Abstract : this paper applies pattern recognition techniques to th e trouble diagnosis of power electronic circuits , and discusses the establishing of reference pattern , the capturing and processing of characteristic information , the building of rule base and reasoning machine 文摘:將模式識別方法用于電力電子電路的故障診斷,詳細(xì)討論了標(biāo)準(zhǔn)類型的建立方法、特征信息的獲取與處理技術(shù)、規(guī)則庫的建立以及推理機。
Each unit of a speech recognition system is studied in this paper , which includes the preprocessing , the training of reference patterns , the connected digit speech recognition algorithm and the postprocessing of confusing pairs . the research of endpoint detection includes the endpoint detection not only in the quiet environment but also in the low signal - to - noise ( snr ) situation . as far as the training of the reference patterns is concerned , the modified k - means algorithm is adopted . the most important part of this paper is the research of connected speech recognition algorithm . two kinds of algorithm are put forward , which are based on the existing fruit of mutual - information match theory 其次漢語連續(xù)數(shù)字發(fā)音連續(xù)程度較高,這主要由于漢語數(shù)字發(fā)音中零聲母語音出現(xiàn)的較多。另外漢語連續(xù)數(shù)字串中各個數(shù)字的協(xié)同發(fā)音現(xiàn)象較嚴(yán)重也給漢語連續(xù)數(shù)字語音識別帶來了困難。本文以互信息理論為基礎(chǔ),從語音模式間的交互信息量的角度,研究了一個完整的語音識別系統(tǒng)的各個組成部分,其中包括預(yù)處理、參考模式的訓(xùn)練、連續(xù)識別算法以及后續(xù)處理部分。