@article{ZHANG2008, 
author = {Jinsong ZHANG and Takatoshi Jitsuhiro and Hirofumi Yamamoto and Xinhui HU and Satoshi Nakamura},
title = {An Introduction to the Chinese Speech Recognition Front-End of the NICT/ATR Multi-Lingual Speech Translation System},
year = {2008},
journal = {Tsinghua Science and Technology},
volume = {13},
number = {4},
pages = {545-552},
keywords = {mutual information, Chinese speech recognition, phoneme set design, hidden Markov network, minimum description length, successive state splitting, multi-class composite N-grams},
url = {https://www.sciopen.com/article/10.1016/S1007-0214(08)70087-7},
doi = {10.1016/S1007-0214(08)70087-7},
abstract = {This paper introduces several important features of the Chinese large vocabulary continuous speech recognition system in the NICT/ATR multi-lingual speech-to-speech translation system. The features include: (1) a flexible way to derive an information rich phoneme set based on mutual information between a text corpus and its phoneme set; (2) a hidden Markov network acoustic model and a successive state splitting algorithm to generate its model topology based on a minimum description length criterion; and (3) advanced language modeling using multi-class composite N-grams. These features allow a recognition performance of 90% character accuracy in tourism related dialogue with a real time response speed.}
}