Non-intrusive estimation of the level of reverberation in speech

Abstract

We show corroborating evidence that, among a set of common acoustic parameters, the clarity index C <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">50</sub> provides a measure of reverberation that is well correlated with speech recognition accuracy. We also present a data driven method for non-intrusive C <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">50</sub> parameter estimation from a single channel speech signal. The method extracts a number of features from the speech signal and uses a binary regression tree, trained on appropriate training data, to estimate the C <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">50</sub> . Evaluation is carried out using speech utterances convolved with real and simulated room impulse responses, and additive babble noise. The new method outperforms a baseline approach in our evaluation.