an object associated with a job flow, and in response to determining that the object is associated with a task type requiring access to a particular resource not accessible to a first interpretation routine: store, within a job queue, a job flow generation request message to cause generation of a job flow definition the defines another job flow for generating the requested view; within a task container in which a second interpretation routine that does have access to the particular resource is executed, generate the job flow definition; store, within a task queue, a job flow generation completion message that includes a copy of the job flow definition; use the job flow definition to perform the other job flow to generate the requested view; and transmit the requested view to the requesting device.

    Automated job flow cancellation for multiple task routine instance errors in many task computing

    公开(公告)号:US11748159B2

    公开(公告)日:2023-09-05

    申请号:US18091691

    申请日:2022-12-30

    CPC classification number: G06F9/4881 G06F9/485

    Abstract: An apparatus including a processor to: within a kill container, in response to a set of error messages indicative of errors in executing multiple instances of a task routine to perform a task of a job flow with multiple data object blocks of a data object, and in response to the quantity of error messages reaching a threshold, output a kill tasks request message that identifies the job flow; within a task container, in response to the kill tasks request message, cease execution of the task routine and output a task cancelation message that identifies the task and the job flow; and within a performance container, in response to he task cancelation message, output a job cancelation message to cause the transmission of an indication of cancelation of the job flow, via a network, and to a requesting device that requested the performance of the job flow.

Patent Agency Ranking