Development of large vocabulary continuous speech recognition system for Mongolian language
Development of large vocabulary continuous speech recognition system for Mongolian language
复制标题
DOI：
--
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
S. Nakagawa;Erdenebat Turmunkh;Hiroshi Kibishi;Kengo Ohta;Yasuhisa Fujii;Masatoshi Tsuchiya;Kazumasa Yamamoto
中科院分区：
文献类型：
--
作者：
S. Nakagawa;Erdenebat Turmunkh;Hiroshi Kibishi;Kengo Ohta;Yasuhisa Fujii;Masatoshi Tsuchiya;Kazumasa Yamamoto
我们开发了一个蒙古语大词汇量连续语音识别系统（LVCSR）。它是蒙古国喀尔喀方言的第一个LVCSR系统。首先，我们建立了蒙古语语音语料库，该语料库包含40名男性说话人的700个不同句子中的6000多个话语，然后我们建立了基于单音素和三音素的Hyns。次要的，音素，morphone和单词为基础的n-gram语言模型准备使用600万字的文本语料库。最后，我们进行了连续语音识别实验，得到的音素正确率分别为56%和67%的单音素HSPER和三音素HSPER。我们还获得了63%和68%的单词正确率，分别使用单音Hyns和单词为基础的三元组和三音Hyns和单词为基础的三元组。
We developed a large vocabulary continuous speech recognition system(LVCSR) for Mongolian language. It is the first LVCSR system of Khalkha dialect in Mongolia. Firstly, we created Mongolian speech corpus for acoustic model and it contains over 6000 utterances in total recorded from 700 different sentences spoken by 40 male speakers, and then we created monophone and triphone based HMMs. Secondary, phoneme, morphone and word based n-gram language models were prepared by using 6 million words in a text corpus. Finally, we conducted continuous speech recognition experiments and obtained the phoneme correct rates of 56% and 67% by using monophone HMMs and triphone HMMs, respectively. We also obtained the word correct rates of 63% and 68% by using monophone HMMs & word based trigram and triphone HMMs & word based trigram, respectively.