(3.231.230.175) 您好!臺灣時間:2021/04/16 02:37
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:沈于中
研究生(外文):SHEN, YU-CHUNG
論文名稱:使用母音諧波頻譜調適之最小控制遞回平均雜訊估測法於語音增強之研究
論文名稱(外文):Estimation of Noise Magnitude Using Minima-Controlled-Recursive-Averaging Algorithm Adapted by Vowel Harmonic for Speech Enhancement
指導教授:陸清達陸清達引用關係
指導教授(外文):Ching-Ta, Lu
口試委員:王玲玲曾崑福陸清達
口試委員(外文):Ling-Ling, WangKung-Fu, TsengChing-Ta, Lu
口試日期:2013-07-25
學位類別:碩士
校院名稱:亞洲大學
系所名稱:資訊傳播學系
學門:傳播學門
學類:一般大眾傳播學類
論文種類:學術論文
論文出版年:2014
畢業學年度:102
語文別:中文
論文頁數:75
中文關鍵詞:雜訊估測諧波調適語音存在機率語音增強最小控制遞回平均估測法
外文關鍵詞:noise estimationharmonic adaptationspeech-presence probabilityspeech enhancementminimum-recursive-controlled averaging
相關次數:
  • 被引用被引用:0
  • 點閱點閱:392
  • 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:12
  • 收藏至我的研究室書目清單書目收藏:0
準確的估測雜訊頻譜強度,可以有效改善語音增強系統的效能,而雜訊估測演算法經常遭遇兩種問題:分別是雜訊頻譜強度低估,導致語音增強語音的殘留雜訊太多,語音仍然吵雜而不夠清晰;另一個問題是雜訊頻譜強度高估,導致增強後的語音失真過大,致使語音訊息的可理解度下降。因此如何準確而有效的估測雜訊頻譜強度,對於改善語音增強處理系統的效能而言,是非常重要的。本文嘗試透過母音諧波頻譜調適(Vowel Harmonic Spectrum Adaptation, VHSA)最小控制遞回平均雜訊估測法(Minima-Controlled-Recursive-Averaging, MCRA),根據不同的雜訊類型、頻譜中雜訊的多寡、及分佈情形不同,將語音存在的機率依據諧波強度作調適,提高語音存在機率的估測準確度,避免產生語音失真,確保增強語音的品質及清晰度;另一方面,也能有效的移除背景雜訊,達到提升語音增強效能的目的。實驗結果證明:本文提出的方法可以有效的提高雜訊強度估測的準確性,而且效能優於最小控制遞回平均雜訊估測法。
Accurately estimating noise magnitude can improve the performance of a speech enhancement system. However, most of noise estimators suffer from either overestimation or underestimation on the noise level. An overestimate on noise will cause serious speech distortion. On the contrary, a great quantity of residual noise will be introduced when noise magnitude is underestimated. Accordingly, how to accurately estimate noise magnitude is important for speech enhancement. In this study, we employ a minima-controlled-recursive -averaging (MCRA) algorithm adapted by vowel harmonics to estimate noise level. A speech-presence probability is adapted by the number of robust harmonics, enabling a vowel spectrum to obtain the value of speech-presence probability approaching unity. The vowel spectra can be well preserved. Consequently, the enhanced speech quality is improved while background noise is efficiently reduced. Experimental results show that the proposed method can accurately estimate noise magnitude and can improve the performance of the MCRA algorithm.
