skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Speaker verification system using acoustic data and non-acoustic data

Abstract

A method and system for speech characterization. One embodiment includes a method for speaker verification which includes collecting data from a speaker, wherein the data comprises acoustic data and non-acoustic data. The data is used to generate a template that includes a first set of "template" parameters. The method further includes receiving a real-time identity claim from a claimant, and using acoustic data and non-acoustic data from the identity claim to generate a second set of parameters. The method further includes comparing the first set of parameters to the set of parameters to determine whether the claimant is the speaker. The first set of parameters and the second set of parameters include at least one purely non-acoustic parameter, including a non-acoustic glottal shape parameter derived from averaging multiple glottal cycle waveforms.

Inventors:
 [1];  [2];  [3];  [4]
  1. Walnut Creek, CA
  2. Danville, CA
  3. Berkeley, CA
  4. Livermore, CA
Publication Date:
Research Org.:
Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
908544
Patent Number(s):
7,016,833
Application Number:
09/879,469
Assignee:
The Regents of the University of California (Oakland, CA) OAK
DOE Contract Number:
W-7405-ENG-48
Resource Type:
Patent
Country of Publication:
United States
Language:
English
Subject:
47 OTHER INSTRUMENTATION

Citation Formats

Gable, Todd J, Ng, Lawrence C, Holzrichter, John F, and Burnett, Greg C. Speaker verification system using acoustic data and non-acoustic data. United States: N. p., 2006. Web.
Gable, Todd J, Ng, Lawrence C, Holzrichter, John F, & Burnett, Greg C. Speaker verification system using acoustic data and non-acoustic data. United States.
Gable, Todd J, Ng, Lawrence C, Holzrichter, John F, and Burnett, Greg C. Tue . "Speaker verification system using acoustic data and non-acoustic data". United States. doi:. https://www.osti.gov/servlets/purl/908544.
@article{osti_908544,
title = {Speaker verification system using acoustic data and non-acoustic data},
author = {Gable, Todd J and Ng, Lawrence C and Holzrichter, John F and Burnett, Greg C},
abstractNote = {A method and system for speech characterization. One embodiment includes a method for speaker verification which includes collecting data from a speaker, wherein the data comprises acoustic data and non-acoustic data. The data is used to generate a template that includes a first set of "template" parameters. The method further includes receiving a real-time identity claim from a claimant, and using acoustic data and non-acoustic data from the identity claim to generate a second set of parameters. The method further includes comparing the first set of parameters to the set of parameters to determine whether the claimant is the speaker. The first set of parameters and the second set of parameters include at least one purely non-acoustic parameter, including a non-acoustic glottal shape parameter derived from averaging multiple glottal cycle waveforms.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Mar 21 00:00:00 EST 2006},
month = {Tue Mar 21 00:00:00 EST 2006}
}

Patent:

Save / Share:
  • Low Power EM radar-like sensors have made it possible to measure properties of the human speech production system in real-time, without acoustic interference. This greatly enhances the quality and quantity of information for many speech related applications. See Holzrichter, Burnett, Ng, and Lea, J. Acoustic. SOC. Am . 103 ( 1) 622 (1998). By combining the Glottal-EM-Sensor (GEMS) with the Acoustic-signals, we've demonstrated an almost 10 fold reduction in error rates from a speaker verification system experiment under a moderate noisy environment (-10dB).
  • In some aspects of the disclosure, a method for creating three-dimensional images of non-linear properties and the compressional to shear velocity ratio in a region remote from a borehole using a conveyed logging tool is disclosed. In some aspects, the method includes arranging a first source in the borehole and generating a steered beam of elastic energy at a first frequency; arranging a second source in the borehole and generating a steerable beam of elastic energy at a second frequency, such that the steerable beam at the first frequency and the steerable beam at the second frequency intercept at amore » location away from the borehole; receiving at the borehole by a sensor a third elastic wave, created by a three wave mixing process, with a frequency equal to a difference between the first and second frequencies and a direction of propagation towards the borehole; determining a location of a three wave mixing region based on the arrangement of the first and second sources and on properties of the third wave signal; and creating three-dimensional images of the non-linear properties using data recorded by repeating the generating, receiving and determining at a plurality of azimuths, inclinations and longitudinal locations within the borehole. The method is additionally used to generate three dimensional images of the ratio of compressional to shear acoustic velocity of the same volume surrounding the borehole.« less
  • A method and system includes generating a first coded acoustic signal including pulses each having a modulated signal at a central frequency; and a second coded acoustic signal each pulse of which includes a modulated signal a central frequency of which is a fraction d of the central frequency of the modulated signal for the corresponding pulse in the first plurality of pulses. A receiver detects a third signal generated by a non-linear mixing process in the mixing zone and the signal is processed to extract the third signal to obtain an emulated micro-seismic event signal occurring at the mixingmore » zone; and to characterize properties of the medium or creating a 3D image of the properties of the medium, or both, based on the emulated micro-seismic event signal.« less