Title :
Improving discriminability among acoustically similar words by modified distance metric
Author :
Kim, Hak S. ; Lin, Ching-Kai
Author_Institution :
Korea Adv. Inst. of Sci. & Technol., Seoul
fDate :
2/4/1988 12:00:00 AM
Abstract :
In a template-matching based speech recognition system excessive weight given to perceptually unimportant spectral variations is undesirable for discriminating among acoustically similar words. By introducing a simple threshold-type nonlinearity applied to the distance metric, the word recognition performance can be improved for a vocabulary with similar sounding words, without modifying the system structure
Keywords :
spectral analysis; speech recognition; acoustically similar words; discriminability; modified distance metric; spectral variations; system structure; template-matching based speech recognition system; vocabulary; weight;
Journal_Title :
Electronics Letters
