(34.204.201.220) 您好!臺灣時間:2021/04/19 17:13
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:張富傑
研究生(外文):Chang Fu Chieh
論文名稱:AMDF的音調擷取方法
論文名稱(外文):AMDF-based pitch tracking algorithm
指導教授:蘇順豐
學位類別:碩士
校院名稱:國立臺灣科技大學
系所名稱:電機工程系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2004
畢業學年度:92
語文別:英文
中文關鍵詞:音調週期性信號切音雜訊比
外文關鍵詞:pitchharmonic signalvoiced segmentSNRAMDF
相關次數:
  • 被引用被引用:1
  • 點閱點閱:329
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
“音調” 在語音分析上是一個很重要的參數, 無論是在語音壓縮, 語音合成, 語言辨認, 或是語料辨識都有著舉足輕重的地位. 帶有良好的音調資訊系統往往有著較高的系統準確度. 本篇論文將引用一個普遍認同的方法來擷取音調資訊,名為AMDF(Average Magnitude Different Function). 然而, 在AMDF演算法裡有著一些問題, 會造成音調擷取的誤差, 這裡我們也提及了幾個改良的AMDF 方法, 我們將看到前人是如何將原本的問題做改善. 再來會介紹我們所提出的改良式-AMDF方法, 最後將這幾個以AMDF 方法為底的演算法做比較. 而”有聲/無聲”的後端應用也會被提及.
Pitch period is a key feature in speech compression, synthesis, language identification and speech recognitions. With better pitch estimation result in better accuracy. The AMDF algorithm is the most efficient and easiest way of estimating pitch contour in the time domain. However, Due to the falling trend of AMDF curves, it is easy to estimate pitch in doubled or halved. To avoid these errors, several algorithms based on AMDF are discussed and compared. These algorithms need to increase its complexity or to add some useful skills to improve the accuracy of the estimated pitch information. Here an improved-AMDF algorithm named Cross-AMDF is developed and proposed. Finally, its application for voiced / unvoiced segment is also presented.
Abstract………………………………………………………………………………..I
Special thanks……………………………………………………………………….III
Contents……………………………………………………………….…………….IV
List of Figure & Table………………………………………………………………VI
Chapter 1 Introduction
1-1 Motivation…………………………………………………………………….1
1-2 Background…………………………………………………………………...2
1-3 The Structure of This Paper…………………………………………………..4
Chapter 2 Speech Processing
2-1 The Generation of Voice………………………………………………………5
2-2 Introduction to Speech Recognition System…………………………………..6
2-3 Feature Extraction of Speech Processing……………………………………...7
2-4 Windowing…………………………………………………………………...11
2-5 Pre-emphasis of Speech Signal………………………………………………13
2-6 Smoothing……………………………………………………………………14
2-7 Signal to Noise Ratio………………………………………………………...16
Chapter 3 Review of Pitch Tracking Algorithms
3-1 Time-domain Pitch Tracking Methods……………………………………….18
3-2 Frequency-domain Pitch Tracking Methods…………………………………22
3-3 Modeling-based Pitch Tracking Methods……………………………………24
3-4 Discussions on the Above-Mentioned Methods……………………………..26
Chapter 4 AMDF-based Algorithms for Pitch Estimation
4-1 AMDF-based Algorithms…………………………………………………….28
4-1-1 AMDF………………………………………………………………….28
4-1-2 LV-AMDF……………………………………………………………...30
4-1-3 CAMDF………………………………………………………………..31
4-1-4 A Probability Approach to AMDF method…………………………….33
4-2 The Proposed Algorithm: Cross_AMDF…………………………………….34
Chapter 5 Performance Comparison
5-1 Procedures of Experiment……………………………………………………40
5-2 Computer Simulation………………………………………………………...43
5-2-1 Time-cost Comparison………………………………………………..45
5-2-2 Accuracy……………………………………………………………...45
5-2-3 Advantages for Rear-end applications………………………………..46
5-2-4 Simulation in different SNR environment……………………………48
IV
5-3 Rear-end Applications………………………………………………………..50
Chapter 6 Conclusions and Future Work…………………………………………53
Reference…………………………………………………………………………….55
[1] M. Ross, H. Schafer, A. Cohen, R. Freuberg and H. Manley, “Average magnitude difference function pitch tractor”, IEEE trans. ASSP, ASSP-22, 353-362, 1974.
[2] Wenyao Zhang, Gang Xu, Yuguo Wang, “Pitch estimation based on circular AMDF”, Acoustics and signal processing on IEEE international conference, volume: 1, 13-17 Page(s): I-341 -I-344 vol.1, 2002.
[3] Gin-Der Wu and Chin-Teng Lin, ”Word boundary detection with Mel-scale frequency bank in
noisy environment”, IEEE Trans, Speech and Audio Processing Volume: 8 Issue: 5,
Page(s): 541 —554, Sept. 2000.
[4] E. Barnard, R.A. Vea, M.P. Alleva, ” Pitch detection with a neural-net classifier”,
IEEE Trans, Signal Processing, Volume: 39 Issue: 2 Page(s): 298 —307, 1991.
[5] Li. B.N.L, Liu. J.N.K., ” A comparative study of speech segmentation and feature extraction on
the recognition of different dialects”, Conference Proceedings on IEEE International Conference,
Volume: 1, 12-15 Page(s): 538 -542 vol.1, Oct. 1999.
[6] S.A. Samad, A. Hussain, Low Kok Fah, ” Pitch detection of speech signals using the cross-correlation technique” , Proceeding on IEEE international conference , Volume: 1 , 24-27 Page(s): 283 -286 vol.1, 2000.
[7] T. Yao, “Digital speech processing”, Shanghai: East China University of Science and Technology
Press, 1992.
[8] L. Gu and R. Liu, “High-Performance Mandarin Pitch Estimation,” Journal of Electronics, vol. 27, pp. 8-11, 1999.
[9] G.S. Ying, L.H. Jamieson, C.D. Michell, “A probabilistic approach to AMDF pitch detection,” ICSLP 96. Proceedings on Fourth International Conference, Volume: 2, 3-6 Page(s): 1201 -1204 vol.2, 1996.
[10] K Kasi, S.A Zahorian, “Yet another algorithm for pitch tracking”, Acoustics, Speech, and Signal Processing on IEEE International Conference, Volume: 1 , 13-17 Page(s): I-361 -I-364 vol.1, 2002.
[11] Kim Hyung Lae, Kim Dae Ho, Ryu Young Sik, Kim Yung Kwon, “A study on pitch detection using local peak and valley for Korean speech recognition”, Digital Signal Processing Applications, Volume: 1, 26-29 Nov. Page(s): 107 -112 vol.1, 1996.
[12] R. W. Schafer and L. R. Rabiner, “System for automatic formant analysis of voiced speech,” JNL, Acoust. Soc. Amer., vol. 47, pp. 634-648, Feb. 1970.
[13] C. A. McGonegal, L. R. Rabiner, and A. E.Rosenberg, “A semi-automatic pitch detector” (SAPD),”IEEE Trans. Acoust, Speech, signal Processing, vol. ASSP-23, pp. 570-574, 1986
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