Patents by Inventor Juan Manuel PERERO CODOSERO

Juan Manuel PERERO CODOSERO 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).

  • Method and system to estimate speaker characteristics on-the-fly for unknown speaker with high accuracy and low latency
    Patent number: 11488608
    Abstract: A computer-implemented technique is presented for profiling an unknown speaker. A DNN-based frame selection allows the system to select the relevant frames necessary to provide a reliable speaker characteristic estimation. A frame selection module selects those frames that contain relevant information for estimating a given speaker characteristic and thereby contributes to the accuracy and the low latency of the system. Real-time speaker characteristics estimation allows the system to estimate the speaker characteristics from a speech segment of accumulated selected frames at any given time. The frame level processing contributes to the low latency as it is not necessary to wait for the whole speech utterance to predict a speaker characteristic but rather a speaker characteristic is estimated from only a few reliable frames. Different stopping criteria also contribute to the accuracy and the low latency of the system.
    Type: Grant
    Filed: December 16, 2019
    Date of Patent: November 1, 2022
    Assignee: SIGMA TECHNOLOGIES GLOBAL LLC
    Inventors: Juan Manuel Perero-Codosero, Fernando Espinoza-Cuadros
  • METHOD AND SYSTEM TO ESTIMATE SPEAKER CHARACTERISTICS ON-THE-FLY FOR UNKNOWN SPEAKER WITH HIGH ACCURACY AND LOW LATENCY
    Publication number: 20210407523
    Abstract: A computer-implemented technique is presented for profiling an unknown speaker. A DNN-based frame selection allows the system to select the relevant frames necessary to provide a reliable speaker characteristic estimation. A frame selection module selects those frames that contain relevant information for estimating a given speaker characteristic and thereby contributes to the accuracy and the low latency of the system. Real-time speaker characteristics estimation allows the system to estimate the speaker characteristics from a speech segment of accumulated selected frames at any given time. The frame level processing contributes to the low latency as it is not necessary to wait for the whole speech utterance to predict a speaker characteristic but rather a speaker characteristic is estimated from only a few reliable frames. Different stopping criteria also contribute to the accuracy and the low latency of the system.
    Type: Application
    Filed: December 16, 2019
    Publication date: December 30, 2021
    Inventors: Juan Manuel PERERO CODOSERO, Fernando ESPINOZA CUADROS