Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/18714
標題: 利用音框移動之比較方法於中字彙之特定語者中文單音辨識
Using the Method of shifting frames to Recognize Isolated Mandarin Word for Speaker-Dependent System
作者: 歐陽杰璋
Yang, Chieh-Chang Oh
關鍵字: the shifting frames of the K-nearest neighbor
音框移動之K-最近鄰居法
出版社: 統計學研究所
引用: [1]. 王小川。“語音訊號處理”。臺北市:全華,2004。 [2]. 王國榮。“Visual Basic 6.0 實戰講座”。臺北巿:旗標,2000。 [3]. 吳明哲,黃世陽。“Visual Basic 6.0中文版學習範本”。臺北市:松崗,1998。 [4]. 陳明熒。“PC電腦語音辨認實作”。旗標書局,1994。 [5]. 李蕙珺,李宗寶。“利用權重式第K位最鄰近方法於中字彙之特定語者中文單音辨識”。碩士論文,國立中興大學應用數學研究所,台中,2009。 [6]. 張國清,李宗寶。“用K-means之動態時間軸校正法於國語數字之語音辨識”。 碩士論文,國立中興大學應用數學研究所,台中,2005。 [7]. 陳首鳴,李宗寶。“利用權重式Multiple Common Vector於中字彙之特定語者中文單音辨識”。碩士論文,國立中興大學應用數學研究所,台中,2009。 [8]. 楊茗惠,黎自奮,李宗寶。“用隱藏式馬可夫方法於頻域特徵之國語數字辨識”。碩士論文,國立中興大學應用數學研究所,台中,2003。 [9]. 籃元隆,李宗寶。“利用權重式多重KNN法於中字彙之特定語者中文單音辨識”。碩士論文,國立中興大學應用數學研究所,台中,2009。 [10]. 羅璟義,李宗寶。“利用權重式共同向量法於中字彙之特定語者中文單音辨識”。碩士論文,國立中興大學應用數學研究所,台中,2009。 [11]. Cover, T.M. and Hart, P.E. “Nearest neighbor Pattern Classification”, IEEE Trans. On Information Theory, vol. 13, no. 1, pp. 21-27, 1967. [12]. Gulmezoglu, M. B., Dzhafarov, V. and Barkana, A.. “A novel approach to isolated word recognition”, IEEE Trans. On Speech and Audio Processing, vol. 7, no. 6, pp. 620-627, 1999. [13]. Gulmezoglu, M. B., Dzhafarov, V. and Barkana, A.. “The common vector approach and its relation to principal component analysis”, IEEE Trans. On Speech and Audio Processing, vol. 9, no. 6, pp. 655-662, 2001. [14]. Higgins, A.L., Bahler, L.G.. and Porter, J.E.. “Voice identification using nearest-neighbor distance measure”, ICASSP, vol. 2, pp. 375-378, 1993. [15]. Tran, T.N., Wehrens, R. and Buydens, L.M.C.. “KNN-kernel density-based clustering for high-dimensional multivariate data”, Computational Statistics and Data Analysis, vol. 51, pp. 513-525, 2006.
摘要: 本篇論文主要是探討337個國語單字的特定語者之單音辨識。首先將337個國語單字分別錄製十次,將其存置資料庫中。錄完之後,針對語音作前處理,再求取其特徵參數。 有了特徵參數之後,先利用前後權重為(0,1)找出母音為何;再利用找出的母音,配合音框移動之K-最近鄰居法所找出的最佳音框移動值,將待測語音與訓練語音做比對,藉此判斷測試語音為哪個國語單字。 在本實驗中,辨識337個國語單字的母音時,會將音框移動分成三種來探討,分別是移動0單位、移動1單位、移動2單位。而三種情形中,以音框移動0單位的辨識率為最好,其Top1為98.02%,整體的最高辨識率則為89.81%。
This paper is to discuss the speech recognition of 337 isolated mandarin words for speaker-dependent and use the method of shifting frames to recognize. First, I record the 337 isolated mandarin words ten times, and save them to speech database. After recording, I focus the speech database on pre-processing, and then through the linear prediction coding, the cepstrum coding to obtain the speech features. With the speech features, I use the weight (0,1) to find out the vowel. And then, I use the vowel with the optimum shifting frames of the K-nearest neighbor to find the test will belong to which isolated mandarin words. In this experiment, it will be divided into three types of shifting frames to recognize the 337 mandarin words in the vowel, move 0 units, move 1 units, move 2 units, respectively. The best recognition rate of three types of shifting frame is to move 0 units. The recognition rate of Top1 is 98.02% and the highest overall recognition rate is 89.81%.
URI: http://hdl.handle.net/11455/18714
文章連結: http://www.airitilibrary.com/Publication/alDetailedMesh1?DocID=U0005-2307201015063300
Appears in Collections:統計學研究所

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.