(3.235.25.169) 您好！臺灣時間：2021/04/17 20:38

### 詳目顯示:::

:

• 被引用:3
• 點閱:110
• 評分:
• 下載:0
• 書目收藏:0
 本篇論文主要是探討50個國字單音的辨識，首先利用主成份分析與共同向量的關係來建構出語音模型，之後在辨識比對的部分，我們將時間的因素考慮進去，所以試著加入動態時間軸校正法，觀察其能否提升辨識率；包括了動態時間軸校正法，本論文討論的其他四個實驗因子：「音框數」、「分群數」、「特徵向量個數」及「語音特徵參數」，希望能找出在何種情況下50個字能具有不錯的鑑別度。而本論文的實驗結果，辨識50個字時，最高辨識率可達97.33 %
 This paper is to discuss the speech recognition of 50 isolated mandarin words. First, we use the relationship between principal component analysis and common vector to construct the speech model. Then we will take into account the time factor and attempt to join the dynamic time warping to improve the rate of recognition. Including dynamic time warping, we also consider the other four experimental factors in this paper: "the number of frame", "the number of cluster", "the number of eigenvector", and "speech feature extraction". We hope to find out which circumstances for the recognition of 50 words would be the best. And the maximum rate of recognition attains 97.33 % on the 50 words.
 目錄中文摘要...........................................................Ⅰ英文摘要...........................................................Ⅱ目錄...............................................................Ⅲ圖目錄............................................................ Ⅴ表目錄............................................................ Ⅵ第一章 緒論..................................................................................................................11-1研究動機與目的........................................................................................11-2研究方向....................................................................................................11-3辨識流程概述............................................................................................21-3-1語音前處理.......................................................................................2 1-3-2求取特徵參數...................................................................................3 1-3-3訓練語音模型...................................................................................4 1-3-4比對辨識...........................................................................................51-4論文架構......................................................................................................5第二章 語音訊號的前處理與特徵值的求取.............................................................72-1 前言..........................................................................................................72-2語音的前處理...........................................................................................7 2-2-1 數位化取樣.................................................................................7 2-2-2 常態化.........................................................................................82-2-3語音端點偵測..............................................................................92-2-4切割音框......................................................................................92-2-5預強調........................................................................................102-2-6視窗化........................................................................................102-3特徵值的求取………………………………………………..………...12第三章 語音模型的建立與辨識方法........................................................................143-1 前言........................................................................................................143-2音框的壓縮與擴張.................................................................................143-3 K-means分群法......................................................................................153-4多重共同向量.........................................................................................17 3-4-1共同向量…………………………………………………………18 3-4-2共同向量與主成份分析的關係…………………………………183-5辨識的方法.............................................................................................193-5-1待測語音的處理……………………………………………........193-5-2 比對的方法………..…………………………….........................203-5-3動態時間軸校正法………….…………………………....……...20第四章 實驗操作流程與實驗結果..........................................................................254-1操作介面.................................................................................................254-2實驗流程.................................................................................................254-2-1語音來源.......................................................................................254-2-2影響辨識率的可能因素………………………………………...254-2-3辨識結果………………………………………………………...26第五章 結論與建議....................................................................................................37參考文獻......................................................................................................................38附錄..............................................................................................................................40附圖目錄圖1.1語音訊號前處理流程圖......................................................................................3圖1.2求取特徵參數流程圖..........................................................................................3圖1.3語音模型建立流程圖..........................................................................................4圖1.4辨識流程圖..........................................................................................................5圖2.1語音類比訊號圖..................................................................................................7圖2.2語音數位訊號圖..................................................................................................7圖2.3原始語音「光」的波形圖..................................................................................8圖2.4經過常態化後，語音「光」的波形圖..............................................................8圖2.5切割音框示意圖................................................................................................10圖2.6視窗函數比較圖................................................................................................11圖3.1 音框壓縮過程圖..............................................................................................14圖3.2 音框擴張過程圖..............................................................................................15圖3.3原始資料分佈圖................................................................................................16圖3.4經K-means後的資料圖...................................................................................16圖3.5多重共同向量法流程圖....................................................................................17圖3.6理想狀況之動態程序........................................................................................21圖3.7整體搜尋路徑限制............................................................................................22圖3.8區域路徑限制一................................................................................................22圖4.1特徵參數為「倒頻譜參數加差倒頻譜參數」之下不同因素影響之辨識率比較圖..............................................................................................................................33圖4.2特徵參數為「倒頻譜參數」之下不同因素影響之辨識率比較圖...............34圖4.3不同的特徵參數影響下之辨識率比較圖.......................................................35附表目錄表3.1 區域路徑限制圖..............................................................................................24表4.1音框數=10，分群數=1之辨識率....................................................................27表4.2音框數=10，分群數=2之辨識率....................................................................28表4.3音框數=20，分群數=1之辨識率....................................................................29表4.4音框數=20，分群數=2之辨識率......................................................................30表4.5音框數=10，分群數=1之辨識率....................................................................31表4.6音框數=10，分群數=2之辨識率....................................................................31表4.7音框數=20，分群數=1之辨識率....................................................................32表4.8音框數=20，分群數=2之辨識率......................................................................32表4.9擴充字彙之辨識率............................................................................................36
 [1]王小川(2004)， “語音訊號處理”，台北市：全華。[2]王國榮(2000)，“Visual Basic 6.0 實戰講座 ”，台北巿：旗標。[3]李宗寶，黎自奮，楊茗惠(2003)，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系，台中。[4]李宗寶，張國清(2005)， “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。[5]李宗寶，吳宗憲(2005)， “探討K-means之共同向量法應用於國語數字辨識”，碩士論文，國立中興大學應用數學研究所，台中。[6]李宗寶，林靖剛(2006)， “利用Multiple Common Vector 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。[7]吳明哲，黃世陽(1998)， “Visual Basic 6.0 中文版學習範本”，台北市：松崗。[8]Angm, H.(1995), “Common vector obtained from linearly independent speech vectors by using LPC parameters,” graduation project, Elect. Electron. Eng. Dept., Osmangazi Univ., Eskisehir, Turkey.[9]Bing, X. and Yihe, S. (1996), “Research on ASIC for multi-speaker isolated word recognition”, ASIC, 2nd International Conference, 21-24, 135-137.[10]Bourouba, H., and Bedda, M. (2004), “HybridapproachDTW/HMMC for the recognition of the isolated Arabic words”, Information and Communication Technologies, 2004 International Conference on, 19-23, 481-482.[11]Chu, Myung-Kyung, and Sohn, Young-Sun (2001), “A User Friendly Interface Operated by the Improved DTW Method”, The 10th IEEE International Conference , 3, 2-5, 1187-1190.[12]Gulmezoglu, M. B., Dzhafarov, V. and Barkana, A.(1999), “ A novel approach to isolated word recognition”, IEEE Trans. On Speech and Audio Processing, vol. 7. No. 6.[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[14]Harb, H., and Husseiny, A.H. (2000), “Isolated words recognition using neural networks”, The 7th IEEE International Conference on, 1, 17-20, 349-351.[15]Keskin, M., Gulmezoglu, M. B., Parlaktuna, O. and Barkana, A. (1996), “Isolated word recognition by extracting personal differences,” in Proc. 6 th Int.Conf. Signal Processing Applications and Technology, Boston, MA , pp.1989-1992.[16]Li, T. F. (2003), “Speech recognition of mandarin monosyllables”, Pattern Recognition 36, 2713-2721.[17]Rabiner, L.R. and Sambur, M.R.(1975), “An algorithm for determining the endpoints of isolated utterances”, The Bell System Technique Journal, Vol.54, pp.297-315.[18]Rabiner, L.R. and Schmidt, C.E.(1980), “Application of Dynamic Time Warping to Connected Digital Recognition,” IEEE Transactions on Acoustics, Speech,and Signal Processing, Vol. 28, pp. 377-388.[19]Sakoe, H. and Chiba, S.(1978), “Dynamic Programming Optimization for Spoken Word Recognition,” IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol. 26, pp. 43-49.[20]Yucel, S.(1996), “Application of Gram-Schmidt orthogonalization method to speech recognition for different noise levels” graduation project, Elect. Electron. Eng. Dept., Osmangazi Univ., Eskisehir, Turkey.
 國圖紙本論文
 推文當script無法執行時可按︰推文 網路書籤當script無法執行時可按︰網路書籤 推薦當script無法執行時可按︰推薦 評分當script無法執行時可按︰評分 引用網址當script無法執行時可按︰引用網址 轉寄當script無法執行時可按︰轉寄

