高解析度之国语类音素单元端点自动标示Sample.pdf

高解析度之國語類音素單元端點自動標示高解析度之國語類音素單元端點自動標示 高解析度之國語類音素單元端點自動標示高解析度之國語類音素單元端點自動標示 Sample-based Phone-like Unit Automatic Labeling in Mandarin Speech 林宥余 You-Yu Lin 國立交通大學電信工程研究所 Institute of Communication Engineering, National Chiao Tung University rossi0927.cm97g@.tw 王逸如 Yih-Ru Wang 國立交通大學電信工程研究所 Institute of Communication Engineering, National Chiao Tung University yrwang@.tw 摘要 在本論文中提出一種以取樣點為單位(sample-based)的高時間解析度之音素端點自 動標示與切割的方法，有別於傳統分析語音信號以音框為單位(frame-based)或是音段為 單位(segment-based)的研究。本文中，我們提出了一些以取樣點為單位的聲學參數；由 實驗結果顯示，這些聲學參數在不同發音特徵之音素轉換間有明顯的變化率，有利於音 素切割位置之標記。我們利用這些發音特徵變化的聲學參數特性，建立一個高時間解析 度的自動音素端點標示與切割系統。由TCC-300國語語料庫進行自動端點標示之實驗結 本論文所提出的方法比傳統以音框為單位之切割方法，亦即HMM之切割方法， 果顯示 ， 更能有效切出精準的短停頓、摩擦音、塞擦音等之音素端點位置。 Abstract This paper presents a sample-based phone boundary detection algorithm which can improve the accuracy of phone boundary labeling in speech signal. In the conventional phone labeling method adopted the frame-based approach, some acoustic features, like MFCCs, are used. And, the statistical approaches are employed to find the phone boundary based on these frame-based features. The HMM-based forced alignment method is most frequently used method. The main drawback of the frame-based approach lies in incapability of modeling rapid changes in speech signal; moreover, the time resolution of this approach is too coarse for some applications. To overcome this problem, a sample-wise phone boundary detection framework is proposed in this study. First, some sample-wise acoustic features are proposed which can