Speech event detection by non negative matrix deconvolution

Support Vector Machines (SVM) are applied to the problem of detecting and classifying broad acoustic-phonetic classes (events). In this paper an approach based on Non-Negative Matrix Deconvolution (NMD) is proposed to merge frame-based SVM predictions into segmental events. To turn the SVM outputs, which are frame-based, into a signal segmented in terms of events, two different event merger methods were tested and the results, using TIMIT speech data, were compared to a broad class detector, built using HMMs with an MFCC front-end. Results show that NMD efficiently controls the number of insertion and deletion errors and outperforms HMM's accuracy. The quality of the event segmenter was measured by means of a recently proposed methodology to evaluate event detectors performance and the results show that the proposed approach also outperforms the competing ones.