Title :
Adaptive template method for speech recognition
Author :
Liu, Yadong ; Lee, Yee-Chun ; Chen, Hsing-Hen ; Sun, Guo-Zheng
Author_Institution :
Dept. of Phys., Maryland Univ., College Park, MD, USA
fDate :
31 Aug-2 Sep 1992
Abstract :
An adaptive template method for pattern recognition is proposed. The template adaptation algorithm is derived based on minimizing the classification error of the classifier. The authors have applied this method to a multispeaker English E-set recognition experiment and achieved a 90.38% average recognition rate with only one template for each letter. This indicates that the derived templates are able to capture the speaker-invariant features of speech signals
Keywords :
speech recognition; classification error; multispeaker English E-set recognition; speaker-invariant features; speech recognition; speech signals; template adaptation algorithm; Adaptive systems; Clustering algorithms; Educational institutions; Pattern recognition; Physics; Spatial databases; Speech analysis; Speech recognition; Sun; Vocabulary;
Conference_Titel :
Neural Networks for Signal Processing [1992] II., Proceedings of the 1992 IEEE-SP Workshop
Conference_Location :
Helsingoer
Print_ISBN :
0-7803-0557-4
DOI :
10.1109/NNSP.1992.253703
