總體經驗模態分解及其平行化處理應用在強健性語音辨識 = Robust S...
國立高雄大學資訊工程學系碩士班

 

  • 總體經驗模態分解及其平行化處理應用在強健性語音辨識 = Robust Speech Recognition by Ensemble Empirical Mode Decomposition and its Parallel Processing
  • 紀錄類型: 書目-語言資料,印刷品 : 單行本
    並列題名: Robust Speech Recognition by Ensemble Empirical Mode Decomposition and its Parallel Processing
    作者: 朱嘉平,
    其他團體作者: 國立高雄大學
    出版地: [高雄市]
    出版者: 撰者;
    出版年: 2012[民101]
    面頁冊數: 75面圖,表格 : 30公分;
    標題: 語音辨識
    標題: Speech Recognition
    電子資源: http://handle.ncl.edu.tw/11296/ndltd/77448005410503425631
    附註: 106年10月31日公開
    附註: 參考書目:面64-66
    摘要註: 本論文主要目的是提升語音信號的抗雜訊能力以提升在具有環境雜訊下的語音辨識率。本論文應用總體經驗模態分解法(Ensemble Empirical Mode Decomposition, Ensemble EMD),將含雜訊的語音訊號分解成多組本質模態函式(Intrinsic Mode Functions, IMFs),並以實數型基因演算法找出最佳IMFs組合參數,再將分離出之IMFs依組合參數還原成語音,還原最理想的語音信號,讓環境噪音影響語音的辨識率降到最低。此外,針對總體經驗模態分解法所造成的運算速度的問題,本論文提出平行化運算來加速總體經驗模態分解法的運算速度,在多核心系統的架構下,結合OpenMP函式庫平行指令針對總體經驗模態分解法做平行化處理使運算速度提升。 The main purposes of this study were to enhance and improve the speech recognition rate of speech recognition systems subject to some environment noise. In our research, we used Ensemble Empirical Mode Decomposition (Ensemble EMD) to decompose the speech signals with noise to several IMFs, and then find the best weights for each IMF by using real-coded genetic algorithm. Thereafter, the speech signals were recovered by summing the weighted IMFs to reduce the effect of the noise. Since the Ensemble EMD will take much computation time, a parallel computation algorithm under multi-core structure is proposed to speed up the computation of Ensemble EMD. We used parallel instruction coding in the OpenMP library to implement our algorithm.
評論
Export
取書館別
 
 
變更密碼
登入