Vail Systems, Inc.

Level 3 Communications, LLC

Bopsi Chandramouli

Todd Whiteley

William Breakell Long

Srinivasa Rao

David Fruin

Yu Zhou

Todd J Whiteley

A system and method for identifying a speaker based on dual calculation of voiceprint match scores, using machine learned voiceprint sets and machine learned hashing models to reduce a voiceprint set, normalizing the joint scores, and performing user identification. The system and method include, among other things, a novel normalization technique designed for multitarget detection that considers scores between all enrolled negative list (NL) utterances and the normalization cohort as a single distribution. The system and method include machine learned hashing models to efficiently find a small subset of utterances from enrolled NL utterances and the normalization cohort that are most similar to the test utterance, so that the number of similarity score computations can be significantly reduced in identifying the speaker.

System and method using machine learned voiceprint sets for efficient determination of voice membership using enhanced score normalization and locality sensitive hashing

Methods and systems for data management include representing, organizing, and accessing very large data sets. Embodiments describe supporting data sets of various size based on attributed data slices (ADSs) to enable reduced memory requirements, query decomposition and parallel execution, and constant execution times for concurrent queries. The ADSs can include data buckets comprising items that are grouped by an attribute key. Attribute groups can be further sorted (e.g., in ascending order) based on the attribute key. According to some embodiments, the essential structure of an ADS provides additional functionality while preserving the behavior expected of an ADS through the use of an Extension Block containing attribute location data.

Data management system using attributed data slices

Implementations of the present disclosure involve systems and methods for federating communications between a first network that transmits and receives messages formatted in a first format and a second network that transmits and receives messages formatted in a second format. The systems and methods are configured to receive a message from the first network formatted in the first format. The system then converts the message into a unified format that may be sent to the second network. After receiving the message in the unified format, the message may then be converted into the format of the second network and sent on the second network like any other message on the second network.

System and method for short message services to an instant messaging conversion

Implementations of the present disclosure involve a system and method for federating communications between a first network that transmits and receives messages formatted in a first format and a second network that transmits and receives messages formatted in a second format. The system and method are configured to receive a message from the first network formatted in the first format. The system then converts the message into a unified format that may be sent to the second network. After receiving the message in the unified format, the message may then be converted into the format of the second network and sent on the second network like any other message on the second network.

Growing community of inventors

Warrenville, IL, United States of America

Bopsi Chandramouli