本論文主要的目標為研究語音辨識相關技術，並加以實現出一套可移植性高、靈活性強、實用性好及辨識率佳的語音關鍵詞辨識擷取系統，此系統主要由三大部份構成，分別為語料讀取程式及關鍵詞語音擷取程式作業於Windows XP SP2作業系統下，以Borland C++ Builder 5為主要開發平台，語音關鍵詞辨識程式作業於Linux Fedora 5作業系統下，使用HTK 3.3工具進行開發。 在此系統中我們使用HTK工具開發HMM來建立聲學模型，並以21個聲母、36個韻母所組成的411個音節，訓練出一個以HMM狀態數、高斯混合數分別為6、17的最佳聲學模型，其訓練語料擷取率高達92%，假警報率低於13%。在進行非訓練語料實驗時，純關鍵詞模組其擷取率及假警報率更是維持僅各差約3%，分別為89%及16%。 最後以HMM狀態數、高斯混合數分別為6、17的聲學模型建構一套語音關鍵詞辨識擷取系統，並設計其介面程式提供使用者便於操作。 This paper’s goal is to research voice reorganization technique and to develop a speech keyword spotting system which can be working on any operation system and have the feature of probability and easy to use. This system are consist of three part, voice data reading program and keyword spotting program are working in the Microsoft Windows XP SP system, and develop platform is Borland C++ Builder 5. Speech keyword reorganization program is developed by HTK 3.3 and working in the Linux Fedora 5system. In this system we use HTK to develop HMM and to build the acoustics model, and we use 411 syllables which is build by 21 initials and 36 finals to develop a acoustics model which HMM state and mixtures is 6 and 17. In this model the training speech detection ratio must reach 92%, false alarm rate must under 13%. In the practical keywod model speech material input experiment, the differential between detection ratio and false alarm ratio keep in 3%, and detection ratio must reach 89%, false alarm rate under 16%. Finally we will use this model to build a speech keyword spotting reorganization system, and we will design a human interface program to provide to the operator, so that they can easy to use this system.
