Patents by Inventor Amruta VIDWANS

Amruta VIDWANS has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Z-vectors: speaker embeddings from raw audio using sincnet, extended CNN architecture and in-network augmentation techniques
    Patent number: 11715460
    Abstract: Described herein are systems and methods for improved audio analysis using a computer-executed neural network having one or more in-network data augmentation layers. The systems described herein help ease or avoid unwanted strain on computing resources by employing the data augmentation techniques within the layers of the neural network. The in-network data augmentation layers will produce various types of simulated audio data when the computer applies the neural network on an inputted audio signal during a training phase, enrollment phase, and/or testing phase. Subsequent layers of the neural network (e.g., convolutional layer, pooling layer, data augmentation layer) ingest the simulated audio data and the inputted audio signal and perform various operations.
    Type: Grant
    Filed: October 8, 2020
    Date of Patent: August 1, 2023
    Assignee: PINDROP SECURITY, INC.
    Inventors: Elie Khoury, Ganesh Sivaraman, Tianxiang Chen, Amruta Vidwans
  • Z-VECTORS: SPEAKER EMBEDDINGS FROM RAW AUDIO USING SINCNET, EXTENDED CNN ARCHITECTURE AND IN-NETWORK AUGMENTATION TECHNIQUES
    Publication number: 20210110813
    Abstract: Described herein are systems and methods for improved audio analysis using a computer-executed neural network having one or more in-network data augmentation layers. The systems described herein help ease or avoid unwanted strain on computing resources by employing the data augmentation techniques within the layers of the neural network. The in-network data augmentation layers will produce various types of simulated audio data when the computer applies the neural network on an inputted audio signal during a training phase, enrollment phase, and/or testing phase. Subsequent layers of the neural network (e.g., convolutional layer, pooling layer, data augmentation layer) ingest the simulated audio data and the inputted audio signal and perform various operations.
    Type: Application
    Filed: October 8, 2020
    Publication date: April 15, 2021
    Inventors: Elie KHOURY, Ganesh SIVARAMAN, Tianxiang CHEN, Amruta VIDWANS