目錄
摘要......................................................................................................I
Abstract ............................................................................................. II
誌謝....................................................................................................III
目錄.....................................................................................................IV
圖目錄...................................................................................................VI
表目錄.................................................................................................VIII
第一章、緒論..................................................................................................................................1
1.1 研究動機與目的..................................................................................1
1.2文獻探討...............................................................................................2
1.3章節結構...............................................................................................5
第二章、單通道語音增強系統與最小控制遞回平均估測法......................................................6
2.1單通道的語音信號.........................................................................................6
2.2語音增強系統架構.........................................................................................7
2.3最小控制遞回平均估測法............................................................................10
第三章、母音諧波頻譜調適最小控制遞回平均(MCRA)雜訊估測法.......................................15
3.1偏移函數..............................................................................................16
3.2基頻估測..............................................................................................18
3.3諧波調適..............................................................................................20
第四章、實驗結果.........................................................................................................................26
4.1 訊雜比改進度..........................................................................................26
4.2語音之聲譜圖...........................................................................................28
4.3 聲音之波形圖..........................................................................................52
第五章、結論與後續研究方向.....................................................................................................64
5.1 結論............................................................................................64
5.2 後續研究....................................................................................64
參考文獻............................................................................................69
簡歷....................................................................................................69
附件一...................................................................................................70
附件二...................................................................................................72
附件三...................................................................................................74
圖目錄
圖 2.1 簡易語音增強系統方塊圖。..............................................................................7
圖 2.2雜訊估測頻譜強度軌跡圖。..............................................................................14
圖 3.1低通濾波器的頻率響應圖。..............................................................................15
圖 3.2偏移函數變化示意圖。.................................................................................16
圖 3.3權重自相關函數軌跡圖。...............................................................................18
圖 3.4基頻頻率估測軌跡圖。.................................................................................19
圖 3.5閾值改變之SNR變化圖。...............................................................................23
圖 3.6閾值改變之SNR變化圖。...............................................................................24
圖 3.7閾值改變之SNR變化圖。...............................................................................25
圖 4.1 語音聲譜圖。受F16戰機座艙雜訊干擾的語音,訊雜比值為0 dB..................................................29
圖 4.2 語音聲譜圖。受F16戰機座艙雜訊干擾的語音,訊雜比值為5 dB..................................................30
圖 4.3 語音聲譜圖。受F16戰機座艙雜訊干擾的語音,訊雜比值為10 dB.................................................31
圖 4.4 語音聲譜圖。受白色雜訊干擾的語音,訊雜比值為0 dB........................................................33
圖 4.5 語音聲譜圖。受白色雜訊干擾的語音,訊雜比值為5 dB........................................................34
圖 4.6 語音聲譜圖。受白色雜訊干擾的語音,訊雜比值為10 dB.......................................................35
圖 4.7 語音聲譜圖。受雞尾酒會雜訊干擾的語音,訊雜比值為0 dB...................................................37
圖 4.8 語音聲譜圖。受雞尾酒會雜訊干擾的語音,訊雜比值為5 dB...................................................38
圖 4.9 語音聲譜圖。受雞尾酒會雜訊干擾的語音,訊雜比值為10 dB.................................................39
圖 4.10 語音聲譜圖。受汽車雜訊干擾的語音,訊雜比值為0 dB.......................................................41
圖 4.11 語音聲譜圖。受汽車雜訊干擾的語音,訊雜比值為5 dB.......................................................42
圖 4.12 語音聲譜圖。受汽車雜訊干擾的語音,訊雜比值為10 dB.....................................................43
圖 4.13 語音聲譜圖。受工廠雜訊干擾的語音,訊雜比值為0 dB.......................................................45
圖 4.14 語音聲譜圖。受工廠雜訊干擾的語音,訊雜比值為5 dB.......................................................46
表目錄
表 3.1各類型噪音母音諧波最佳調適參數修正閾值。.................................................................22
表 4.1六類雜訊的環境,三種訊雜比,經過語音增強後的SNR改善值比較表。.............................27

[1] N. S. Kim and J.-H. Chang, “Spectral enhancement based on global soft decision,” IEEE Signal Processing Letters, vol. 7, pp. 108-110, May 2000.
[2] R. J. McAulay and M. L. Malpass, “Speech enhancement using a soft decision noise suppression filter,” IEEE Transactions on. Acoustics., Speech, and Signal Processing, vol. ASSP-28, pp. 137–145, Apr. 1980.
[3] I. Cohen and B. Berdugo, “Speech enhancement for nonstationary noise environments,” Signal Processing, vol. 81, pp. 2403–2418, Nov. 2001.
[4] J. Meyer, K. U. Simmer, and K. D. Kammeyer, “Comparison of one-and-two-channel noise-estimation techniques,” in Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing, 1997, pp. 137-145.
[5] C. –T. Lu, J. –H. Shen, and K. –F. Tseng, “Speech enhancement using three-step-decision gain factor with optimal smoothing,” International Journal of Electrical Engineering, vol. 18, no. 5, pp. 209-221, Oct. 2011.
[6] C. –T. Lu, “Enhancement of single channel speech using perceptual-decision-directed approach,” Speech Communication, vol. 53, no. 4, pp. 495-507, Apr. 2011.
[7] C. –T. Lu, “Reduction of musical residual noise using block-and-directional-median filter adapted by harmonic properties,” Speech Communication, vol. 58, pp. 35-48, Mar. 2014.
[8] D. Malah, R. V. Cox, and A. J. Accardi, “Tracking speech-presence uncertainty to improve speech enhancement in nonstationary noise environments,” in Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing,1999, pp. 789-792.