 1 用隱藏式馬可夫方法於頻域特徵之國語數字辨識 2 用K-means之動態時間軸校正法於國語數字之語音辨識 3 利用權重式多重KNN法於中字彙之特定語者中文單音辨識 4 用K-means之共同向量法於國語數字辨識 5 利用Multiple Common Vector於國語數字之語音辨識 6 利用權重式MultipleCommonVector於中字彙之特定語者中文單音辨識 7 探討梅爾頻率倒頻譜係數之特徵擷取對國語子音之影響 8 American Sign Language Recognition Using Principal Component Analysis and Dynamic Time Warping

 無相關期刊

 1 利用混合式及PCA之辨識法於特定語者中文單音辨識 2 利用共同向量法於特定語者中文單音辨識 3 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 4 利用權重式MultipleCommonVector於中字彙之特定語者中文單音辨識 5 利用權重式多重KNN法於中字彙之特定語者中文單音辨識 6 用K-means之動態時間軸校正法於國語數字之語音辨識 7 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 8 具不完整資料的多變量偏斜常態模型之研究 9 用K-means之共同向量法於國語數字辨識 10 用隱藏式馬可夫方法於頻域特徵之國語數字辨識 11 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 12 中文語音辨識系統增進辨識率之策略研究-以地址系統與二、三、四字詞系統為例 13 利用快速演算法估計多變量資料之改變點位置 14 互信網路下安全管理的合作式防禦架構 15 關於σ-limit的Korovkin型近似定理

 簡易查詢 | 進階查詢 | 熱門排行 | 我的研究室