Patent · US Expired

Discriminative gaussian mixture models for speaker verification

US6411930B1 · kind B1 · utility

65Cited by
8References
27Claims
0Family size

Assignee

Inventor

Key dates

Filing dateFeb 12, 1999
Grant dateJun 25, 2002
Priority date
Expiry dateFeb 12, 2019

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L17/06
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Speaker identification is performed using a single Gaussian mixture model (GMM) for multiple speakers—referred to herein as a Discriminative Gaussian mixture model (DGMM). A likelihood sum of the single GMM is factored into two parts, one of which depends only on the Gaussian mixture model, and the other of which is a discriminative term. The discriminative term allows for the use of a binary classifier, such as a support vector machine (SVM). In one embodiment of the invention, a voice messaging system incorporates a DGMM to identify the speaker who generated a message, if that speaker is a member of a chosen list of target speakers, or to identify the speaker as a “non-target” otherwise.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.