Patent · US Expired

Method and apparatus for removing noise from feature vectors

US6985858B2 · kind B2 · utility

169Cited by
7References
8Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMar 20, 2001
Grant dateJan 10, 2006
Priority date
Expiry dateJun 17, 2023

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L15/20
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method and computer-readable medium are provided for identifying clean signal feature vectors from noisy signal feature vectors. The method is based on variational inference techniques. One aspect of the invention includes using an iterative approach to identify the clean signal feature vector. Another aspect of the invention includes using the variance of a set of noise feature vectors and/or channel distortion feature vectors when identifying the clean signal feature vectors. Further aspects of the invention use mixtures of distributions of noise feature vectors and/or channel distortion feature vectors when identifying the clean signal feature vectors. Additional aspects of the invention include using a variance for the noisy signal feature vector conditioned on fixed values of noise, channel transfer function, and clean speech, when identifying the clean signal feature vector.

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