Title :
Connectionist architecture for all Mandarin syllables recognition
Author_Institution :
Dept. of Inf. Syst. & Comput. Sci., Nat. Univ. of Singapore, Singapore
Abstract :
This paper presents a modular connectionist architecture for all Mandarin syllables recognition. The technique used is based on the time-delay neural networks (TDNN). The architecture developed is capable of recognizing all 35 finals, 21 initials and 4 tones of the entire vocabulary of isolated Chinese syllables. Experimental results show a recognition accuracy of 93.9% for the finals, 92.7% for the initials and 99.3% for the tones, giving rise to an overall syllable recognition rate of about 90%
Keywords :
delays; neural net architecture; speech recognition; finals; initials; isolated Chinese syllables; modular connectionist architecture; spoken Mandarin syllables recognition; time-delay neural networks; tones; Computer architecture; Computer science; Electronic mail; Hidden Markov models; Information systems; Modular construction; Neural networks; Speech recognition; Testing; Vocabulary;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.488988
