臺灣博碩士論文加值系統

本論文提出麥克風陣列與目標干擾比(Target-to-Jammer, TJR)的語音活動特徵搭配混和高斯模型(Gaussian mixture model, GMM)與目標干擾比的語音活動特徵搭配最小控制遞迴平均法 ( Minima Controlled Recursive Averaging , MCRA )的兩種穩健型語音活動偵測方法。並且將此方法與長時間訊號變動程度 (Long-Term Signal Variability)和訊號能量做比較，在大部分的狀況下使用干擾比當語音活動偵測的正確率都高於其它特徵。當訊雜比越來越低的時候，目標干擾比(Target-to-Jammer, TJR)的優勢會越來越顯著。

In this thesis, two methods detecting voice activity by microphone array are proposed. The first method combines target-to-jammer ratio with minima controlled recursive averaging. The second method combines target-to-jammer ratio with Gaussian mixture model. These two methods are compared with signal energy method and long-term signal variability method. In most situations, the correct rate by using target-to-jammer ratio is higher than other features. When signal to noise ratio (SNR) gets lower, the target-to-jammer ration method will be more robust than using other features.

摘 要 ..................................................... I
ABSTRACT ................................................... II
誌謝 .......................................................III
圖目錄 ..................................................... V
表目錄 ....................................................VIII
第一章 緒論 ............................................... 1
1.1 研究動機 ............................................. 1
1.2 研究目標 ............................................. 1
1.3 文獻回顧 ............................................. 2
1.4 論文架構 ............................................. 3
第二章 適應性陣列訊號處理 .................................. 4
2.1 陣列訊號處理 .......................................... 4
2.2 適應性訊號處理 ........................................ 6
2.3 適應性空間濾波器：TRANSFER FUNCTIONS GENERALIZED
SIDELOBE CANCELER (GSC) .................................... 7
第三章 語音活動偵測 ........................................ 12
3.1 語音活動偵測 .......................................... 12
3.2 TARGET-TO-JAMMER RATIO ................................ 13
3.3 長時間訊號變動程度 ( LONG-TERM SIGNAL VARIABILITY) .... 17
3.4 最小控制遞迴平均法 ( MINIMA CONTROLLED RECURSIVE
AVERAGING , MCRA ) ......................................... 19
3.5 兩個元件的混和高斯模型 (GAUSSIAN MIXTURE MODEL) ...... 22
3.6 延續機制( HANG OVER SCHEME) ........................... 25
第四章 實驗結果與分析 ...................................... 27
4.1 TJR 和 LTSV 實驗結果與分析 ............................ 33
第五章 結論 ............................................... 65
5.1 研究成果 .............................................. 65
5.2 未來展望 .............................................. 65
參考文獻 ................................................... 66

[1] J. A. Haigh and J. S. Mason, “Robust voice activity detection using cepstral features,” in Proc. IEEE TENCON, China, 1993, pp. 321–324
[2] Ishizuka, K. et al., "Study of noise robust voice activity detection based on periodic component to aperiodic component ratio," Proc. of SAPA '06, pp.65-70, Sept. 2006
[3] J. L. Shen, J. W. Hung, and L. S. Lee, "Robust entropy-based endpoint detection for speech recognition in noisy environments", ICSLP, 1998
[4] Prasanta Kumar Ghosh, Andreas Tsiarts, Shirkanth Narayanan, “Robust voice activity detection using long-term signal variability, ” IEEE Transactions on audio, speech, and language processing, VOL. 19, NO. 3, MARCH 2011
[5] J. Chen and W. Ser, “Speech Detection Using Microphone Array”, Electronic Letters, Vol. 36, No. 2, pp. 181-182, Jan. 2000
[6] I. Potamitis, “Estimation of Speech Presence Probability in the field of Microphone Array,” IEEE Signal Processing Letters, Vol. 11, No. 12, pp. 956-959, December 2004
[7]Regine Le Bouquin-Jeannes, Gerard Faucon, “Study of a voice activity detector and its influence on a noise reduction system,” Speech Communication, Vol. 16, pp. 245-254, 1995
[8] J. E. Rubio, K. Ishizuka, H. Sawada, S. Araki, T. Nakatani, and M. Fujimoto, “Two-microphone voice activity detection based on the homogeneity of the direction arrival estimates,” in Proc. IEEE Intl. Conf. Acoust., Speech, Signal Process. ICASSP) , pp.385-388, 2007
[9] Michael W. Hoffman, Zhao Li, and Devajani Khataniar, “GSC-Based Spataial Voice Activity Detection for Enhanced Speech Coding in the presence of competing speech,” IEEE Transactions on speech and audio processing, VOL. 9, NO. 2, MARCH 2001
[10] J. Sohn and W. Sung, “A voice activity detector employing soft decision based noise spectrum adaptation,” in Proc. Int. Conf. Acoust., Speech, Signal Process., vol. 1, Seattle, WA, 1998, pp. 365–368
[11] S. Gazor, W. Zhang, “A soft voice activity detector based on a Laplacian-Gaussian model,” IEEE Trans. Speech Audio Process., vol. 11, no. 5, pp. 498–505, Sep. 2003
[12] R. Tahmasbi, S. Rezaei, “Change point detection in GARCH models for voice activity detection,” IEEE Trans. Audio Speech Lang. Process., vol.16, no. 5, pp. 1038–1046, July 2008
[13] O. L. Frost, III, “An algorithm for linearly constrained adaptive array processing,” Proc. IEEE, vol. 60, pp. 926–935, Jan. 1972
[14] L. J. Griffiths and C. W. Jim, “An alternative approach to linearly constrained adaptive beamforming,” IEEE Trans. Antennas Propagat., vol. AP-30, pp. 27–34, Jan. 1982
[15] Sharon Gannot; David Burshtein; Ehud Weinstein, “Signal enhancement using beamforming and Nonstationarity with applications to speech, ” IEEE Transactions on signal processing, Vol. 49, NO. 8, August 2001
[16] I. Cohen and B. Berdugo, "Speech enhancement for nonstationary noise environments", Signal Process. , vol. 81, pp.2403 - 2418 , 2001
[17] Dongwen Ying, Yonghond Yan, Jianwu Dang, Frank K. Sonng, “Voice activity detection based on an unsupervised learning framework, ” Audio, Speech, and Language Processing, IEEE Transactions, 2011
[18] Iain A. McCowan, Herve Bourlard, “Microphone array post-filter basaed on noise field coherence,” IEEE Transactions on speece and audio processing, VOL. 11, NO6, November 2003
[19] I. Cohen and B. Berdugo, "Speech enhancement for nonstationary noise environments", Signal Process. , vol. 81, pp.2403 - 2418 , 2001.
[20] J. Ramirez, T. C. Segura and etc., “Efficient voice activity detection algorithms using long-terms speech information, ” Speech commun., vol.42, no3, pp. 271-287, 2004
[21] K. Ishizuka and T. Nakatani, “Study of noise robust voice activity detection based on periodic component to aperiodic component ratio,” Proc. SAPA ’06, Pittsburgh, USA, 2006, pp. 65-70