Template-based and HMM-based Approaches for Isolated Spanish Digit Recognition
Lucas D. Terissi, Juan Carlos Gómez · INTELIGENCIA ARTIFICIAL · 2006
"Isolated word recognition is usually performed by two diferent approaches, viz., Conventional Templatebasedand Hidden Markov Models (HMM)-based. A comparison between these approaches for isolated digitrecognition (in Spanish language) is performed in this paper. For the template-based approach, severalDynamic Time Warping algorithms are proposed and implemented in a Matlab environment, while for theHMM-based approach, the algorithms available in a freeware toolbox has been employed. The algorithmsare tested on a database collected during a Course on Digital Processing of Speech Signals at the Universityof Rosario. The test results show that a better performance can be obtained with a HMM-based digitrecognizer."