[9] H. G. Hirsch and C. Ehrlicher, “Noise estimation techniques for robust speech recognition,” in Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing, 1995, pp. 153-156.
[10] V. Stahl, A. Fischer, and R. Bippus, “Quantile based noise estimation for spectral subtraction and Wiener filtering,” in Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing, 2000, pp. 1875-1878.
[11] R. Martin, “Spectral subtraction based on minimum statistics,” in Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing, 1994, pp. 1182-1185.
[12] R. Martin, “Noise power spectral density estimation based on optimal smoothing and minimum statistics,” IEEE Transactions on Speech, and Audio Processing, vol. 9, no. 5, pp. 504-512, July 2001.
[13] G. Doblinger, “Computationally efficient speech enhancement by spectral minima tracking in subbands,” in Proc.IEEE International Conference on Acoustics, Speech, and Signal Processing, 1995, pp. 1513-1516.
[14] I. Cohen, and B. Berdugo, “Noise estimation by minima controlled recursive averaging for robust speech enhancement,” IEEE Signal Processing Letters, vol. 9, no. 1, pp. 12-15, Jan. 2002.
[15] A. Varga and H. J. M. Steeneken, “Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems,” Speech Communication, vol. 12, no. 3, pp. 247-251, July 1993.
[16] Y. Ephraim and D. Malah, "Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator, " IEEE Transactions on Acoustics, Speech and Signal Processing, vol. 32, no. 6, pp. 1109-1121, Dec. 1984.
[17] I. Cohen, and B. Baruch, "Speech enhancement for non-stationary noise environments," Signal Processing, vol. 81, no. 11, pp. 2403-2418, Nov. 2001.
[18] R. Santana, L. Zao., and R. Coelho, “Ambient Noise Classification for Automatic Speaker Identification,” in Proc. International Telecommunications Symposium, 2010.
[19] C. Breithaupt, T. Gerkmann, and R. Martin “Cepstral smoothing of spectral filter gains for speech enhancement without musical noise” IEEE. Signal Processing Letters, vol. 14, no. 12, pp. 1036-1039, Dec. 2007.
[20] I. Cohen, "Noise spectrum estimation in adverse environments: improved minima controlled recursive averaging," IEEE. Transactions on Speech and Audio Processing, vol. 11, no. 5, pp. 466-475, Sept. 2003.
[21] J. S. Erkelens and R. Heusdens, "Fast noise tracking based on recursive smoothing of mmse noise power estimates," in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing, 2008, pp. 4873-4876.
[22] J. M. Kum, Y. S. Park, and J. H. Chang, "Improved minima controlled recursive averaging technique using conditional maximum a posteriori criterion for speech enhancement," Digital Signal Processing, vol. 20, no. 6, pp. 1572-1578, Dec. 2010.
[23] N.Fan, J. Rosca, and R. Balan, "Speech noise estimation using enhanced minima controlled recursive averaging," in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing, 2007, vol. 4, pp. 581-584.
[24] T. D. Tran, Q. C. Nguyen, and D. K. Nguyen, "Speech enhancement using modified IMCRA and OMLSA methods," in Proc. IEEE International Conference on Communications and Electronics, 2010, pp. 195-200.
[25] C. Li, and W. Liu, "A noise estimation method based on speech presence probability and spectral sparseness," in Proc. INTERSPEECH, 2011, pp. 1197-1120.
[26] Y. H. Son, and S. M. Lee, "Improved speech absence probability estimation based on environmental noise classification," Journal of Central South University, vol. 19, no. 9, pp. 2548-2553, Sept. 2012.
[27] T. Gerkmann, C. Breithaupt, and R. Martin, "Improved a posteriori speech presence probability estimation based on a likelihood ratio with fixed priors," IEEE Transactions on Audio Speech and Language Processing, vol. 16, no. 5, July 2008.
[28] C. Li, and W. Liu, "Improved a posteriori speech presence probability estimation based on cepstro-temporal smoothing and time-frequency correlation," in Proc. INTERSPEECH, 2011, pp. 1201-1204.
[29] Y. S. Park, and J. H. Chang, "A probabilistic combination method of minimum statistics and soft decision for robust noise power estimation in speech enhancement," IEEE. Signal Processing Letters, vol.15, pp. 95-98, Jan. 2008.
[30] W. Lee, , J. H. Song, and J. H. Chang, "Minima-controlled speech presence uncertainty tracking method for speech enhancement," Signal Processing, vol. 91, no. 1, pp. 155-161, Jan. 2011.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊
 
系統版面圖檔 系統版面圖檔