【摘要】：語音作為人們交流和表達情感的一種重要媒介,在日常生活中卻總是受到噪聲的干擾,因此我們需要對混入背景噪聲的干凈語音進行語音增強。語音增強算法的最終目標就是對背景噪聲進行抑制,改善語音聽覺質(zhì)量,同時保證一定的語音可懂度。人們對語音增強算法的研究已有半個多世紀的歷史,這期間涌現(xiàn)過很多經(jīng)典的語音增強算法,如譜減法、維納濾波法、幅度譜最小均方誤差算法等,且一直為人們所研究。這些算法在高信噪比平穩(wěn)噪聲下,通常可以取得良好的語音增強效果,但是在低信噪比非平穩(wěn)噪聲下,語音增強效果卻不盡人意,還有很多需要攻克的難題。所以,在低信噪比非平穩(wěn)噪聲場景下對帶噪語音信號進行語音增強仍是當前國內(nèi)外學者研究的一個熱點。本文主要針對對數(shù)譜最小均方誤差(Log-Spectral Amplitude Minimum Mean-Square Error,LSA-MMSE)算法以及信號子空間算法在低信噪比場景下存在的缺陷提出改進。主要研究工作如下:首先,提出了低信噪比場景下改進的LSA-MMSE算法。針對傳統(tǒng)LSA-MMSE算法在強噪聲環(huán)境下語音信息完整保留效果不佳,本文將Loizou等人提出的大部分語音增強算法對帶噪語音進行增強處理后普遍存在兩種不同類型失真,這一理論應(yīng)用到LSA-MMSE算法中。基于這一理論對LSA-MMSE算法提出了改進。以往學者總是將區(qū)域Ⅰ的衰減失真和區(qū)域Ⅱ小于或等于6.02dB的放大失真所對應(yīng)的幅度譜歸為一類處理,認為這樣不會對語音信息的完整保留造成影響,研究表明這樣反而會產(chǎn)生更多殘留噪聲。基于這一點,本文對衰減失真對應(yīng)的幅度譜、小于等于6.02dB放大失真對應(yīng)的幅度譜、大于6.02dB放大失真所對應(yīng)的幅度譜分別采取不同程度的向下約束。另外,低信噪比場景下先驗信噪比和增益函數(shù)的估計誤差對語音增強效果有很大影響,改進的LSA-MMSE算法中分別對它們進行了調(diào)整。實驗結(jié)果表明,低信噪比場景下本文算法更好地保留了語音的主要信息,同時有效抑制了低頻部分的背景噪聲。其次,提出了低信噪比場景下改進的信號子空間語音增強算法。子空間算法有著良好的去噪效果,但在低信噪比環(huán)境下仍然殘留較多噪聲。本文首先把濾除小于零的特征值及與之對應(yīng)的特征向量,這一方法應(yīng)用到傳統(tǒng)子空間算法中,以達到優(yōu)化信號子空間的效果。同時提出使用共享正弦多窗譜的協(xié)方差估計方法減小估計誤差和計算復(fù)雜度。最后對估計的干凈語音引入維納濾波函數(shù)進行修正。實驗結(jié)果表明,在5種常見噪聲的低信噪比場景下,改進算法能有效去除背景噪聲,改善語音聽覺質(zhì)量,其語音增強效果整體優(yōu)于改進前的算法。
[Abstract]:As an important medium for people to communicate and express their emotions, speech is always disturbed by noise in daily life. Therefore, we need to enhance the voice of clean speech mixed with background noise. The final goal of speech enhancement algorithm is to suppress background noise, improve the quality of speech hearing, and ensure a certain degree of speech intelligibility. Speech enhancement algorithms have been studied for more than half a century. During this period, many classical speech enhancement algorithms have emerged, such as spectral subtraction, Wiener filter, amplitude spectrum minimum mean square error algorithm and so on. These algorithms can usually achieve good speech enhancement effect under high SNR stationary noise, but in low SNR non-stationary noise, the speech enhancement effect is not satisfactory, and there are still many difficult problems to be solved. Therefore, speech enhancement of noisy speech signal in low SNR non-stationary noise scene is still a hot research topic at home and abroad. This paper focuses on the improvement of the logarithmic spectrum minimum mean square error (Log-Spectral Amplitude Minimum Mean-Square Error,LSA-MMSE) algorithm and the signal subspace algorithm in low SNR scenarios. The main research work is as follows: firstly, an improved LSA-MMSE algorithm in low SNR scenario is proposed. Because the traditional LSA-MMSE algorithm can not preserve the speech information completely in the environment of strong noise, there are two different types of distortion after most of the speech enhancement algorithms proposed by Loizou et al are used to enhance the noisy speech. This theory is applied to LSA-MMSE algorithm. Based on this theory, the LSA-MMSE algorithm is improved. In the past, the attenuation distortion of region I and the amplitudes of region 鈪，

本文編號：2363390