Title :
Chinese monosyllable recognition based on initial-final segmentation
Author :
Jinpei, Xu ; Ziyun, Yang ; Zongxian, Sha
Author_Institution :
Harbin Inst. of Technol., China
Abstract :
A Chinese monosyllable recognition approach using initial-final segmentation, segmental vector quantization, and separate matching is developed for improving recognition performance. Preliminary experiments showed the effectiveness of this approach. A correct recognition rate of 83.9% for the first candidate and 96.0% for the first three candidates has been obtained for the vocabulary of all 403 Chinese monosyllables without tone
Keywords :
speech recognition; Chinese monosyllable recognition; initial-final segmentation; segmental vector quantization; separate matching; speech recognition; toneless monosyllables; Band pass filters; Cepstral analysis; Cepstrum; Digital signal processors; Signal analysis; Signal processing algorithms; Signal sampling; Speech recognition; Vector quantization; Vocabulary;
Conference_Titel :
Pattern Recognition, 1988., 9th International Conference on
Conference_Location :
Rome
Print_ISBN :
0-8186-0878-1
DOI :
10.1109/ICPR.1988.28404
