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

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