Patent · US Expired

Speaker verification and speaker identification based on eigenvoices

US6141644A · kind A · utility

271Cited by
7References
11Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 4, 1998
Grant dateOct 31, 2000
Priority date
Expiry dateSep 4, 2018

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L17/02
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Speech models are constructed and trained upon the speech of known client speakers (and also impostor speakers, in the case of speaker verification). Parameters from these models are concatenated to define supervectors and a linear transformation upon these supervectors results in a dimensionality reduction yielding a low-dimensional space called eigenspace. The training speakers are then represented as points or distributions in eigenspace. Thereafter, new speech data from the test speaker is placed into eigenspace through a similar linear transformation and the proximity in eigenspace of the test speaker to the training speakers serves to authenticate or identify the test speaker.

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