A multivariate speech activity detector based on the syllable rate

Computationally efficient speech extraction algorithms have significant potential economic benefit, by automating an extremely tedious manual process. Previously, algorithms which discriminate between speech and one specific other signal type have been developed , and often fail when the specific non-speech signal is replaced by a different signal type. Moreover, several such signal specific discriminators have been combined in order to tackle the general speech vs. non-speech discrimination problem, with predictable negative results. When the number of disriminating features is large, compression methods such as Principal Components have been applied to reduce dimension, even though information may be lost in the process. In this paper, graphical tools are applied to determine a set of features which produce excellent speech vs. non-speech clustering. This cluster structure provides the basis for a general speech vs. non-speech discriminator, which significantly outperforms the TALKATIVE speech extraction algorithm.