Title :
Language identification using vector quantization
Author :
Dan, Qu ; Bingxi, Wang ; Xin, Wei
Author_Institution :
Dept. of Inf. Sci. of Inf. Eng., Zhengzhou Univ., Henan, China
Abstract :
When compared with speech technologies in speech processing, automatic language identification is a relatively new yet difficult problem. In this paper, two language identification algorithms are provided and some experiments are conducted using OGI-TS telephone speech corpus. Then experiments results are described. It is shown that the optimal recognition rates for the two algorithms are 65.38% and 73.08%, respectively.
Keywords :
speech recognition; vector quantisation; OGI-TS telephone speech corpus; language identification; optimal recognition rates; vector quantization; Banking; Emergency services; Information retrieval; Information science; Natural languages; Speech enhancement; Speech processing; Speech recognition; Telephony; Vector quantization;
Conference_Titel :
Signal Processing, 2002 6th International Conference on
Print_ISBN :
0-7803-7488-6
DOI :
10.1109/ICOSP.2002.1181100
