使用迭代溫妮濾波器於線性預估模型之語音增強

Speech Enhancement Using Iterative Wiener Filter in the Linear Predictive Model

蘇建彰(Jian-Jhang Su)

指導教授 ： 簡福榮

國立臺北科技大學/電資學院/電機工程系研究所/碩士(2012年)

摘要

語音信號會受背景雜訊影響而導致整體品質和辨識率降低。語音增強系統的主要目的為降低背景雜訊對語音訊號的影響，並且使增強後的語音訊號有較低的語音失真。而語音增強是一種通常會用在語音傳輸與語音辨識的技術，從含有雜訊的語音中，藉由雜訊追蹤演算法，來重建乾淨的語音。而語音增強的方法有很多種，如以濾波器技術、頻譜回復技術與基於模型技術等語音增強技術。
本文使用了線性預估模型之三種語音增強方法與三種雜訊追蹤方法，其中語音增強方法包括卡爾曼濾波器(KF)、修正卡爾曼濾波器(MKF)、迭代溫妮濾波器(IWF)，雜訊追蹤方法包括最小統計法(MS)、最小控制遞迴平均法(MCRA)與改善式最小控制遞迴平均法(IMCRA)。以上的方法互相搭配，其實驗結果將與濾波器技術之語音增強中的溫妮濾波器(WF)和頻譜回復技術之語音增強中的最大概似頻譜振幅(MLSA)比較。實驗結果顯示，與溫妮濾波器和最大概似頻譜振幅的結果相比，線性預估模型之迭代溫妮濾波器可以獲得比較好的改善，又以使用線性預估模型之迭代溫妮濾波器搭配MCRA雜訊追蹤法，可以獲得最明顯的效果。

關鍵字

語音增強 ； 雜訊追蹤 ； 線性預估模型

並列摘要

Speech signals are tend to decrease the speech quality when corrupted by background noises. The aim of speech enhancement is to reduce the background noise from a noisy speech signal while keeping the speech distortion as low as possible. And this Speech technique is usually used in speech transmission and speech recognition that recovers the clean speech from noisy speech by using a noise tracking algorithm. There are three categories for speech enhancement including filtering techniques, spectral restoration techniques, and speech model techniques.
In this thesis three speech enhancement methods based on linear predictive model are investigated that includes Kalman filter (KF), modified Kalman filter (MKF), and iterative Wiener filter (IWF). Two other famous methods the Wiener filter (WF) method and maximum-likelihood spectral amplitude (MLSA) method are also included for comparison. In the experiments, each enhancement method incorporates with three well-known noise tracking algorithms, including minimum statistics (MS), minima controlled recursive averaging (MCRA), and improved minima controlled recursive averaging (IMCRA) for recovering clean speech. The experimental results show that compared with the Wiener filter and maximum-likelihood spectral amplitude, the proposed iterative Wiener filter in the linear predictive model provides superior performance. Among all combinations, the latter with MCRA noise tracking can achieves the most excellent results.

並列關鍵字

Speech Enhancement ； Noise Tracking ； Linear Predictive Model

參考文獻

[2] J. D. Gibson, B. Koo and S. D. Gray, “Filtering of colored noise for speech enhancement and coding,” IEEE Transactions on Signal Processing, vol. 39, no. 8, Aug. 1991, pp. 1732-1742.

[4] M. Gabrea, “Adaptive Kalman filtering-based speech enhancement algorithm,” Canadian Conference on Electrical and Computer Engineering, vol. 1, 2001, pp. 521-526.

[5] J. Chen, Fundamentals of Noise Reduction in Spring Handbook of Speech Processing, Chapter 43, Springer, 2008.

[7] S. V. Vaseghi, Advanced Digital Signal Processing and Noise Reduction, Second Edition, Chapter 8, 2000.

[8] V. Grancharov, J. H. Plasberg, J. Samuelsson and W. B. Kleijn, “Generalized Postfilter for Speech Quality Enhancement,” IEEE Transactions on Audio, Speech, and Language Processing, vol. 16, no. 1, Jan. 2008, pp. 57 - 64.