Chrome Extension
WeChat Mini Program
Use on ChatGLM

汉语连续语音识别系统中三音子模型的优化

Application Research of Computers(2013)

Cited 2|Views7
No score
Abstract
为了更准确地估计状态聚类前有调三音子的模型参数,从而提高聚类后捆绑状态的精度及系统的识别性能,针对汉语连续语音识别中,有些有调三音子的训练样本数非常少,而其对应的无调三音子的训练样本数相对较多的情况,提出用其对应的无调三音子的模型参数进行初始化,并用最大后验概率准则训练模型。汉语大词汇量连续语音识别实验表明,该方法可以提高训练语料中稀疏三音子聚类前的模型精度,从而提高系统的识别性能。
More
Translated text
Key words
decision tree-based clustering,initials and finals,triphone model,maximum a posteriori(MAP)
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined