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

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最小控制遞回平均雜訊估測法，根據不同的雜訊類型、頻譜中雜訊含量的多寡、及雜訊頻譜分佈情形不同，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 level 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.