Sequential k-nearest neighbor pattern recognition for usable speech classification

Abstract

The accuracy of speech processing techniques degrades when operating in a co-channel environment. Co-channel speech occurs when more than one person is talking at the same time. The idea of usable speech segmentation is to identify and extract those portions of co-channel speech that are minimally degraded but still useful for speech process-ing application such as speaker identification. Usable speech measures are features that are extracted from the co-channel signal to distinguish between usable and unusable speech. In this paper, a new usable speech extraction technique is pre-sented. The new method extracts features recursively and variable length segmentation is performed by making se-quential decisions on the k-NN pattern classifier class assign-ments. This new approach is able to identify 79 % of available usable speech segments with 21 % false alarms and it requires lesser amount of data to make accurate decisions compared to previously presented methods.