Please use this identifier to cite or link to this item:
標題: 利用Multiple Common Vector 及 Dynamic Time Warping於特定語者中文單音辨識
Using the Method of Multiple Common Vector and Dynamic Time Warping to Recognize Isolated Mandarin Word for Speaker-Dependent System
作者: 林子傑
Lin, Tzu-Chieh
關鍵字: Common Vector;共同向量;Principal Component Analysis;Dynamic Time Warping;主成份分析;動態時間軸校正法
出版社: 應用數學系所
引用: [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.
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.
其他識別: U0005-3006200814113800
Appears in Collections:應用數學系所

Show full item record

Google ScholarTM


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