A vector quantizer classifier for blind signal to noise ratio estimation of speech signals

Russell Ondusko, Matthew Marbach, Ravi P. Ramachandran, Linda M. Head, Mark C. Huggins

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations


A blind approach for estimating the signal to noise ratio (SNR) of a speech signal corrupted by additive noise is proposed. The method is based on a pattern recognition paradigm using various linear predictive based features and a vector quantizer classifier. Blind SNR estimation is very useful in speaker identification systems in which a confidence metric is determined along with the speaker identity. The confidence metric is partially based on the mismatch between the training and testing conditions of the speaker identification system and SNR estimation is very important in evaluating the degree of this mismatch. The aim is to correctly estimate SNR values from 0 to 30 dB, a range that is both practical and crucial for speaker identification systems. Additive white Gaussian noise is investigated. The best features are the line spectral frequencies, reflection coefficients and the log area ratios. The linear predictive cepstrum also shows great promise. The average SNR estimation error is 1.6 dB.

Original languageAmerican English
Title of host publicationISCAS 2006
Subtitle of host publication2006 IEEE International Symposium on Circuits and Systems, Proceedings
Number of pages4
StatePublished - 2006
EventISCAS 2006: 2006 IEEE International Symposium on Circuits and Systems - Kos, Greece
Duration: May 21 2006May 24 2006

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems


OtherISCAS 2006: 2006 IEEE International Symposium on Circuits and Systems

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this