An investigation into the relative speaker verification performance of various types of vector quantisation (VQ) and dynamic time warping (DTW) classifiers is presented. The study covers a number of algorithmic issues involved in the above classifiers, and examines the effects of these on the verification accuracy. The experiments are based on the use of a subset from the Brent (telephone quality) speech database. This subset consists of repetitions of isolated digit utterances 1 to 9 and zero. The paper describes the experimental work, and presents an analysis of the results.
|Title of host publication||In: Procs of the European Conf on Security and Detection, 1997 ( ECOS'97)|
|Publisher||Institute of Electrical and Electronics Engineers (IEEE)|
|Publication status||Published - 1997|