A two-level TDNN (TLTDNN) technique for large vocabulary Mandarin final recognition

Author

Poo, Gee-Swee

Author_Institution

Dept. of Inf. Syst. & Comput. Sci., Nat. Univ. of Singapore, Singapore

Volume

7

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

4396

Abstract

A two-level time-delay neural network (TLTDNN) technique has been developed to recognize all Mandarin finals of the entire Chinese syllables. The first level discriminates the vowel-group (a,e,i,o,u,v) and the nasal-group based on nasal ending, (-n,-ng,-others). Orthogonal combination of the two groupings in the first level enables the second level discrimination of all 35 Mandarin finals. The technique was thoroughly tested with 8 sets of 1265 isolated Hanyu pinyin syllables, with 6 sets used for training and 2 sets used for testing. The overall result shows that a high recognition rate of 95.3% for inside testing and 93.9% for outside testing is achievable

Keywords

neural nets; speech recognition; Hanyu pinyin syllables; Mandarin final; nasal-group; speech recognition; two-level time-delay neural network; vowel-group; Computer science; Databases; Information systems; Natural languages; Neural networks; Speech recognition; Testing; Time domain analysis; Vector quantization; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374976

Filename

374976